diff --git a/OAR.2073614.stderr b/OAR.2073614.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..fb24beae5afe1d77fbc9d36af38e2f3cefc52aa5
--- /dev/null
+++ b/OAR.2073614.stderr
@@ -0,0 +1,14 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 90, in main
+    trainer.train(train_loader, args.epochs)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 116, in train
+    mean_epoch_loss, recon_loss, kl_loss, prediction_loss, prediction_random_continue_loss = self._train_epoch(data_loader)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 177, in _train_epoch
+    iter_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter = self._train_iteration(data, label)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 227, in _train_iteration
+    pred_loss_iter = pred_loss.item()
+AttributeError: 'float' object has no attribute 'item'
diff --git a/OAR.2073614.stdout b/OAR.2073614.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..66020866a81aa2d0329c58c710a2dafcc3ab7cf4
--- /dev/null
+++ b/OAR.2073614.stdout
@@ -0,0 +1,47 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=90000, experiment_name='VAE_bs_64_ls_30', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=30, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=60, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=30, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 780735
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last (iter 151)'
diff --git a/OAR.2073615.stderr b/OAR.2073615.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..fb24beae5afe1d77fbc9d36af38e2f3cefc52aa5
--- /dev/null
+++ b/OAR.2073615.stderr
@@ -0,0 +1,14 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 90, in main
+    trainer.train(train_loader, args.epochs)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 116, in train
+    mean_epoch_loss, recon_loss, kl_loss, prediction_loss, prediction_random_continue_loss = self._train_epoch(data_loader)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 177, in _train_epoch
+    iter_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter = self._train_iteration(data, label)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 227, in _train_iteration
+    pred_loss_iter = pred_loss.item()
+AttributeError: 'float' object has no attribute 'item'
diff --git a/OAR.2073615.stdout b/OAR.2073615.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..0a8efe970b046805d80801bac8026ab605adcb85
--- /dev/null
+++ b/OAR.2073615.stdout
@@ -0,0 +1,47 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64_ls_40', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=40, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=80, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=40, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 788435
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last (iter 279)'
diff --git a/OAR.2073616.stderr b/OAR.2073616.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..fb24beae5afe1d77fbc9d36af38e2f3cefc52aa5
--- /dev/null
+++ b/OAR.2073616.stderr
@@ -0,0 +1,14 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 90, in main
+    trainer.train(train_loader, args.epochs)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 116, in train
+    mean_epoch_loss, recon_loss, kl_loss, prediction_loss, prediction_random_continue_loss = self._train_epoch(data_loader)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 177, in _train_epoch
+    iter_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter = self._train_iteration(data, label)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 227, in _train_iteration
+    pred_loss_iter = pred_loss.item()
+AttributeError: 'float' object has no attribute 'item'
diff --git a/OAR.2073616.stdout b/OAR.2073616.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..8279477f7f6f0bc801dd1e118ae95a149724d96b
--- /dev/null
+++ b/OAR.2073616.stdout
@@ -0,0 +1,47 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64_ls_50', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=50, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=100, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=50, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 796135
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last (iter 274)'
diff --git a/OAR.2073617.stderr b/OAR.2073617.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..b800dbc96d0955b2893e858442aeea11bcc338e5
--- /dev/null
+++ b/OAR.2073617.stderr
@@ -0,0 +1,10 @@
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 417, in load_checkpoint
+    self.mean_epoch_loss = checkpoint['loss']
+KeyError: 'loss'
diff --git a/OAR.2073617.stdout b/OAR.2073617.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..e943950ae7124cf77d6991cee93fa200316bb8fb
--- /dev/null
+++ b/OAR.2073617.stdout
@@ -0,0 +1,46 @@
+Namespace(batch_size=256, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='beta_VAE_bs_256', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 765335
+don't use continuous capacity
diff --git a/OAR.2073618.stderr b/OAR.2073618.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..098b08da0aaa87bef5c2bd27253657ef66d93589
--- /dev/null
+++ b/OAR.2073618.stderr
@@ -0,0 +1,20 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py:26: UserWarning: 
+    There is an imbalance between your GPUs. You may want to exclude GPU 1 which
+    has less than 75% of the memory or cores of GPU 0. You can do so by setting
+    the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES
+    environment variable.
+  warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 90, in main
+    trainer.train(train_loader, args.epochs)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 116, in train
+    mean_epoch_loss, recon_loss, kl_loss, prediction_loss, prediction_random_continue_loss = self._train_epoch(data_loader)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 177, in _train_epoch
+    iter_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter = self._train_iteration(data, label)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 227, in _train_iteration
+    pred_loss_iter = pred_loss.item()
+AttributeError: 'float' object has no attribute 'item'
diff --git a/OAR.2073618.stdout b/OAR.2073618.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..1202a570fecb38c4eeeeabb6be079490e99ebf35
--- /dev/null
+++ b/OAR.2073618.stdout
@@ -0,0 +1,47 @@
+Namespace(batch_size=64, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='beta_VAE_bs_64', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+Tesla K40c
+Tesla K20m
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 765335
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last (iter 797)'
diff --git a/OAR.2073619.stderr b/OAR.2073619.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..fb24beae5afe1d77fbc9d36af38e2f3cefc52aa5
--- /dev/null
+++ b/OAR.2073619.stderr
@@ -0,0 +1,14 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 90, in main
+    trainer.train(train_loader, args.epochs)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 116, in train
+    mean_epoch_loss, recon_loss, kl_loss, prediction_loss, prediction_random_continue_loss = self._train_epoch(data_loader)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 177, in _train_epoch
+    iter_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter = self._train_iteration(data, label)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 227, in _train_iteration
+    pred_loss_iter = pred_loss.item()
+AttributeError: 'float' object has no attribute 'item'
diff --git a/OAR.2073619.stdout b/OAR.2073619.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..67e7361c72d348e4207d8f7d180714c73dffb53a
--- /dev/null
+++ b/OAR.2073619.stdout
@@ -0,0 +1,47 @@
+Namespace(batch_size=256, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_256', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce GTX 1080 Ti
+GeForce GTX 1080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 765335
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last (iter 728)'
diff --git a/OAR.2073620.stderr b/OAR.2073620.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..fb24beae5afe1d77fbc9d36af38e2f3cefc52aa5
--- /dev/null
+++ b/OAR.2073620.stderr
@@ -0,0 +1,14 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 90, in main
+    trainer.train(train_loader, args.epochs)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 116, in train
+    mean_epoch_loss, recon_loss, kl_loss, prediction_loss, prediction_random_continue_loss = self._train_epoch(data_loader)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 177, in _train_epoch
+    iter_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter = self._train_iteration(data, label)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 227, in _train_iteration
+    pred_loss_iter = pred_loss.item()
+AttributeError: 'float' object has no attribute 'item'
diff --git a/OAR.2073620.stdout b/OAR.2073620.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..3e687bb7cce3ed2b837b89e0bcbc563b8ab2477f
--- /dev/null
+++ b/OAR.2073620.stdout
@@ -0,0 +1,47 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce GTX 1080 Ti
+GeForce GTX 1080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 765335
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last (iter 929)'
diff --git a/OAR.2073621.stderr b/OAR.2073621.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..fb24beae5afe1d77fbc9d36af38e2f3cefc52aa5
--- /dev/null
+++ b/OAR.2073621.stderr
@@ -0,0 +1,14 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 90, in main
+    trainer.train(train_loader, args.epochs)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 116, in train
+    mean_epoch_loss, recon_loss, kl_loss, prediction_loss, prediction_random_continue_loss = self._train_epoch(data_loader)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 177, in _train_epoch
+    iter_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter = self._train_iteration(data, label)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 227, in _train_iteration
+    pred_loss_iter = pred_loss.item()
+AttributeError: 'float' object has no attribute 'item'
diff --git a/OAR.2073621.stdout b/OAR.2073621.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..ad3dc39bb9c9125ad93ff2828f2426b9cb2049ae
--- /dev/null
+++ b/OAR.2073621.stdout
@@ -0,0 +1,47 @@
+Namespace(batch_size=64, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='beta_VAE_bs_64_ls_15', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=15, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce GTX 1080 Ti
+GeForce GTX 1080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=30, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=15, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 769185
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last (iter 418)'
diff --git a/OAR.2073622.stderr b/OAR.2073622.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..fb24beae5afe1d77fbc9d36af38e2f3cefc52aa5
--- /dev/null
+++ b/OAR.2073622.stderr
@@ -0,0 +1,14 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 90, in main
+    trainer.train(train_loader, args.epochs)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 116, in train
+    mean_epoch_loss, recon_loss, kl_loss, prediction_loss, prediction_random_continue_loss = self._train_epoch(data_loader)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 177, in _train_epoch
+    iter_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter = self._train_iteration(data, label)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 227, in _train_iteration
+    pred_loss_iter = pred_loss.item()
+AttributeError: 'float' object has no attribute 'item'
diff --git a/OAR.2073622.stdout b/OAR.2073622.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..8f812fd6f98e66ea3d9a5c1980052c12aa6513e4
--- /dev/null
+++ b/OAR.2073622.stdout
@@ -0,0 +1,47 @@
+Namespace(batch_size=64, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='beta_VAE_bs_64_ls_20', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=20, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=40, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=20, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 773035
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_20/checkpoints/last (iter 390)'
diff --git a/OAR.2073623.stderr b/OAR.2073623.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..fb24beae5afe1d77fbc9d36af38e2f3cefc52aa5
--- /dev/null
+++ b/OAR.2073623.stderr
@@ -0,0 +1,14 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 90, in main
+    trainer.train(train_loader, args.epochs)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 116, in train
+    mean_epoch_loss, recon_loss, kl_loss, prediction_loss, prediction_random_continue_loss = self._train_epoch(data_loader)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 177, in _train_epoch
+    iter_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter = self._train_iteration(data, label)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 227, in _train_iteration
+    pred_loss_iter = pred_loss.item()
+AttributeError: 'float' object has no attribute 'item'
diff --git a/OAR.2073623.stdout b/OAR.2073623.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..a81af3d1f14cb11e862afe026c721e7b3dcd7de2
--- /dev/null
+++ b/OAR.2073623.stdout
@@ -0,0 +1,47 @@
+Namespace(batch_size=64, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='beta_VAE_bs_64_ls_5', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=5, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=10, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=5, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 761485
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last (iter 423)'
diff --git a/OAR.2073624.stderr b/OAR.2073624.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..fb24beae5afe1d77fbc9d36af38e2f3cefc52aa5
--- /dev/null
+++ b/OAR.2073624.stderr
@@ -0,0 +1,14 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 90, in main
+    trainer.train(train_loader, args.epochs)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 116, in train
+    mean_epoch_loss, recon_loss, kl_loss, prediction_loss, prediction_random_continue_loss = self._train_epoch(data_loader)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 177, in _train_epoch
+    iter_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter = self._train_iteration(data, label)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 227, in _train_iteration
+    pred_loss_iter = pred_loss.item()
+AttributeError: 'float' object has no attribute 'item'
diff --git a/OAR.2073624.stdout b/OAR.2073624.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..d48a91da485def2e078ed07d7640428a69258cc1
--- /dev/null
+++ b/OAR.2073624.stdout
@@ -0,0 +1,47 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64_ls_5', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=5, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+Tesla K80
+Tesla K80
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=10, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=5, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 761485
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last (iter 469)'
diff --git a/OAR.2073625.stderr b/OAR.2073625.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..fb24beae5afe1d77fbc9d36af38e2f3cefc52aa5
--- /dev/null
+++ b/OAR.2073625.stderr
@@ -0,0 +1,14 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 90, in main
+    trainer.train(train_loader, args.epochs)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 116, in train
+    mean_epoch_loss, recon_loss, kl_loss, prediction_loss, prediction_random_continue_loss = self._train_epoch(data_loader)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 177, in _train_epoch
+    iter_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter = self._train_iteration(data, label)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 227, in _train_iteration
+    pred_loss_iter = pred_loss.item()
+AttributeError: 'float' object has no attribute 'item'
diff --git a/OAR.2073625.stdout b/OAR.2073625.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..8334200c81d4bd2e046d56e1f730946db9b2f6a1
--- /dev/null
+++ b/OAR.2073625.stdout
@@ -0,0 +1,47 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64_ls_15', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=15, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=30, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=15, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 769185
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last (iter 473)'
diff --git a/OAR.2073626.stderr b/OAR.2073626.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..098b08da0aaa87bef5c2bd27253657ef66d93589
--- /dev/null
+++ b/OAR.2073626.stderr
@@ -0,0 +1,20 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py:26: UserWarning: 
+    There is an imbalance between your GPUs. You may want to exclude GPU 1 which
+    has less than 75% of the memory or cores of GPU 0. You can do so by setting
+    the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES
+    environment variable.
+  warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 90, in main
+    trainer.train(train_loader, args.epochs)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 116, in train
+    mean_epoch_loss, recon_loss, kl_loss, prediction_loss, prediction_random_continue_loss = self._train_epoch(data_loader)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 177, in _train_epoch
+    iter_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter = self._train_iteration(data, label)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 227, in _train_iteration
+    pred_loss_iter = pred_loss.item()
+AttributeError: 'float' object has no attribute 'item'
diff --git a/OAR.2073626.stdout b/OAR.2073626.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..0320def299d5bf92924e7e9c58dc9e5aaa26c6bc
--- /dev/null
+++ b/OAR.2073626.stdout
@@ -0,0 +1,47 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64_ls_20', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=20, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+Tesla K40c
+Tesla K20m
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=40, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=20, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 773035
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last (iter 306)'
diff --git a/OAR.2073627.stderr b/OAR.2073627.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..b800dbc96d0955b2893e858442aeea11bcc338e5
--- /dev/null
+++ b/OAR.2073627.stderr
@@ -0,0 +1,10 @@
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 417, in load_checkpoint
+    self.mean_epoch_loss = checkpoint['loss']
+KeyError: 'loss'
diff --git a/OAR.2073627.stdout b/OAR.2073627.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..3fe0224e9c4c7307bf82327141400a998bf48f00
--- /dev/null
+++ b/OAR.2073627.stdout
@@ -0,0 +1,46 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64_ls_10_lr_5e_4', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=5e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+Tesla K80
+Tesla K80
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 765335
+don't use continuous capacity
diff --git a/OAR.2073628.stderr b/OAR.2073628.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..098b08da0aaa87bef5c2bd27253657ef66d93589
--- /dev/null
+++ b/OAR.2073628.stderr
@@ -0,0 +1,20 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py:26: UserWarning: 
+    There is an imbalance between your GPUs. You may want to exclude GPU 1 which
+    has less than 75% of the memory or cores of GPU 0. You can do so by setting
+    the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES
+    environment variable.
+  warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 90, in main
+    trainer.train(train_loader, args.epochs)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 116, in train
+    mean_epoch_loss, recon_loss, kl_loss, prediction_loss, prediction_random_continue_loss = self._train_epoch(data_loader)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 177, in _train_epoch
+    iter_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter = self._train_iteration(data, label)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 227, in _train_iteration
+    pred_loss_iter = pred_loss.item()
+AttributeError: 'float' object has no attribute 'item'
diff --git a/OAR.2073628.stdout b/OAR.2073628.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..97ef0d150e4bf2a60306ef46367a88385cd972f0
--- /dev/null
+++ b/OAR.2073628.stdout
@@ -0,0 +1,47 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64_conv_64_64_128_128', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=64, nb_filter_conv2=64, nb_filter_conv3=128, nb_filter_conv4=128, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+Tesla K40c
+Tesla K20m
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(128, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(128, 512, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=512, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=512, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(512, 128, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(128, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(128, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(64, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 3037975
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last (iter 86)'
diff --git a/OAR.2073629.stderr b/OAR.2073629.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..a05bd0cf67e59c97a5ce1817b6b36aa1d39a5602
--- /dev/null
+++ b/OAR.2073629.stderr
@@ -0,0 +1,18 @@
+
0it [00:00, ?it/s]
  0%|          | 0/26421880 [00:00<?, ?it/s]
  2%|▏         | 458752/26421880 [00:00<00:05, 4474569.32it/s]
 20%|█▉        | 5201920/26421880 [00:00<00:03, 6143480.35it/s]
 42%|████▏     | 11124736/26421880 [00:00<00:01, 8375378.25it/s]
 67%|██████▋   | 17571840/26421880 [00:00<00:00, 11333282.55it/s]
 81%|████████  | 21405696/26421880 [00:00<00:00, 14153805.20it/s]
26427392it [00:00, 34157672.34it/s]                              
+
0it [00:00, ?it/s]
32768it [00:00, 377753.89it/s]
+
0it [00:00, ?it/s]
  1%|          | 40960/4422102 [00:00<00:11, 383863.09it/s]
 43%|████▎     | 1892352/4422102 [00:00<00:04, 543543.42it/s]
4423680it [00:00, 18197425.40it/s]                           
+
0it [00:00, ?it/s]
8192it [00:00, 155806.69it/s]
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 416, in load_checkpoint
+    checkpoint = torch.load(file_path)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 426, in load
+    return _load(f, map_location, pickle_module, **pickle_load_args)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 603, in _load
+    magic_number = pickle_module.load(f, **pickle_load_args)
+_pickle.UnpicklingError: invalid load key, 'v'.
diff --git a/OAR.2073629.stdout b/OAR.2073629.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..941eb758629f7b4dc090749cc5ee5095112388dd
--- /dev/null
+++ b/OAR.2073629.stdout
@@ -0,0 +1,53 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='fashion_data', disc_capacity=None, epochs=9000000, experiment_name='VAE_bs_64_ls_30', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=30, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=False, lr=0.0001, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+creare new diretory experiment: fashion_data/VAE_bs_64_ls_30
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to ../data/fashion_data/FashionMNIST/raw/train-images-idx3-ubyte.gz
+Extracting ../data/fashion_data/FashionMNIST/raw/train-images-idx3-ubyte.gz to ../data/fashion_data/FashionMNIST/raw
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to ../data/fashion_data/FashionMNIST/raw/train-labels-idx1-ubyte.gz
+Extracting ../data/fashion_data/FashionMNIST/raw/train-labels-idx1-ubyte.gz to ../data/fashion_data/FashionMNIST/raw
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to ../data/fashion_data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz
+Extracting ../data/fashion_data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz to ../data/fashion_data/FashionMNIST/raw
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz to ../data/fashion_data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz
+Extracting ../data/fashion_data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to ../data/fashion_data/FashionMNIST/raw
+Processing...
+Done!
+load dataset: fashion_data, with: 60032 train images of shape: (1, 32, 32)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(1, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=60, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=30, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 745853
+don't use continuous capacity
diff --git a/OAR.2073630.stderr b/OAR.2073630.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..58928426168a8079560ed30fb20401078b2ad5cf
--- /dev/null
+++ b/OAR.2073630.stderr
@@ -0,0 +1,17 @@
+
0it [00:00, ?it/s]
  0%|          | 0/26421880 [00:00<?, ?it/s]
  2%|▏         | 434176/26421880 [00:00<00:06, 4139831.03it/s]
 20%|█▉        | 5210112/26421880 [00:00<00:03, 5684392.16it/s]
 43%|████▎     | 11468800/26421880 [00:00<00:01, 7791554.56it/s]
 67%|██████▋   | 17588224/26421880 [00:00<00:00, 10554194.82it/s]
 81%|████████  | 21323776/26421880 [00:00<00:00, 13404568.69it/s]
26427392it [00:00, 32585926.59it/s]                              
+
0it [00:00, ?it/s]
32768it [00:00, 380307.52it/s]
+
0it [00:00, ?it/s]
  1%|          | 40960/4422102 [00:00<00:11, 367976.57it/s]
 32%|███▏      | 1425408/4422102 [00:00<00:05, 519533.42it/s]
4423680it [00:00, 14307670.56it/s]                           
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 416, in load_checkpoint
+    checkpoint = torch.load(file_path)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 426, in load
+    return _load(f, map_location, pickle_module, **pickle_load_args)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 603, in _load
+    magic_number = pickle_module.load(f, **pickle_load_args)
+_pickle.UnpicklingError: invalid load key, 'v'.
diff --git a/OAR.2073630.stdout b/OAR.2073630.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..a5a252ea06c9f703d2b260b4a9c0fe79317f7904
--- /dev/null
+++ b/OAR.2073630.stdout
@@ -0,0 +1,53 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='fashion_data', disc_capacity=None, epochs=9000000, experiment_name='VAE_bs_64_ls_40', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=40, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=False, lr=0.0001, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+creare new diretory experiment: fashion_data/VAE_bs_64_ls_40
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to ../data/fashion_data/FashionMNIST/raw/train-images-idx3-ubyte.gz
+Extracting ../data/fashion_data/FashionMNIST/raw/train-images-idx3-ubyte.gz to ../data/fashion_data/FashionMNIST/raw
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to ../data/fashion_data/FashionMNIST/raw/train-labels-idx1-ubyte.gz
+Extracting ../data/fashion_data/FashionMNIST/raw/train-labels-idx1-ubyte.gz to ../data/fashion_data/FashionMNIST/raw
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to ../data/fashion_data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz
+Extracting ../data/fashion_data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz to ../data/fashion_data/FashionMNIST/raw
+Using downloaded and verified file: ../data/fashion_data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz
+Extracting ../data/fashion_data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to ../data/fashion_data/FashionMNIST/raw
+Processing...
+Done!
+load dataset: fashion_data, with: 60032 train images of shape: (1, 32, 32)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(1, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=80, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=40, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 753553
+don't use continuous capacity
diff --git a/OAR.2073631.stderr b/OAR.2073631.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..12689b97a5e2548e098a7d7e506c8fb49514bad9
--- /dev/null
+++ b/OAR.2073631.stderr
@@ -0,0 +1,15 @@
+
0it [00:00, ?it/s]
  0%|          | 0/26421880 [00:00<?, ?it/s]
  2%|▏         | 442368/26421880 [00:00<00:06, 4070505.31it/s]
  4%|▍         | 1097728/26421880 [00:00<00:05, 4564965.03it/s]
  6%|▌         | 1499136/26421880 [00:00<00:05, 4351570.58it/s]
  8%|▊         | 1998848/26421880 [00:00<00:05, 4483903.94it/s]
  9%|▉         | 2490368/26421880 [00:00<00:05, 4592980.04it/s]
 11%|█         | 2891776/26421880 [00:00<00:05, 4194835.70it/s]
 13%|█▎        | 3424256/26421880 [00:00<00:05, 4331072.15it/s]
 15%|█▌        | 3973120/26421880 [00:01<00:05, 4478339.92it/s]
 17%|█▋        | 4481024/26421880 [00:01<00:04, 4632115.71it/s]
 19%|█▉        | 5046272/26421880 [00:01<00:04, 4790979.61it/s]
 21%|██        | 5611520/26421880 [00:01<00:04, 5019353.37it/s]
 24%|██▎       | 6217728/26421880 [00:01<00:03, 5179866.35it/s]
 26%|██▌       | 6832128/26421880 [00:01<00:03, 5422062.47it/s]
 28%|██▊       | 7438336/26421880 [00:01<00:03, 5542913.83it/s]
 31%|███       | 8060928/26421880 [00:01<00:03, 5705859.60it/s]
 33%|███▎      | 8691712/26421880 [00:01<00:03, 5858477.57it/s]
 35%|███▌      | 9371648/26421880 [00:01<00:02, 6110391.30it/s]
 38%|███▊      | 9994240/26421880 [00:02<00:02, 5649039.49it/s]
 40%|████      | 10575872/26421880 [00:02<00:02, 5470762.67it/s]
 42%|████▏     | 11132928/26421880 [00:02<00:02, 5333611.24it/s]
 44%|████▍     | 11706368/26421880 [00:02<00:02, 5428585.36it/s]
 46%|████▋     | 12279808/26421880 [00:02<00:02, 5408230.81it/s]
 49%|████▉     | 12894208/26421880 [00:02<00:02, 5596652.44it/s]
 51%|█████     | 13524992/26421880 [00:02<00:02, 5712618.58it/s]
 54%|█████▎    | 14163968/26421880 [00:02<00:02, 5892932.04it/s]
 56%|█████▌    | 14811136/26421880 [00:02<00:01, 6050963.43it/s]
 59%|█████▊    | 15491072/26421880 [00:03<00:01, 6205873.01it/s]
 61%|██████▏   | 16195584/26421880 [00:03<00:01, 6423779.29it/s]
 64%|██████▍   | 16924672/26421880 [00:03<00:01, 6651538.87it/s]
 67%|██████▋   | 17661952/26421880 [00:03<00:01, 6799540.10it/s]
 70%|██████▉   | 18399232/26421880 [00:03<00:01, 6952568.09it/s]
 73%|███████▎  | 19218432/26421880 [00:03<00:00, 7225465.44it/s]
 76%|███████▌  | 20045824/26421880 [00:03<00:00, 7387079.73it/s]
 79%|███████▉  | 20914176/26421880 [00:03<00:00, 7682798.75it/s]
 82%|████████▏ | 21733376/26421880 [00:03<00:00, 7824386.58it/s]
 86%|████████▌ | 22626304/26421880 [00:03<00:00, 8112099.21it/s]
 89%|████████▉ | 23511040/26421880 [00:04<00:00, 8282547.03it/s]
 92%|█████████▏| 24436736/26421880 [00:04<00:00, 8514264.00it/s]
 96%|█████████▌| 25395200/26421880 [00:04<00:00, 8798873.09it/s]
100%|█████████▉| 26337280/26421880 [00:04<00:00, 8971802.37it/s]
26427392it [00:04, 5711392.68it/s]                              
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 416, in load_checkpoint
+    checkpoint = torch.load(file_path)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 426, in load
+    return _load(f, map_location, pickle_module, **pickle_load_args)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 603, in _load
+    magic_number = pickle_module.load(f, **pickle_load_args)
+_pickle.UnpicklingError: invalid load key, 'v'.
diff --git a/OAR.2073631.stdout b/OAR.2073631.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..ae4288ac1589cbc7bad8992bd53748b0c327147a
--- /dev/null
+++ b/OAR.2073631.stdout
@@ -0,0 +1,53 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='fashion_data', disc_capacity=None, epochs=9000000, experiment_name='VAE_bs_64_ls_50', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=50, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=False, lr=0.0001, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+creare new diretory experiment: fashion_data/VAE_bs_64_ls_50
+Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to ../data/fashion_data/FashionMNIST/raw/train-images-idx3-ubyte.gz
+Extracting ../data/fashion_data/FashionMNIST/raw/train-images-idx3-ubyte.gz to ../data/fashion_data/FashionMNIST/raw
+Using downloaded and verified file: ../data/fashion_data/FashionMNIST/raw/train-labels-idx1-ubyte.gz
+Extracting ../data/fashion_data/FashionMNIST/raw/train-labels-idx1-ubyte.gz to ../data/fashion_data/FashionMNIST/raw
+Using downloaded and verified file: ../data/fashion_data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz
+Extracting ../data/fashion_data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz to ../data/fashion_data/FashionMNIST/raw
+Using downloaded and verified file: ../data/fashion_data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz
+Extracting ../data/fashion_data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to ../data/fashion_data/FashionMNIST/raw
+Processing...
+Done!
+load dataset: fashion_data, with: 60032 train images of shape: (1, 32, 32)
+use 2 gpu who named:
+Tesla K80
+Tesla K80
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(1, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=100, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=50, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 761253
+don't use continuous capacity
diff --git a/OAR.2073632.stderr b/OAR.2073632.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..53422e29aaddfc8344f662f9f75b39f077a2b864
--- /dev/null
+++ b/OAR.2073632.stderr
@@ -0,0 +1,14 @@
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 416, in load_checkpoint
+    checkpoint = torch.load(file_path)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 426, in load
+    return _load(f, map_location, pickle_module, **pickle_load_args)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 603, in _load
+    magic_number = pickle_module.load(f, **pickle_load_args)
+_pickle.UnpicklingError: invalid load key, 'v'.
diff --git a/OAR.2073632.stdout b/OAR.2073632.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..c9cc82f4bd0586e5941048355f9104270d9d8901
--- /dev/null
+++ b/OAR.2073632.stdout
@@ -0,0 +1,43 @@
+Namespace(batch_size=64, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='fashion_data', disc_capacity=None, epochs=9000000, experiment_name='beta_VAE_bs_64', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=False, lr=0.0001, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+creare new diretory experiment: fashion_data/beta_VAE_bs_64
+load dataset: fashion_data, with: 60032 train images of shape: (1, 32, 32)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(1, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 730453
+don't use continuous capacity
diff --git a/OAR.2073633.stderr b/OAR.2073633.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..7e7e28a232a403708d1b9f7d3408370611296849
--- /dev/null
+++ b/OAR.2073633.stderr
@@ -0,0 +1,20 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py:26: UserWarning: 
+    There is an imbalance between your GPUs. You may want to exclude GPU 1 which
+    has less than 75% of the memory or cores of GPU 0. You can do so by setting
+    the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES
+    environment variable.
+  warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 416, in load_checkpoint
+    checkpoint = torch.load(file_path)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 426, in load
+    return _load(f, map_location, pickle_module, **pickle_load_args)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 603, in _load
+    magic_number = pickle_module.load(f, **pickle_load_args)
+_pickle.UnpicklingError: invalid load key, 'v'.
diff --git a/OAR.2073633.stdout b/OAR.2073633.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..678b1b41c628c15aa010bc4c49c53c851c505c19
--- /dev/null
+++ b/OAR.2073633.stdout
@@ -0,0 +1,43 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='fashion_data', disc_capacity=None, epochs=9000000, experiment_name='VAE_bs_64', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=False, lr=0.0001, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+creare new diretory experiment: fashion_data/VAE_bs_64
+load dataset: fashion_data, with: 60032 train images of shape: (1, 32, 32)
+use 2 gpu who named:
+Tesla K40c
+Tesla K20m
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(1, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 730453
+don't use continuous capacity
diff --git a/OAR.2073634.stderr b/OAR.2073634.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..53422e29aaddfc8344f662f9f75b39f077a2b864
--- /dev/null
+++ b/OAR.2073634.stderr
@@ -0,0 +1,14 @@
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 416, in load_checkpoint
+    checkpoint = torch.load(file_path)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 426, in load
+    return _load(f, map_location, pickle_module, **pickle_load_args)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 603, in _load
+    magic_number = pickle_module.load(f, **pickle_load_args)
+_pickle.UnpicklingError: invalid load key, 'v'.
diff --git a/OAR.2073634.stdout b/OAR.2073634.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..221f7ee51263c571276dd60b7959228e06ba754e
--- /dev/null
+++ b/OAR.2073634.stdout
@@ -0,0 +1,43 @@
+Namespace(batch_size=64, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='fashion_data', disc_capacity=None, epochs=9000000, experiment_name='beta_VAE_bs_64_ls_15', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=15, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=False, lr=0.0001, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+creare new diretory experiment: fashion_data/beta_VAE_bs_64_ls_15
+load dataset: fashion_data, with: 60032 train images of shape: (1, 32, 32)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(1, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=30, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=15, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 734303
+don't use continuous capacity
diff --git a/OAR.2073635.stderr b/OAR.2073635.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..53422e29aaddfc8344f662f9f75b39f077a2b864
--- /dev/null
+++ b/OAR.2073635.stderr
@@ -0,0 +1,14 @@
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 416, in load_checkpoint
+    checkpoint = torch.load(file_path)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 426, in load
+    return _load(f, map_location, pickle_module, **pickle_load_args)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 603, in _load
+    magic_number = pickle_module.load(f, **pickle_load_args)
+_pickle.UnpicklingError: invalid load key, 'v'.
diff --git a/OAR.2073635.stdout b/OAR.2073635.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..02a1b936c306230808f0b5b6e6351c911369da79
--- /dev/null
+++ b/OAR.2073635.stdout
@@ -0,0 +1,43 @@
+Namespace(batch_size=64, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='fashion_data', disc_capacity=None, epochs=9000000, experiment_name='beta_VAE_bs_64_ls_20', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=20, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=False, lr=0.0001, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+creare new diretory experiment: fashion_data/beta_VAE_bs_64_ls_20
+load dataset: fashion_data, with: 60032 train images of shape: (1, 32, 32)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(1, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=40, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=20, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 738153
+don't use continuous capacity
diff --git a/OAR.2073636.stderr b/OAR.2073636.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..53422e29aaddfc8344f662f9f75b39f077a2b864
--- /dev/null
+++ b/OAR.2073636.stderr
@@ -0,0 +1,14 @@
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 416, in load_checkpoint
+    checkpoint = torch.load(file_path)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 426, in load
+    return _load(f, map_location, pickle_module, **pickle_load_args)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 603, in _load
+    magic_number = pickle_module.load(f, **pickle_load_args)
+_pickle.UnpicklingError: invalid load key, 'v'.
diff --git a/OAR.2073636.stdout b/OAR.2073636.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..eaeca4913be3b81c08fe7c8e2e0c71797e5af237
--- /dev/null
+++ b/OAR.2073636.stdout
@@ -0,0 +1,43 @@
+Namespace(batch_size=64, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='fashion_data', disc_capacity=None, epochs=9000000, experiment_name='beta_VAE_bs_64_ls_5', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=5, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=False, lr=0.0001, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+creare new diretory experiment: fashion_data/beta_VAE_bs_64_ls_5
+load dataset: fashion_data, with: 60032 train images of shape: (1, 32, 32)
+use 2 gpu who named:
+Tesla K80
+Tesla K80
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(1, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=10, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=5, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 726603
+don't use continuous capacity
diff --git a/OAR.2073637.stderr b/OAR.2073637.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..53422e29aaddfc8344f662f9f75b39f077a2b864
--- /dev/null
+++ b/OAR.2073637.stderr
@@ -0,0 +1,14 @@
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 416, in load_checkpoint
+    checkpoint = torch.load(file_path)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 426, in load
+    return _load(f, map_location, pickle_module, **pickle_load_args)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 603, in _load
+    magic_number = pickle_module.load(f, **pickle_load_args)
+_pickle.UnpicklingError: invalid load key, 'v'.
diff --git a/OAR.2073637.stdout b/OAR.2073637.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..607f58d9a072a54547d57d1bc45678cafc9a5e50
--- /dev/null
+++ b/OAR.2073637.stdout
@@ -0,0 +1,43 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='fashion_data', disc_capacity=None, epochs=9000000, experiment_name='VAE_bs_64_ls_5', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=5, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=False, lr=0.0001, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+creare new diretory experiment: fashion_data/VAE_bs_64_ls_5
+load dataset: fashion_data, with: 60032 train images of shape: (1, 32, 32)
+use 2 gpu who named:
+GeForce GTX 1080 Ti
+GeForce GTX 1080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(1, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=10, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=5, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 726603
+don't use continuous capacity
diff --git a/OAR.2073638.stderr b/OAR.2073638.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..7e7e28a232a403708d1b9f7d3408370611296849
--- /dev/null
+++ b/OAR.2073638.stderr
@@ -0,0 +1,20 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py:26: UserWarning: 
+    There is an imbalance between your GPUs. You may want to exclude GPU 1 which
+    has less than 75% of the memory or cores of GPU 0. You can do so by setting
+    the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES
+    environment variable.
+  warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 416, in load_checkpoint
+    checkpoint = torch.load(file_path)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 426, in load
+    return _load(f, map_location, pickle_module, **pickle_load_args)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 603, in _load
+    magic_number = pickle_module.load(f, **pickle_load_args)
+_pickle.UnpicklingError: invalid load key, 'v'.
diff --git a/OAR.2073638.stdout b/OAR.2073638.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..bf4d4b186e451b7e30d4ecf88799b84b8b91f014
--- /dev/null
+++ b/OAR.2073638.stdout
@@ -0,0 +1,43 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='fashion_data', disc_capacity=None, epochs=9000000, experiment_name='VAE_bs_64_ls_15', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=15, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=False, lr=0.0001, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+creare new diretory experiment: fashion_data/VAE_bs_64_ls_15
+load dataset: fashion_data, with: 60032 train images of shape: (1, 32, 32)
+use 2 gpu who named:
+Tesla K40c
+Tesla K20m
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(1, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=30, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=15, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 734303
+don't use continuous capacity
diff --git a/OAR.2073639.stderr b/OAR.2073639.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..4a4dd9e8ac27dd96e76572cf1c6e9c9a17567927
--- /dev/null
+++ b/OAR.2073639.stderr
@@ -0,0 +1,44 @@
+Traceback (most recent call last):
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/tarfile.py", line 2289, in next
+    tarinfo = self.tarinfo.fromtarfile(self)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/tarfile.py", line 1095, in fromtarfile
+    obj = cls.frombuf(buf, tarfile.encoding, tarfile.errors)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/tarfile.py", line 1031, in frombuf
+    raise EmptyHeaderError("empty header")
+tarfile.EmptyHeaderError: empty header
+
+During handling of the above exception, another exception occurred:
+
+Traceback (most recent call last):
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 595, in _load
+    return legacy_load(f)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 506, in legacy_load
+    with closing(tarfile.open(fileobj=f, mode='r:', format=tarfile.PAX_FORMAT)) as tar, \
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/tarfile.py", line 1591, in open
+    return func(name, filemode, fileobj, **kwargs)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/tarfile.py", line 1621, in taropen
+    return cls(name, mode, fileobj, **kwargs)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/tarfile.py", line 1484, in __init__
+    self.firstmember = self.next()
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/tarfile.py", line 2304, in next
+    raise ReadError("empty file")
+tarfile.ReadError: empty file
+
+During handling of the above exception, another exception occurred:
+
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 416, in load_checkpoint
+    checkpoint = torch.load(file_path)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 426, in load
+    return _load(f, map_location, pickle_module, **pickle_load_args)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 597, in _load
+    if _is_zipfile(f):
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 75, in _is_zipfile
+    if ord(magic_byte) != ord(read_byte):
+TypeError: ord() expected a character, but string of length 0 found
diff --git a/OAR.2073639.stdout b/OAR.2073639.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..47fa97396a045d9d7fa30dc41a15e90a3d9af2d6
--- /dev/null
+++ b/OAR.2073639.stdout
@@ -0,0 +1,43 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='fashion_data', disc_capacity=None, epochs=9000000, experiment_name='VAE_bs_64_ls_20', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=20, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=False, lr=0.0001, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+creare new diretory experiment: fashion_data/VAE_bs_64_ls_20
+load dataset: fashion_data, with: 60032 train images of shape: (1, 32, 32)
+use 2 gpu who named:
+GeForce GTX 1080 Ti
+GeForce GTX 1080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(1, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=40, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=20, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 738153
+don't use continuous capacity
diff --git a/OAR.2073640.stderr b/OAR.2073640.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..fb24beae5afe1d77fbc9d36af38e2f3cefc52aa5
--- /dev/null
+++ b/OAR.2073640.stderr
@@ -0,0 +1,14 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 90, in main
+    trainer.train(train_loader, args.epochs)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 116, in train
+    mean_epoch_loss, recon_loss, kl_loss, prediction_loss, prediction_random_continue_loss = self._train_epoch(data_loader)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 177, in _train_epoch
+    iter_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter = self._train_iteration(data, label)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 227, in _train_iteration
+    pred_loss_iter = pred_loss.item()
+AttributeError: 'float' object has no attribute 'item'
diff --git a/OAR.2073640.stdout b/OAR.2073640.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..c9819896770dee7abf6d68caf0778aba0265613d
--- /dev/null
+++ b/OAR.2073640.stdout
@@ -0,0 +1,45 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='fashion_data', disc_capacity=None, epochs=9000000, experiment_name='VAE_bs_64_ls_10_lr_5e_4', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=False, lr=0.0005, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+creare new diretory experiment: fashion_data/VAE_bs_64_ls_10_lr_5e_4
+create new directory: trained_models/fashion_data/VAE_bs_64_ls_10_lr_5e_4/checkpoints
+load dataset: fashion_data, with: 60032 train images of shape: (1, 32, 32)
+use 2 gpu who named:
+GeForce GTX 1080 Ti
+GeForce GTX 1080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(1, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 730453
+don't use continuous capacity
+=> no checkpoint found at 'trained_models/fashion_data/VAE_bs_64_ls_10_lr_5e_4/checkpoints/last'
diff --git a/OAR.2073641.stderr b/OAR.2073641.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..7e7e28a232a403708d1b9f7d3408370611296849
--- /dev/null
+++ b/OAR.2073641.stderr
@@ -0,0 +1,20 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py:26: UserWarning: 
+    There is an imbalance between your GPUs. You may want to exclude GPU 1 which
+    has less than 75% of the memory or cores of GPU 0. You can do so by setting
+    the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES
+    environment variable.
+  warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 416, in load_checkpoint
+    checkpoint = torch.load(file_path)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 426, in load
+    return _load(f, map_location, pickle_module, **pickle_load_args)
+  File "/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/serialization.py", line 603, in _load
+    magic_number = pickle_module.load(f, **pickle_load_args)
+_pickle.UnpicklingError: invalid load key, 'v'.
diff --git a/OAR.2073641.stdout b/OAR.2073641.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..cbd72273605ed03ceb6515fa430db355dbcfc843
--- /dev/null
+++ b/OAR.2073641.stdout
@@ -0,0 +1,43 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='fashion_data', disc_capacity=None, epochs=9000000, experiment_name='VAE_bs_64_conv_64_64_128_128', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=False, lr=0.0001, nb_filter_conv1=64, nb_filter_conv2=64, nb_filter_conv3=128, nb_filter_conv4=128, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+creare new diretory experiment: fashion_data/VAE_bs_64_conv_64_64_128_128
+load dataset: fashion_data, with: 60032 train images of shape: (1, 32, 32)
+use 2 gpu who named:
+Tesla K40c
+Tesla K20m
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(1, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(128, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(128, 512, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=512, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=512, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(512, 128, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(128, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(128, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(64, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 2902677
+don't use continuous capacity
diff --git a/OAR.2073642.stderr b/OAR.2073642.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..4d7c3450eca653bd78d41f7de18ba444d3017bf9
--- /dev/null
+++ b/OAR.2073642.stderr
@@ -0,0 +1,3 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+## OAR [2020-07-07 08:29:14] Job 2073642 KILLED ##
diff --git a/OAR.2073642.stdout b/OAR.2073642.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..7f7eb13148ad7c92b8a769c2ce15b660ff83bf91
--- /dev/null
+++ b/OAR.2073642.stdout
@@ -0,0 +1,5216 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=90000, experiment_name='VAE_bs_64_ls_30', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=30, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=60, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=30, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 780735
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last (iter 151)'
+0/69092	Loss: 90.857
+3200/69092	Loss: 100.896
+6400/69092	Loss: 102.867
+9600/69092	Loss: 100.896
+12800/69092	Loss: 101.476
+16000/69092	Loss: 100.314
+19200/69092	Loss: 102.579
+22400/69092	Loss: 100.823
+25600/69092	Loss: 101.249
+28800/69092	Loss: 98.799
+32000/69092	Loss: 100.542
+35200/69092	Loss: 100.504
+38400/69092	Loss: 99.883
+41600/69092	Loss: 100.650
+44800/69092	Loss: 101.331
+48000/69092	Loss: 101.926
+51200/69092	Loss: 100.185
+54400/69092	Loss: 100.923
+57600/69092	Loss: 100.491
+60800/69092	Loss: 101.226
+64000/69092	Loss: 101.842
+67200/69092	Loss: 100.903
+Training time 0:13:22.536955
+Epoch: 1 Average loss: 100.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 152)
+0/69092	Loss: 112.391
+3200/69092	Loss: 101.627
+6400/69092	Loss: 101.528
+9600/69092	Loss: 100.415
+12800/69092	Loss: 101.177
+16000/69092	Loss: 100.456
+19200/69092	Loss: 101.405
+22400/69092	Loss: 100.677
+25600/69092	Loss: 100.944
+28800/69092	Loss: 101.739
+32000/69092	Loss: 100.738
+35200/69092	Loss: 100.845
+38400/69092	Loss: 100.162
+41600/69092	Loss: 101.028
+44800/69092	Loss: 99.590
+48000/69092	Loss: 100.294
+51200/69092	Loss: 101.643
+54400/69092	Loss: 100.665
+57600/69092	Loss: 101.591
+60800/69092	Loss: 100.224
+64000/69092	Loss: 100.692
+67200/69092	Loss: 102.154
+Training time 0:10:52.556148
+Epoch: 2 Average loss: 100.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 153)
+0/69092	Loss: 107.454
+3200/69092	Loss: 101.489
+6400/69092	Loss: 100.728
+9600/69092	Loss: 99.638
+12800/69092	Loss: 100.251
+16000/69092	Loss: 100.477
+19200/69092	Loss: 100.710
+22400/69092	Loss: 99.758
+25600/69092	Loss: 99.931
+28800/69092	Loss: 101.879
+32000/69092	Loss: 100.798
+35200/69092	Loss: 100.518
+38400/69092	Loss: 100.419
+41600/69092	Loss: 100.298
+44800/69092	Loss: 101.043
+48000/69092	Loss: 101.101
+51200/69092	Loss: 100.542
+54400/69092	Loss: 101.929
+57600/69092	Loss: 100.215
+60800/69092	Loss: 101.169
+64000/69092	Loss: 101.229
+67200/69092	Loss: 100.054
+Training time 0:10:13.335563
+Epoch: 3 Average loss: 100.73
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 154)
+0/69092	Loss: 88.903
+3200/69092	Loss: 100.694
+6400/69092	Loss: 100.380
+9600/69092	Loss: 100.438
+12800/69092	Loss: 100.192
+16000/69092	Loss: 101.963
+19200/69092	Loss: 100.461
+22400/69092	Loss: 100.583
+25600/69092	Loss: 100.875
+28800/69092	Loss: 98.934
+32000/69092	Loss: 99.607
+35200/69092	Loss: 101.819
+38400/69092	Loss: 99.161
+41600/69092	Loss: 100.947
+44800/69092	Loss: 99.773
+48000/69092	Loss: 100.309
+51200/69092	Loss: 100.968
+54400/69092	Loss: 100.739
+57600/69092	Loss: 101.130
+60800/69092	Loss: 102.463
+64000/69092	Loss: 101.432
+67200/69092	Loss: 101.092
+Training time 0:10:10.925639
+Epoch: 4 Average loss: 100.72
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 155)
+0/69092	Loss: 101.284
+3200/69092	Loss: 100.317
+6400/69092	Loss: 100.133
+9600/69092	Loss: 101.435
+12800/69092	Loss: 101.001
+16000/69092	Loss: 101.030
+19200/69092	Loss: 101.369
+22400/69092	Loss: 99.846
+25600/69092	Loss: 99.866
+28800/69092	Loss: 100.989
+32000/69092	Loss: 99.827
+35200/69092	Loss: 100.994
+38400/69092	Loss: 100.439
+41600/69092	Loss: 100.306
+44800/69092	Loss: 101.138
+48000/69092	Loss: 101.276
+51200/69092	Loss: 100.358
+54400/69092	Loss: 101.804
+57600/69092	Loss: 100.310
+60800/69092	Loss: 100.296
+64000/69092	Loss: 101.495
+67200/69092	Loss: 101.331
+Training time 0:10:24.263162
+Epoch: 5 Average loss: 100.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 156)
+0/69092	Loss: 91.869
+3200/69092	Loss: 100.730
+6400/69092	Loss: 100.619
+9600/69092	Loss: 99.290
+12800/69092	Loss: 99.293
+16000/69092	Loss: 101.506
+19200/69092	Loss: 100.954
+22400/69092	Loss: 100.630
+25600/69092	Loss: 100.642
+28800/69092	Loss: 101.194
+32000/69092	Loss: 99.540
+35200/69092	Loss: 101.119
+38400/69092	Loss: 100.036
+41600/69092	Loss: 102.296
+44800/69092	Loss: 101.366
+48000/69092	Loss: 101.069
+51200/69092	Loss: 99.667
+54400/69092	Loss: 100.424
+57600/69092	Loss: 101.080
+60800/69092	Loss: 101.214
+64000/69092	Loss: 100.979
+67200/69092	Loss: 100.434
+Training time 0:10:16.979999
+Epoch: 6 Average loss: 100.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 157)
+0/69092	Loss: 103.696
+3200/69092	Loss: 99.888
+6400/69092	Loss: 102.452
+9600/69092	Loss: 101.145
+12800/69092	Loss: 98.928
+16000/69092	Loss: 99.634
+19200/69092	Loss: 100.475
+22400/69092	Loss: 100.984
+25600/69092	Loss: 101.335
+28800/69092	Loss: 100.237
+32000/69092	Loss: 100.423
+35200/69092	Loss: 101.199
+38400/69092	Loss: 100.595
+41600/69092	Loss: 100.726
+44800/69092	Loss: 100.514
+48000/69092	Loss: 100.415
+51200/69092	Loss: 100.428
+54400/69092	Loss: 100.919
+57600/69092	Loss: 101.008
+60800/69092	Loss: 100.350
+64000/69092	Loss: 101.610
+67200/69092	Loss: 100.413
+Training time 0:10:44.289171
+Epoch: 7 Average loss: 100.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 158)
+0/69092	Loss: 99.058
+3200/69092	Loss: 100.530
+6400/69092	Loss: 99.354
+9600/69092	Loss: 100.078
+12800/69092	Loss: 100.434
+16000/69092	Loss: 100.931
+19200/69092	Loss: 100.534
+22400/69092	Loss: 100.907
+25600/69092	Loss: 100.255
+28800/69092	Loss: 99.552
+32000/69092	Loss: 102.825
+35200/69092	Loss: 101.045
+38400/69092	Loss: 102.631
+41600/69092	Loss: 99.552
+44800/69092	Loss: 101.287
+48000/69092	Loss: 100.109
+51200/69092	Loss: 99.976
+54400/69092	Loss: 101.527
+57600/69092	Loss: 101.586
+60800/69092	Loss: 100.806
+64000/69092	Loss: 101.035
+67200/69092	Loss: 99.979
+Training time 0:09:59.705624
+Epoch: 8 Average loss: 100.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 159)
+0/69092	Loss: 103.561
+3200/69092	Loss: 101.245
+6400/69092	Loss: 101.131
+9600/69092	Loss: 99.564
+12800/69092	Loss: 99.659
+16000/69092	Loss: 100.434
+19200/69092	Loss: 101.038
+22400/69092	Loss: 100.173
+25600/69092	Loss: 100.267
+28800/69092	Loss: 100.739
+32000/69092	Loss: 100.412
+35200/69092	Loss: 102.110
+38400/69092	Loss: 100.020
+41600/69092	Loss: 101.792
+44800/69092	Loss: 101.294
+48000/69092	Loss: 101.586
+51200/69092	Loss: 99.891
+54400/69092	Loss: 100.281
+57600/69092	Loss: 101.081
+60800/69092	Loss: 100.948
+64000/69092	Loss: 99.330
+67200/69092	Loss: 101.067
+Training time 0:10:03.692942
+Epoch: 9 Average loss: 100.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 160)
+0/69092	Loss: 100.755
+3200/69092	Loss: 102.696
+6400/69092	Loss: 102.509
+9600/69092	Loss: 100.596
+12800/69092	Loss: 99.879
+16000/69092	Loss: 101.567
+19200/69092	Loss: 100.958
+22400/69092	Loss: 100.226
+25600/69092	Loss: 99.870
+28800/69092	Loss: 99.772
+32000/69092	Loss: 100.681
+35200/69092	Loss: 101.588
+38400/69092	Loss: 100.448
+41600/69092	Loss: 99.148
+44800/69092	Loss: 100.254
+48000/69092	Loss: 100.904
+51200/69092	Loss: 99.440
+54400/69092	Loss: 100.085
+57600/69092	Loss: 98.232
+60800/69092	Loss: 100.112
+64000/69092	Loss: 101.036
+67200/69092	Loss: 101.011
+Training time 0:10:25.881331
+Epoch: 10 Average loss: 100.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 161)
+0/69092	Loss: 91.759
+3200/69092	Loss: 101.597
+6400/69092	Loss: 99.947
+9600/69092	Loss: 100.180
+12800/69092	Loss: 101.015
+16000/69092	Loss: 97.057
+19200/69092	Loss: 100.711
+22400/69092	Loss: 101.811
+25600/69092	Loss: 99.226
+28800/69092	Loss: 100.769
+32000/69092	Loss: 99.366
+35200/69092	Loss: 100.113
+38400/69092	Loss: 100.704
+41600/69092	Loss: 101.669
+44800/69092	Loss: 101.506
+48000/69092	Loss: 101.513
+51200/69092	Loss: 101.313
+54400/69092	Loss: 101.363
+57600/69092	Loss: 99.833
+60800/69092	Loss: 100.909
+64000/69092	Loss: 99.774
+67200/69092	Loss: 100.637
+Training time 0:10:35.023585
+Epoch: 11 Average loss: 100.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 162)
+0/69092	Loss: 107.944
+3200/69092	Loss: 100.648
+6400/69092	Loss: 99.919
+9600/69092	Loss: 101.079
+12800/69092	Loss: 100.624
+16000/69092	Loss: 100.319
+19200/69092	Loss: 101.166
+22400/69092	Loss: 101.354
+25600/69092	Loss: 100.493
+28800/69092	Loss: 99.155
+32000/69092	Loss: 98.583
+35200/69092	Loss: 101.474
+38400/69092	Loss: 99.048
+41600/69092	Loss: 100.080
+44800/69092	Loss: 99.624
+48000/69092	Loss: 102.056
+51200/69092	Loss: 99.685
+54400/69092	Loss: 100.620
+57600/69092	Loss: 100.928
+60800/69092	Loss: 101.815
+64000/69092	Loss: 101.294
+67200/69092	Loss: 100.444
+Training time 0:10:39.147597
+Epoch: 12 Average loss: 100.50
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 163)
+0/69092	Loss: 90.271
+3200/69092	Loss: 100.667
+6400/69092	Loss: 100.967
+9600/69092	Loss: 100.144
+12800/69092	Loss: 100.500
+16000/69092	Loss: 100.114
+19200/69092	Loss: 100.426
+22400/69092	Loss: 101.159
+25600/69092	Loss: 99.706
+28800/69092	Loss: 100.198
+32000/69092	Loss: 100.439
+35200/69092	Loss: 100.815
+38400/69092	Loss: 100.880
+41600/69092	Loss: 98.307
+44800/69092	Loss: 99.669
+48000/69092	Loss: 101.589
+51200/69092	Loss: 101.234
+54400/69092	Loss: 100.851
+57600/69092	Loss: 99.295
+60800/69092	Loss: 101.259
+64000/69092	Loss: 100.284
+67200/69092	Loss: 100.930
+Training time 0:10:16.745973
+Epoch: 13 Average loss: 100.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 164)
+0/69092	Loss: 110.381
+3200/69092	Loss: 100.312
+6400/69092	Loss: 99.831
+9600/69092	Loss: 100.926
+12800/69092	Loss: 98.216
+16000/69092	Loss: 101.681
+19200/69092	Loss: 101.070
+22400/69092	Loss: 99.323
+25600/69092	Loss: 100.217
+28800/69092	Loss: 102.129
+32000/69092	Loss: 100.339
+35200/69092	Loss: 102.523
+38400/69092	Loss: 100.062
+41600/69092	Loss: 100.664
+44800/69092	Loss: 99.133
+48000/69092	Loss: 100.377
+51200/69092	Loss: 101.199
+54400/69092	Loss: 100.055
+57600/69092	Loss: 100.580
+60800/69092	Loss: 101.073
+64000/69092	Loss: 99.813
+67200/69092	Loss: 101.102
+Training time 0:10:22.531546
+Epoch: 14 Average loss: 100.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 165)
+0/69092	Loss: 105.286
+3200/69092	Loss: 100.594
+6400/69092	Loss: 100.157
+9600/69092	Loss: 100.147
+12800/69092	Loss: 99.849
+16000/69092	Loss: 100.910
+19200/69092	Loss: 97.858
+22400/69092	Loss: 100.878
+25600/69092	Loss: 101.757
+28800/69092	Loss: 99.680
+32000/69092	Loss: 100.134
+35200/69092	Loss: 100.873
+38400/69092	Loss: 100.967
+41600/69092	Loss: 101.347
+44800/69092	Loss: 102.215
+48000/69092	Loss: 100.206
+51200/69092	Loss: 99.963
+54400/69092	Loss: 101.613
+57600/69092	Loss: 100.700
+60800/69092	Loss: 100.405
+64000/69092	Loss: 99.284
+67200/69092	Loss: 100.606
+Training time 0:10:17.460304
+Epoch: 15 Average loss: 100.50
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 166)
+0/69092	Loss: 109.605
+3200/69092	Loss: 99.625
+6400/69092	Loss: 101.296
+9600/69092	Loss: 99.007
+12800/69092	Loss: 101.360
+16000/69092	Loss: 100.476
+19200/69092	Loss: 100.594
+22400/69092	Loss: 101.498
+25600/69092	Loss: 98.941
+28800/69092	Loss: 98.080
+32000/69092	Loss: 100.335
+35200/69092	Loss: 99.571
+38400/69092	Loss: 102.125
+41600/69092	Loss: 99.909
+44800/69092	Loss: 100.261
+48000/69092	Loss: 101.179
+51200/69092	Loss: 99.661
+54400/69092	Loss: 101.432
+57600/69092	Loss: 99.418
+60800/69092	Loss: 100.694
+64000/69092	Loss: 100.913
+67200/69092	Loss: 100.276
+Training time 0:10:08.676841
+Epoch: 16 Average loss: 100.30
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 167)
+0/69092	Loss: 103.221
+3200/69092	Loss: 99.201
+6400/69092	Loss: 100.848
+9600/69092	Loss: 98.694
+12800/69092	Loss: 101.440
+16000/69092	Loss: 99.760
+19200/69092	Loss: 100.571
+22400/69092	Loss: 101.013
+25600/69092	Loss: 98.245
+28800/69092	Loss: 100.137
+32000/69092	Loss: 100.147
+35200/69092	Loss: 102.266
+38400/69092	Loss: 99.774
+41600/69092	Loss: 101.011
+44800/69092	Loss: 100.263
+48000/69092	Loss: 100.845
+51200/69092	Loss: 100.166
+54400/69092	Loss: 100.333
+57600/69092	Loss: 99.643
+60800/69092	Loss: 100.004
+64000/69092	Loss: 100.515
+67200/69092	Loss: 100.858
+Training time 0:10:09.258986
+Epoch: 17 Average loss: 100.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 168)
+0/69092	Loss: 98.589
+3200/69092	Loss: 100.657
+6400/69092	Loss: 99.640
+9600/69092	Loss: 99.491
+12800/69092	Loss: 100.384
+16000/69092	Loss: 99.559
+19200/69092	Loss: 100.651
+22400/69092	Loss: 99.591
+25600/69092	Loss: 103.578
+28800/69092	Loss: 101.906
+32000/69092	Loss: 100.018
+35200/69092	Loss: 99.243
+38400/69092	Loss: 98.868
+41600/69092	Loss: 100.799
+44800/69092	Loss: 99.205
+48000/69092	Loss: 100.436
+51200/69092	Loss: 100.848
+54400/69092	Loss: 101.567
+57600/69092	Loss: 100.539
+60800/69092	Loss: 100.597
+64000/69092	Loss: 99.924
+67200/69092	Loss: 99.761
+Training time 0:10:40.501785
+Epoch: 18 Average loss: 100.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 169)
+0/69092	Loss: 101.090
+3200/69092	Loss: 98.897
+6400/69092	Loss: 101.100
+9600/69092	Loss: 98.165
+12800/69092	Loss: 101.350
+16000/69092	Loss: 101.014
+19200/69092	Loss: 99.836
+22400/69092	Loss: 100.248
+25600/69092	Loss: 98.994
+28800/69092	Loss: 100.682
+32000/69092	Loss: 101.074
+35200/69092	Loss: 101.534
+38400/69092	Loss: 99.495
+41600/69092	Loss: 100.129
+44800/69092	Loss: 100.414
+48000/69092	Loss: 99.205
+51200/69092	Loss: 100.103
+54400/69092	Loss: 100.189
+57600/69092	Loss: 101.436
+60800/69092	Loss: 100.053
+64000/69092	Loss: 100.833
+67200/69092	Loss: 101.550
+Training time 0:10:35.079849
+Epoch: 19 Average loss: 100.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 170)
+0/69092	Loss: 104.111
+3200/69092	Loss: 99.837
+6400/69092	Loss: 99.601
+9600/69092	Loss: 99.668
+12800/69092	Loss: 101.194
+16000/69092	Loss: 101.369
+19200/69092	Loss: 99.923
+22400/69092	Loss: 100.139
+25600/69092	Loss: 99.507
+28800/69092	Loss: 99.263
+32000/69092	Loss: 100.740
+35200/69092	Loss: 101.556
+38400/69092	Loss: 99.704
+41600/69092	Loss: 98.574
+44800/69092	Loss: 99.651
+48000/69092	Loss: 101.120
+51200/69092	Loss: 100.802
+54400/69092	Loss: 100.553
+57600/69092	Loss: 100.646
+60800/69092	Loss: 100.835
+64000/69092	Loss: 100.099
+67200/69092	Loss: 101.293
+Training time 0:10:31.615761
+Epoch: 20 Average loss: 100.28
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 171)
+0/69092	Loss: 100.596
+3200/69092	Loss: 99.743
+6400/69092	Loss: 100.214
+9600/69092	Loss: 100.563
+12800/69092	Loss: 100.838
+16000/69092	Loss: 100.816
+19200/69092	Loss: 99.976
+22400/69092	Loss: 100.197
+25600/69092	Loss: 102.278
+28800/69092	Loss: 99.107
+32000/69092	Loss: 99.602
+35200/69092	Loss: 99.449
+38400/69092	Loss: 100.602
+41600/69092	Loss: 100.785
+44800/69092	Loss: 100.824
+48000/69092	Loss: 100.576
+51200/69092	Loss: 99.966
+54400/69092	Loss: 100.054
+57600/69092	Loss: 100.230
+60800/69092	Loss: 100.171
+64000/69092	Loss: 100.501
+67200/69092	Loss: 100.154
+Training time 0:10:23.653780
+Epoch: 21 Average loss: 100.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 172)
+0/69092	Loss: 102.655
+3200/69092	Loss: 100.107
+6400/69092	Loss: 100.795
+9600/69092	Loss: 101.244
+12800/69092	Loss: 100.354
+16000/69092	Loss: 101.621
+19200/69092	Loss: 99.983
+22400/69092	Loss: 102.301
+25600/69092	Loss: 100.026
+28800/69092	Loss: 98.556
+32000/69092	Loss: 100.287
+35200/69092	Loss: 99.643
+38400/69092	Loss: 100.953
+41600/69092	Loss: 100.417
+44800/69092	Loss: 99.072
+48000/69092	Loss: 99.223
+51200/69092	Loss: 99.633
+54400/69092	Loss: 99.651
+57600/69092	Loss: 101.218
+60800/69092	Loss: 100.078
+64000/69092	Loss: 100.579
+67200/69092	Loss: 101.242
+Training time 0:10:20.973984
+Epoch: 22 Average loss: 100.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 173)
+0/69092	Loss: 103.888
+3200/69092	Loss: 100.748
+6400/69092	Loss: 100.900
+9600/69092	Loss: 100.073
+12800/69092	Loss: 98.744
+16000/69092	Loss: 99.252
+19200/69092	Loss: 101.954
+22400/69092	Loss: 101.632
+25600/69092	Loss: 101.654
+28800/69092	Loss: 99.831
+32000/69092	Loss: 100.271
+35200/69092	Loss: 99.135
+38400/69092	Loss: 99.074
+41600/69092	Loss: 99.457
+44800/69092	Loss: 101.231
+48000/69092	Loss: 101.178
+51200/69092	Loss: 101.375
+54400/69092	Loss: 98.308
+57600/69092	Loss: 100.247
+60800/69092	Loss: 99.567
+64000/69092	Loss: 99.512
+67200/69092	Loss: 100.534
+Training time 0:10:18.045025
+Epoch: 23 Average loss: 100.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 174)
+0/69092	Loss: 98.240
+3200/69092	Loss: 102.289
+6400/69092	Loss: 98.598
+9600/69092	Loss: 98.990
+12800/69092	Loss: 99.472
+16000/69092	Loss: 101.627
+19200/69092	Loss: 101.218
+22400/69092	Loss: 100.225
+25600/69092	Loss: 100.430
+28800/69092	Loss: 100.316
+32000/69092	Loss: 101.919
+35200/69092	Loss: 100.060
+38400/69092	Loss: 99.616
+41600/69092	Loss: 101.506
+44800/69092	Loss: 99.442
+48000/69092	Loss: 101.454
+51200/69092	Loss: 99.450
+54400/69092	Loss: 100.213
+57600/69092	Loss: 98.830
+60800/69092	Loss: 102.337
+64000/69092	Loss: 100.273
+67200/69092	Loss: 98.916
+Training time 0:10:38.205521
+Epoch: 24 Average loss: 100.30
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 175)
+0/69092	Loss: 92.109
+3200/69092	Loss: 100.725
+6400/69092	Loss: 100.539
+9600/69092	Loss: 100.119
+12800/69092	Loss: 100.424
+16000/69092	Loss: 100.177
+19200/69092	Loss: 100.786
+22400/69092	Loss: 99.217
+25600/69092	Loss: 100.067
+28800/69092	Loss: 100.467
+32000/69092	Loss: 101.432
+35200/69092	Loss: 99.315
+38400/69092	Loss: 101.069
+41600/69092	Loss: 100.867
+44800/69092	Loss: 100.729
+48000/69092	Loss: 100.158
+51200/69092	Loss: 99.724
+54400/69092	Loss: 101.087
+57600/69092	Loss: 99.889
+60800/69092	Loss: 97.432
+64000/69092	Loss: 100.877
+67200/69092	Loss: 99.569
+Training time 0:10:21.527763
+Epoch: 25 Average loss: 100.25
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 176)
+0/69092	Loss: 108.606
+3200/69092	Loss: 101.711
+6400/69092	Loss: 99.079
+9600/69092	Loss: 99.500
+12800/69092	Loss: 99.765
+16000/69092	Loss: 98.451
+19200/69092	Loss: 101.255
+22400/69092	Loss: 101.426
+25600/69092	Loss: 99.685
+28800/69092	Loss: 99.951
+32000/69092	Loss: 101.204
+35200/69092	Loss: 100.354
+38400/69092	Loss: 100.712
+41600/69092	Loss: 100.057
+44800/69092	Loss: 99.986
+48000/69092	Loss: 100.277
+51200/69092	Loss: 99.919
+54400/69092	Loss: 100.001
+57600/69092	Loss: 100.471
+60800/69092	Loss: 100.701
+64000/69092	Loss: 98.902
+67200/69092	Loss: 98.618
+Training time 0:10:13.242627
+Epoch: 26 Average loss: 100.14
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 177)
+0/69092	Loss: 105.623
+3200/69092	Loss: 99.517
+6400/69092	Loss: 100.253
+9600/69092	Loss: 99.371
+12800/69092	Loss: 100.768
+16000/69092	Loss: 100.403
+19200/69092	Loss: 100.631
+22400/69092	Loss: 100.900
+25600/69092	Loss: 100.815
+28800/69092	Loss: 99.351
+32000/69092	Loss: 100.677
+35200/69092	Loss: 100.108
+38400/69092	Loss: 99.413
+41600/69092	Loss: 100.386
+44800/69092	Loss: 98.949
+48000/69092	Loss: 99.557
+51200/69092	Loss: 100.739
+54400/69092	Loss: 101.089
+57600/69092	Loss: 99.154
+60800/69092	Loss: 101.132
+64000/69092	Loss: 99.649
+67200/69092	Loss: 100.929
+Training time 0:10:31.626549
+Epoch: 27 Average loss: 100.20
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 178)
+0/69092	Loss: 95.884
+3200/69092	Loss: 99.686
+6400/69092	Loss: 99.836
+9600/69092	Loss: 100.794
+12800/69092	Loss: 100.388
+16000/69092	Loss: 99.477
+19200/69092	Loss: 101.988
+22400/69092	Loss: 99.644
+25600/69092	Loss: 101.782
+28800/69092	Loss: 100.246
+32000/69092	Loss: 100.852
+35200/69092	Loss: 100.964
+38400/69092	Loss: 99.352
+41600/69092	Loss: 101.068
+44800/69092	Loss: 98.179
+48000/69092	Loss: 100.101
+51200/69092	Loss: 99.964
+54400/69092	Loss: 99.895
+57600/69092	Loss: 100.055
+60800/69092	Loss: 99.892
+64000/69092	Loss: 101.129
+67200/69092	Loss: 99.472
+Training time 0:10:26.415918
+Epoch: 28 Average loss: 100.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 179)
+0/69092	Loss: 91.758
+3200/69092	Loss: 98.980
+6400/69092	Loss: 100.410
+9600/69092	Loss: 98.389
+12800/69092	Loss: 101.778
+16000/69092	Loss: 98.980
+19200/69092	Loss: 100.459
+22400/69092	Loss: 101.037
+25600/69092	Loss: 100.936
+28800/69092	Loss: 99.847
+32000/69092	Loss: 99.671
+35200/69092	Loss: 101.104
+38400/69092	Loss: 98.966
+41600/69092	Loss: 100.606
+44800/69092	Loss: 100.329
+48000/69092	Loss: 100.492
+51200/69092	Loss: 98.739
+54400/69092	Loss: 101.190
+57600/69092	Loss: 100.210
+60800/69092	Loss: 101.215
+64000/69092	Loss: 102.043
+67200/69092	Loss: 98.037
+Training time 0:10:31.627884
+Epoch: 29 Average loss: 100.12
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 180)
+0/69092	Loss: 99.603
+3200/69092	Loss: 100.262
+6400/69092	Loss: 99.990
+9600/69092	Loss: 99.990
+12800/69092	Loss: 99.227
+16000/69092	Loss: 99.937
+19200/69092	Loss: 99.885
+22400/69092	Loss: 99.973
+25600/69092	Loss: 100.742
+28800/69092	Loss: 100.392
+32000/69092	Loss: 99.453
+35200/69092	Loss: 100.560
+38400/69092	Loss: 101.674
+41600/69092	Loss: 100.410
+44800/69092	Loss: 98.796
+48000/69092	Loss: 99.496
+51200/69092	Loss: 98.951
+54400/69092	Loss: 99.372
+57600/69092	Loss: 99.080
+60800/69092	Loss: 101.399
+64000/69092	Loss: 100.448
+67200/69092	Loss: 101.755
+Training time 0:10:48.548870
+Epoch: 30 Average loss: 100.08
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 181)
+0/69092	Loss: 91.752
+3200/69092	Loss: 99.817
+6400/69092	Loss: 102.202
+9600/69092	Loss: 100.571
+12800/69092	Loss: 98.966
+16000/69092	Loss: 99.668
+19200/69092	Loss: 99.439
+22400/69092	Loss: 100.390
+25600/69092	Loss: 97.432
+28800/69092	Loss: 100.275
+32000/69092	Loss: 100.104
+35200/69092	Loss: 98.484
+38400/69092	Loss: 101.402
+41600/69092	Loss: 99.439
+44800/69092	Loss: 101.007
+48000/69092	Loss: 99.529
+51200/69092	Loss: 99.163
+54400/69092	Loss: 100.444
+57600/69092	Loss: 100.537
+60800/69092	Loss: 98.722
+64000/69092	Loss: 99.280
+67200/69092	Loss: 101.686
+Training time 0:10:14.941037
+Epoch: 31 Average loss: 99.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 182)
+0/69092	Loss: 106.586
+3200/69092	Loss: 100.005
+6400/69092	Loss: 99.821
+9600/69092	Loss: 99.832
+12800/69092	Loss: 99.667
+16000/69092	Loss: 99.305
+19200/69092	Loss: 100.230
+22400/69092	Loss: 99.397
+25600/69092	Loss: 100.039
+28800/69092	Loss: 101.120
+32000/69092	Loss: 100.445
+35200/69092	Loss: 99.876
+38400/69092	Loss: 99.501
+41600/69092	Loss: 100.364
+44800/69092	Loss: 101.419
+48000/69092	Loss: 100.961
+51200/69092	Loss: 100.997
+54400/69092	Loss: 99.904
+57600/69092	Loss: 100.214
+60800/69092	Loss: 100.010
+64000/69092	Loss: 100.869
+67200/69092	Loss: 99.687
+Training time 0:10:34.812231
+Epoch: 32 Average loss: 100.13
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 183)
+0/69092	Loss: 93.891
+3200/69092	Loss: 100.324
+6400/69092	Loss: 98.926
+9600/69092	Loss: 99.533
+12800/69092	Loss: 99.932
+16000/69092	Loss: 100.664
+19200/69092	Loss: 99.626
+22400/69092	Loss: 98.362
+25600/69092	Loss: 101.330
+28800/69092	Loss: 100.157
+32000/69092	Loss: 99.218
+35200/69092	Loss: 99.712
+38400/69092	Loss: 99.349
+41600/69092	Loss: 100.170
+44800/69092	Loss: 99.584
+48000/69092	Loss: 101.099
+51200/69092	Loss: 101.326
+54400/69092	Loss: 100.069
+57600/69092	Loss: 97.962
+60800/69092	Loss: 99.988
+64000/69092	Loss: 100.369
+67200/69092	Loss: 100.646
+Training time 0:10:34.876007
+Epoch: 33 Average loss: 99.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 184)
+0/69092	Loss: 109.234
+3200/69092	Loss: 100.259
+6400/69092	Loss: 99.103
+9600/69092	Loss: 99.288
+12800/69092	Loss: 99.466
+16000/69092	Loss: 99.369
+19200/69092	Loss: 99.338
+22400/69092	Loss: 99.939
+25600/69092	Loss: 100.008
+28800/69092	Loss: 99.636
+32000/69092	Loss: 100.290
+35200/69092	Loss: 98.803
+38400/69092	Loss: 101.810
+41600/69092	Loss: 98.660
+44800/69092	Loss: 100.392
+48000/69092	Loss: 100.782
+51200/69092	Loss: 101.097
+54400/69092	Loss: 98.786
+57600/69092	Loss: 100.128
+60800/69092	Loss: 100.663
+64000/69092	Loss: 99.414
+67200/69092	Loss: 99.784
+Training time 0:10:47.630232
+Epoch: 34 Average loss: 99.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 185)
+0/69092	Loss: 97.111
+3200/69092	Loss: 100.152
+6400/69092	Loss: 99.348
+9600/69092	Loss: 100.469
+12800/69092	Loss: 98.369
+16000/69092	Loss: 100.901
+19200/69092	Loss: 100.777
+22400/69092	Loss: 99.093
+25600/69092	Loss: 99.746
+28800/69092	Loss: 100.486
+32000/69092	Loss: 99.241
+35200/69092	Loss: 98.725
+38400/69092	Loss: 97.958
+41600/69092	Loss: 100.874
+44800/69092	Loss: 100.811
+48000/69092	Loss: 100.262
+51200/69092	Loss: 100.120
+54400/69092	Loss: 101.258
+57600/69092	Loss: 100.820
+60800/69092	Loss: 99.457
+64000/69092	Loss: 99.680
+67200/69092	Loss: 99.815
+Training time 0:10:41.843923
+Epoch: 35 Average loss: 99.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 186)
+0/69092	Loss: 108.355
+3200/69092	Loss: 98.779
+6400/69092	Loss: 100.292
+9600/69092	Loss: 98.851
+12800/69092	Loss: 100.044
+16000/69092	Loss: 98.120
+19200/69092	Loss: 99.108
+22400/69092	Loss: 101.134
+25600/69092	Loss: 100.805
+28800/69092	Loss: 100.451
+32000/69092	Loss: 99.621
+35200/69092	Loss: 99.175
+38400/69092	Loss: 99.566
+41600/69092	Loss: 100.592
+44800/69092	Loss: 99.871
+48000/69092	Loss: 99.017
+51200/69092	Loss: 100.155
+54400/69092	Loss: 100.068
+57600/69092	Loss: 100.351
+60800/69092	Loss: 101.316
+64000/69092	Loss: 100.137
+67200/69092	Loss: 99.779
+Training time 0:10:05.566934
+Epoch: 36 Average loss: 99.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 187)
+0/69092	Loss: 103.196
+3200/69092	Loss: 99.906
+6400/69092	Loss: 100.314
+9600/69092	Loss: 98.491
+12800/69092	Loss: 99.373
+16000/69092	Loss: 100.230
+19200/69092	Loss: 100.517
+22400/69092	Loss: 100.481
+25600/69092	Loss: 99.836
+28800/69092	Loss: 100.558
+32000/69092	Loss: 99.144
+35200/69092	Loss: 100.250
+38400/69092	Loss: 99.398
+41600/69092	Loss: 99.600
+44800/69092	Loss: 100.777
+48000/69092	Loss: 101.557
+51200/69092	Loss: 99.813
+54400/69092	Loss: 100.117
+57600/69092	Loss: 99.102
+60800/69092	Loss: 100.214
+64000/69092	Loss: 98.335
+67200/69092	Loss: 99.586
+Training time 0:10:04.009083
+Epoch: 37 Average loss: 99.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 188)
+0/69092	Loss: 107.788
+3200/69092	Loss: 99.971
+6400/69092	Loss: 99.769
+9600/69092	Loss: 99.672
+12800/69092	Loss: 98.309
+16000/69092	Loss: 100.179
+19200/69092	Loss: 99.373
+22400/69092	Loss: 101.619
+25600/69092	Loss: 100.711
+28800/69092	Loss: 100.456
+32000/69092	Loss: 99.981
+35200/69092	Loss: 100.431
+38400/69092	Loss: 99.393
+41600/69092	Loss: 99.713
+44800/69092	Loss: 100.156
+48000/69092	Loss: 98.664
+51200/69092	Loss: 101.249
+54400/69092	Loss: 97.876
+57600/69092	Loss: 98.876
+60800/69092	Loss: 100.144
+64000/69092	Loss: 98.713
+67200/69092	Loss: 102.235
+Training time 0:10:43.959253
+Epoch: 38 Average loss: 99.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 189)
+0/69092	Loss: 95.501
+3200/69092	Loss: 99.865
+6400/69092	Loss: 100.067
+9600/69092	Loss: 99.613
+12800/69092	Loss: 99.825
+16000/69092	Loss: 100.896
+19200/69092	Loss: 99.022
+22400/69092	Loss: 100.082
+25600/69092	Loss: 99.652
+28800/69092	Loss: 100.217
+32000/69092	Loss: 100.147
+35200/69092	Loss: 99.513
+38400/69092	Loss: 98.243
+41600/69092	Loss: 101.492
+44800/69092	Loss: 99.259
+48000/69092	Loss: 100.438
+51200/69092	Loss: 101.395
+54400/69092	Loss: 100.464
+57600/69092	Loss: 100.178
+60800/69092	Loss: 100.122
+64000/69092	Loss: 98.909
+67200/69092	Loss: 100.198
+Training time 0:10:17.392535
+Epoch: 39 Average loss: 99.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 190)
+0/69092	Loss: 101.971
+3200/69092	Loss: 100.184
+6400/69092	Loss: 99.472
+9600/69092	Loss: 100.074
+12800/69092	Loss: 99.729
+16000/69092	Loss: 99.095
+19200/69092	Loss: 98.950
+22400/69092	Loss: 100.000
+25600/69092	Loss: 98.855
+28800/69092	Loss: 99.936
+32000/69092	Loss: 99.257
+35200/69092	Loss: 100.012
+38400/69092	Loss: 100.004
+41600/69092	Loss: 99.095
+44800/69092	Loss: 99.975
+48000/69092	Loss: 99.939
+51200/69092	Loss: 100.654
+54400/69092	Loss: 98.649
+57600/69092	Loss: 100.555
+60800/69092	Loss: 100.283
+64000/69092	Loss: 99.914
+67200/69092	Loss: 99.788
+Training time 0:10:28.842219
+Epoch: 40 Average loss: 99.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 191)
+0/69092	Loss: 101.597
+3200/69092	Loss: 100.014
+6400/69092	Loss: 98.563
+9600/69092	Loss: 98.354
+12800/69092	Loss: 99.940
+16000/69092	Loss: 100.385
+19200/69092	Loss: 99.405
+22400/69092	Loss: 101.010
+25600/69092	Loss: 100.370
+28800/69092	Loss: 100.120
+32000/69092	Loss: 99.645
+35200/69092	Loss: 99.534
+38400/69092	Loss: 100.931
+41600/69092	Loss: 101.011
+44800/69092	Loss: 98.383
+48000/69092	Loss: 100.098
+51200/69092	Loss: 101.095
+54400/69092	Loss: 99.720
+57600/69092	Loss: 98.328
+60800/69092	Loss: 101.772
+64000/69092	Loss: 100.598
+67200/69092	Loss: 99.596
+Training time 0:10:45.286246
+Epoch: 41 Average loss: 99.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 192)
+0/69092	Loss: 91.291
+3200/69092	Loss: 98.867
+6400/69092	Loss: 99.181
+9600/69092	Loss: 99.653
+12800/69092	Loss: 100.358
+16000/69092	Loss: 100.018
+19200/69092	Loss: 98.716
+22400/69092	Loss: 100.581
+25600/69092	Loss: 99.702
+28800/69092	Loss: 100.165
+32000/69092	Loss: 100.310
+35200/69092	Loss: 100.323
+38400/69092	Loss: 99.728
+41600/69092	Loss: 99.181
+44800/69092	Loss: 99.004
+48000/69092	Loss: 98.477
+51200/69092	Loss: 100.643
+54400/69092	Loss: 101.339
+57600/69092	Loss: 100.399
+60800/69092	Loss: 99.899
+64000/69092	Loss: 99.267
+67200/69092	Loss: 100.047
+Training time 0:10:18.492338
+Epoch: 42 Average loss: 99.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 193)
+0/69092	Loss: 105.006
+3200/69092	Loss: 99.319
+6400/69092	Loss: 99.881
+9600/69092	Loss: 97.793
+12800/69092	Loss: 100.456
+16000/69092	Loss: 100.753
+19200/69092	Loss: 100.031
+22400/69092	Loss: 99.345
+25600/69092	Loss: 99.292
+28800/69092	Loss: 100.057
+32000/69092	Loss: 100.796
+35200/69092	Loss: 100.910
+38400/69092	Loss: 99.907
+41600/69092	Loss: 99.271
+44800/69092	Loss: 100.345
+48000/69092	Loss: 99.032
+51200/69092	Loss: 99.591
+54400/69092	Loss: 100.363
+57600/69092	Loss: 100.152
+60800/69092	Loss: 100.329
+64000/69092	Loss: 98.795
+67200/69092	Loss: 99.749
+Training time 0:10:32.316081
+Epoch: 43 Average loss: 99.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 194)
+0/69092	Loss: 109.327
+3200/69092	Loss: 99.620
+6400/69092	Loss: 101.251
+9600/69092	Loss: 99.205
+12800/69092	Loss: 100.275
+16000/69092	Loss: 100.633
+19200/69092	Loss: 100.554
+22400/69092	Loss: 99.521
+25600/69092	Loss: 100.220
+28800/69092	Loss: 99.770
+32000/69092	Loss: 100.229
+35200/69092	Loss: 100.142
+38400/69092	Loss: 100.114
+41600/69092	Loss: 99.020
+44800/69092	Loss: 99.948
+48000/69092	Loss: 99.449
+51200/69092	Loss: 100.691
+54400/69092	Loss: 99.656
+57600/69092	Loss: 99.175
+60800/69092	Loss: 97.822
+64000/69092	Loss: 100.637
+67200/69092	Loss: 98.860
+Training time 0:10:27.955207
+Epoch: 44 Average loss: 99.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 195)
+0/69092	Loss: 103.113
+3200/69092	Loss: 100.830
+6400/69092	Loss: 100.051
+9600/69092	Loss: 98.203
+12800/69092	Loss: 99.365
+16000/69092	Loss: 101.058
+19200/69092	Loss: 100.739
+22400/69092	Loss: 100.733
+25600/69092	Loss: 98.094
+28800/69092	Loss: 99.634
+32000/69092	Loss: 98.826
+35200/69092	Loss: 100.177
+38400/69092	Loss: 101.023
+41600/69092	Loss: 99.069
+44800/69092	Loss: 98.332
+48000/69092	Loss: 99.572
+51200/69092	Loss: 101.048
+54400/69092	Loss: 99.387
+57600/69092	Loss: 100.036
+60800/69092	Loss: 99.614
+64000/69092	Loss: 100.092
+67200/69092	Loss: 100.824
+Training time 0:10:20.707392
+Epoch: 45 Average loss: 99.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 196)
+0/69092	Loss: 101.672
+3200/69092	Loss: 100.151
+6400/69092	Loss: 98.475
+9600/69092	Loss: 98.938
+12800/69092	Loss: 99.368
+16000/69092	Loss: 100.406
+19200/69092	Loss: 101.791
+22400/69092	Loss: 98.229
+25600/69092	Loss: 99.229
+28800/69092	Loss: 99.775
+32000/69092	Loss: 100.879
+35200/69092	Loss: 99.694
+38400/69092	Loss: 99.279
+41600/69092	Loss: 99.232
+44800/69092	Loss: 99.763
+48000/69092	Loss: 99.679
+51200/69092	Loss: 101.186
+54400/69092	Loss: 100.612
+57600/69092	Loss: 101.177
+60800/69092	Loss: 99.868
+64000/69092	Loss: 99.273
+67200/69092	Loss: 100.419
+Training time 0:10:36.786436
+Epoch: 46 Average loss: 99.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 197)
+0/69092	Loss: 100.309
+3200/69092	Loss: 100.264
+6400/69092	Loss: 100.730
+9600/69092	Loss: 100.129
+12800/69092	Loss: 99.833
+16000/69092	Loss: 100.191
+19200/69092	Loss: 100.162
+22400/69092	Loss: 98.993
+25600/69092	Loss: 98.119
+28800/69092	Loss: 98.927
+32000/69092	Loss: 99.597
+35200/69092	Loss: 99.961
+38400/69092	Loss: 99.764
+41600/69092	Loss: 98.273
+44800/69092	Loss: 100.927
+48000/69092	Loss: 99.511
+51200/69092	Loss: 99.209
+54400/69092	Loss: 98.003
+57600/69092	Loss: 100.990
+60800/69092	Loss: 100.939
+64000/69092	Loss: 101.469
+67200/69092	Loss: 98.810
+Training time 0:10:40.852756
+Epoch: 47 Average loss: 99.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 198)
+0/69092	Loss: 105.644
+3200/69092	Loss: 100.593
+6400/69092	Loss: 101.211
+9600/69092	Loss: 100.058
+12800/69092	Loss: 99.996
+16000/69092	Loss: 99.575
+19200/69092	Loss: 100.106
+22400/69092	Loss: 99.275
+25600/69092	Loss: 98.502
+28800/69092	Loss: 99.723
+32000/69092	Loss: 99.027
+35200/69092	Loss: 101.237
+38400/69092	Loss: 100.273
+41600/69092	Loss: 98.902
+44800/69092	Loss: 98.972
+48000/69092	Loss: 100.254
+51200/69092	Loss: 98.863
+54400/69092	Loss: 100.031
+57600/69092	Loss: 99.992
+60800/69092	Loss: 98.660
+64000/69092	Loss: 100.026
+67200/69092	Loss: 100.506
+Training time 0:10:26.034638
+Epoch: 48 Average loss: 99.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 199)
+0/69092	Loss: 95.413
+3200/69092	Loss: 98.943
+6400/69092	Loss: 98.991
+9600/69092	Loss: 100.614
+12800/69092	Loss: 100.537
+16000/69092	Loss: 98.366
+19200/69092	Loss: 100.623
+22400/69092	Loss: 100.206
+25600/69092	Loss: 99.816
+28800/69092	Loss: 99.232
+32000/69092	Loss: 98.806
+35200/69092	Loss: 100.646
+38400/69092	Loss: 99.282
+41600/69092	Loss: 100.115
+44800/69092	Loss: 99.019
+48000/69092	Loss: 99.151
+51200/69092	Loss: 99.442
+54400/69092	Loss: 100.448
+57600/69092	Loss: 101.120
+60800/69092	Loss: 100.314
+64000/69092	Loss: 100.010
+67200/69092	Loss: 98.674
+Training time 0:10:21.240841
+Epoch: 49 Average loss: 99.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 200)
+0/69092	Loss: 102.408
+3200/69092	Loss: 100.761
+6400/69092	Loss: 97.953
+9600/69092	Loss: 98.630
+12800/69092	Loss: 98.831
+16000/69092	Loss: 98.589
+19200/69092	Loss: 99.892
+22400/69092	Loss: 99.324
+25600/69092	Loss: 101.391
+28800/69092	Loss: 99.549
+32000/69092	Loss: 99.111
+35200/69092	Loss: 99.079
+38400/69092	Loss: 100.512
+41600/69092	Loss: 100.609
+44800/69092	Loss: 99.491
+48000/69092	Loss: 98.808
+51200/69092	Loss: 100.457
+54400/69092	Loss: 99.549
+57600/69092	Loss: 99.309
+60800/69092	Loss: 100.732
+64000/69092	Loss: 99.489
+67200/69092	Loss: 100.023
+Training time 0:10:25.492892
+Epoch: 50 Average loss: 99.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 201)
+0/69092	Loss: 97.946
+3200/69092	Loss: 99.103
+6400/69092	Loss: 99.525
+9600/69092	Loss: 100.505
+12800/69092	Loss: 99.001
+16000/69092	Loss: 98.883
+19200/69092	Loss: 99.661
+22400/69092	Loss: 100.461
+25600/69092	Loss: 100.764
+28800/69092	Loss: 100.174
+32000/69092	Loss: 98.131
+35200/69092	Loss: 98.357
+38400/69092	Loss: 100.394
+41600/69092	Loss: 100.652
+44800/69092	Loss: 99.453
+48000/69092	Loss: 99.669
+51200/69092	Loss: 99.848
+54400/69092	Loss: 99.853
+57600/69092	Loss: 99.930
+60800/69092	Loss: 99.252
+64000/69092	Loss: 99.663
+67200/69092	Loss: 99.385
+Training time 0:10:11.897027
+Epoch: 51 Average loss: 99.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 202)
+0/69092	Loss: 100.107
+3200/69092	Loss: 99.804
+6400/69092	Loss: 99.210
+9600/69092	Loss: 98.463
+12800/69092	Loss: 98.645
+16000/69092	Loss: 98.991
+19200/69092	Loss: 100.865
+22400/69092	Loss: 99.669
+25600/69092	Loss: 99.627
+28800/69092	Loss: 99.284
+32000/69092	Loss: 98.647
+35200/69092	Loss: 100.887
+38400/69092	Loss: 98.235
+41600/69092	Loss: 98.853
+44800/69092	Loss: 100.267
+48000/69092	Loss: 99.703
+51200/69092	Loss: 99.212
+54400/69092	Loss: 99.498
+57600/69092	Loss: 99.871
+60800/69092	Loss: 100.398
+64000/69092	Loss: 99.988
+67200/69092	Loss: 100.443
+Training time 0:10:33.920889
+Epoch: 52 Average loss: 99.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 203)
+0/69092	Loss: 102.239
+3200/69092	Loss: 100.075
+6400/69092	Loss: 98.246
+9600/69092	Loss: 98.537
+12800/69092	Loss: 100.331
+16000/69092	Loss: 100.385
+19200/69092	Loss: 98.937
+22400/69092	Loss: 98.990
+25600/69092	Loss: 99.417
+28800/69092	Loss: 99.268
+32000/69092	Loss: 100.513
+35200/69092	Loss: 99.251
+38400/69092	Loss: 100.531
+41600/69092	Loss: 98.965
+44800/69092	Loss: 97.725
+48000/69092	Loss: 100.967
+51200/69092	Loss: 98.503
+54400/69092	Loss: 99.213
+57600/69092	Loss: 100.521
+60800/69092	Loss: 100.201
+64000/69092	Loss: 98.700
+67200/69092	Loss: 99.567
+Training time 0:10:38.298598
+Epoch: 53 Average loss: 99.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 204)
+0/69092	Loss: 105.655
+3200/69092	Loss: 101.401
+6400/69092	Loss: 99.467
+9600/69092	Loss: 98.936
+12800/69092	Loss: 99.665
+16000/69092	Loss: 99.952
+19200/69092	Loss: 98.737
+22400/69092	Loss: 98.863
+25600/69092	Loss: 97.455
+28800/69092	Loss: 99.410
+32000/69092	Loss: 98.793
+35200/69092	Loss: 99.978
+38400/69092	Loss: 99.341
+41600/69092	Loss: 100.227
+44800/69092	Loss: 100.890
+48000/69092	Loss: 97.993
+51200/69092	Loss: 99.457
+54400/69092	Loss: 99.362
+57600/69092	Loss: 99.603
+60800/69092	Loss: 100.673
+64000/69092	Loss: 100.219
+67200/69092	Loss: 101.139
+Training time 0:10:21.205873
+Epoch: 54 Average loss: 99.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 205)
+0/69092	Loss: 102.741
+3200/69092	Loss: 99.815
+6400/69092	Loss: 98.845
+9600/69092	Loss: 99.791
+12800/69092	Loss: 98.744
+16000/69092	Loss: 98.616
+19200/69092	Loss: 99.934
+22400/69092	Loss: 100.888
+25600/69092	Loss: 100.002
+28800/69092	Loss: 99.425
+32000/69092	Loss: 100.970
+35200/69092	Loss: 98.703
+38400/69092	Loss: 99.776
+41600/69092	Loss: 99.547
+44800/69092	Loss: 99.242
+48000/69092	Loss: 100.630
+51200/69092	Loss: 100.067
+54400/69092	Loss: 98.791
+57600/69092	Loss: 98.962
+60800/69092	Loss: 99.509
+64000/69092	Loss: 99.143
+67200/69092	Loss: 100.739
+Training time 0:10:28.607954
+Epoch: 55 Average loss: 99.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 206)
+0/69092	Loss: 101.518
+3200/69092	Loss: 99.409
+6400/69092	Loss: 100.732
+9600/69092	Loss: 98.345
+12800/69092	Loss: 98.863
+16000/69092	Loss: 99.533
+19200/69092	Loss: 97.889
+22400/69092	Loss: 99.086
+25600/69092	Loss: 98.706
+28800/69092	Loss: 99.156
+32000/69092	Loss: 100.096
+35200/69092	Loss: 99.982
+38400/69092	Loss: 100.506
+41600/69092	Loss: 99.459
+44800/69092	Loss: 100.491
+48000/69092	Loss: 100.745
+51200/69092	Loss: 99.351
+54400/69092	Loss: 99.836
+57600/69092	Loss: 98.923
+60800/69092	Loss: 98.979
+64000/69092	Loss: 99.750
+67200/69092	Loss: 99.852
+Training time 0:10:32.159731
+Epoch: 56 Average loss: 99.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 207)
+0/69092	Loss: 109.474
+3200/69092	Loss: 98.843
+6400/69092	Loss: 97.963
+9600/69092	Loss: 97.940
+12800/69092	Loss: 101.564
+16000/69092	Loss: 99.928
+19200/69092	Loss: 99.958
+22400/69092	Loss: 100.826
+25600/69092	Loss: 99.833
+28800/69092	Loss: 99.193
+32000/69092	Loss: 99.281
+35200/69092	Loss: 101.295
+38400/69092	Loss: 99.704
+41600/69092	Loss: 98.427
+44800/69092	Loss: 99.495
+48000/69092	Loss: 98.707
+51200/69092	Loss: 100.527
+54400/69092	Loss: 99.484
+57600/69092	Loss: 99.227
+60800/69092	Loss: 97.992
+64000/69092	Loss: 99.812
+67200/69092	Loss: 99.742
+Training time 0:10:26.434714
+Epoch: 57 Average loss: 99.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 208)
+0/69092	Loss: 89.529
+3200/69092	Loss: 99.274
+6400/69092	Loss: 98.912
+9600/69092	Loss: 99.182
+12800/69092	Loss: 101.189
+16000/69092	Loss: 100.550
+19200/69092	Loss: 99.465
+22400/69092	Loss: 100.113
+25600/69092	Loss: 99.419
+28800/69092	Loss: 99.792
+32000/69092	Loss: 100.569
+35200/69092	Loss: 99.029
+38400/69092	Loss: 99.296
+41600/69092	Loss: 99.008
+44800/69092	Loss: 99.276
+48000/69092	Loss: 100.129
+51200/69092	Loss: 99.816
+54400/69092	Loss: 99.758
+57600/69092	Loss: 99.577
+60800/69092	Loss: 99.559
+64000/69092	Loss: 99.507
+67200/69092	Loss: 99.881
+Training time 0:10:19.568203
+Epoch: 58 Average loss: 99.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 209)
+0/69092	Loss: 102.095
+3200/69092	Loss: 98.804
+6400/69092	Loss: 99.094
+9600/69092	Loss: 101.257
+12800/69092	Loss: 100.161
+16000/69092	Loss: 100.096
+19200/69092	Loss: 98.840
+22400/69092	Loss: 98.773
+25600/69092	Loss: 99.646
+28800/69092	Loss: 98.767
+32000/69092	Loss: 98.419
+35200/69092	Loss: 99.061
+38400/69092	Loss: 99.012
+41600/69092	Loss: 99.509
+44800/69092	Loss: 97.732
+48000/69092	Loss: 98.475
+51200/69092	Loss: 100.461
+54400/69092	Loss: 100.377
+57600/69092	Loss: 98.997
+60800/69092	Loss: 100.422
+64000/69092	Loss: 99.270
+67200/69092	Loss: 100.090
+Training time 0:10:40.459240
+Epoch: 59 Average loss: 99.47
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 210)
+0/69092	Loss: 95.130
+3200/69092	Loss: 98.785
+6400/69092	Loss: 99.397
+9600/69092	Loss: 100.195
+12800/69092	Loss: 98.950
+16000/69092	Loss: 99.349
+19200/69092	Loss: 99.120
+22400/69092	Loss: 99.751
+25600/69092	Loss: 99.621
+28800/69092	Loss: 99.267
+32000/69092	Loss: 98.711
+35200/69092	Loss: 99.986
+38400/69092	Loss: 100.057
+41600/69092	Loss: 98.161
+44800/69092	Loss: 100.598
+48000/69092	Loss: 100.427
+51200/69092	Loss: 99.950
+54400/69092	Loss: 99.130
+57600/69092	Loss: 100.212
+60800/69092	Loss: 100.297
+64000/69092	Loss: 97.729
+67200/69092	Loss: 98.686
+Training time 0:10:32.378114
+Epoch: 60 Average loss: 99.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 211)
+0/69092	Loss: 97.846
+3200/69092	Loss: 99.329
+6400/69092	Loss: 100.636
+9600/69092	Loss: 99.569
+12800/69092	Loss: 99.186
+16000/69092	Loss: 99.478
+19200/69092	Loss: 100.048
+22400/69092	Loss: 99.767
+25600/69092	Loss: 98.263
+28800/69092	Loss: 99.787
+32000/69092	Loss: 99.854
+35200/69092	Loss: 99.202
+38400/69092	Loss: 98.750
+41600/69092	Loss: 99.060
+44800/69092	Loss: 100.517
+48000/69092	Loss: 98.832
+51200/69092	Loss: 100.595
+54400/69092	Loss: 97.948
+57600/69092	Loss: 100.756
+60800/69092	Loss: 97.541
+64000/69092	Loss: 99.417
+67200/69092	Loss: 99.893
+Training time 0:10:28.694864
+Epoch: 61 Average loss: 99.45
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 212)
+0/69092	Loss: 93.360
+3200/69092	Loss: 98.589
+6400/69092	Loss: 98.516
+9600/69092	Loss: 98.308
+12800/69092	Loss: 101.047
+16000/69092	Loss: 100.486
+19200/69092	Loss: 100.801
+22400/69092	Loss: 99.115
+25600/69092	Loss: 99.551
+28800/69092	Loss: 99.936
+32000/69092	Loss: 99.656
+35200/69092	Loss: 98.617
+38400/69092	Loss: 97.997
+41600/69092	Loss: 98.681
+44800/69092	Loss: 100.006
+48000/69092	Loss: 99.858
+51200/69092	Loss: 97.644
+54400/69092	Loss: 100.042
+57600/69092	Loss: 100.402
+60800/69092	Loss: 99.417
+64000/69092	Loss: 99.340
+67200/69092	Loss: 100.697
+Training time 0:10:31.409032
+Epoch: 62 Average loss: 99.45
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 213)
+0/69092	Loss: 84.580
+3200/69092	Loss: 99.229
+6400/69092	Loss: 99.526
+9600/69092	Loss: 99.732
+12800/69092	Loss: 99.422
+16000/69092	Loss: 99.754
+19200/69092	Loss: 98.123
+22400/69092	Loss: 99.946
+25600/69092	Loss: 99.046
+28800/69092	Loss: 100.582
+32000/69092	Loss: 100.366
+35200/69092	Loss: 99.814
+38400/69092	Loss: 97.370
+41600/69092	Loss: 99.952
+44800/69092	Loss: 99.620
+48000/69092	Loss: 99.263
+51200/69092	Loss: 97.473
+54400/69092	Loss: 99.297
+57600/69092	Loss: 98.905
+60800/69092	Loss: 98.707
+64000/69092	Loss: 100.912
+67200/69092	Loss: 100.969
+Training time 0:10:17.362485
+Epoch: 63 Average loss: 99.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 214)
+0/69092	Loss: 114.400
+3200/69092	Loss: 97.764
+6400/69092	Loss: 99.099
+9600/69092	Loss: 98.859
+12800/69092	Loss: 97.764
+16000/69092	Loss: 99.153
+19200/69092	Loss: 97.880
+22400/69092	Loss: 99.759
+25600/69092	Loss: 100.466
+28800/69092	Loss: 99.716
+32000/69092	Loss: 100.597
+35200/69092	Loss: 100.961
+38400/69092	Loss: 97.704
+41600/69092	Loss: 101.317
+44800/69092	Loss: 99.530
+48000/69092	Loss: 100.704
+51200/69092	Loss: 99.413
+54400/69092	Loss: 99.026
+57600/69092	Loss: 100.211
+60800/69092	Loss: 98.438
+64000/69092	Loss: 100.655
+67200/69092	Loss: 98.607
+Training time 0:10:36.457637
+Epoch: 64 Average loss: 99.44
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 215)
+0/69092	Loss: 96.599
+3200/69092	Loss: 98.555
+6400/69092	Loss: 99.314
+9600/69092	Loss: 99.056
+12800/69092	Loss: 98.790
+16000/69092	Loss: 98.815
+19200/69092	Loss: 98.971
+22400/69092	Loss: 99.589
+25600/69092	Loss: 100.497
+28800/69092	Loss: 99.577
+32000/69092	Loss: 98.631
+35200/69092	Loss: 99.650
+38400/69092	Loss: 99.623
+41600/69092	Loss: 100.140
+44800/69092	Loss: 97.560
+48000/69092	Loss: 98.809
+51200/69092	Loss: 99.295
+54400/69092	Loss: 99.682
+57600/69092	Loss: 100.089
+60800/69092	Loss: 100.863
+64000/69092	Loss: 100.211
+67200/69092	Loss: 98.723
+Training time 0:10:27.230790
+Epoch: 65 Average loss: 99.41
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 216)
+0/69092	Loss: 100.366
+3200/69092	Loss: 99.686
+6400/69092	Loss: 98.964
+9600/69092	Loss: 99.077
+12800/69092	Loss: 99.877
+16000/69092	Loss: 98.458
+19200/69092	Loss: 100.246
+22400/69092	Loss: 97.611
+25600/69092	Loss: 99.237
+28800/69092	Loss: 100.466
+32000/69092	Loss: 98.007
+35200/69092	Loss: 97.007
+38400/69092	Loss: 99.961
+41600/69092	Loss: 99.189
+44800/69092	Loss: 99.750
+48000/69092	Loss: 100.621
+51200/69092	Loss: 100.004
+54400/69092	Loss: 98.347
+57600/69092	Loss: 98.564
+60800/69092	Loss: 101.066
+64000/69092	Loss: 100.448
+67200/69092	Loss: 99.723
+Training time 0:10:22.426309
+Epoch: 66 Average loss: 99.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 217)
+0/69092	Loss: 98.789
+3200/69092	Loss: 99.339
+6400/69092	Loss: 98.521
+9600/69092	Loss: 98.536
+12800/69092	Loss: 98.876
+16000/69092	Loss: 99.705
+19200/69092	Loss: 98.964
+22400/69092	Loss: 98.826
+25600/69092	Loss: 99.523
+28800/69092	Loss: 99.250
+32000/69092	Loss: 98.844
+35200/69092	Loss: 99.166
+38400/69092	Loss: 101.091
+41600/69092	Loss: 99.869
+44800/69092	Loss: 99.679
+48000/69092	Loss: 99.413
+51200/69092	Loss: 100.144
+54400/69092	Loss: 99.404
+57600/69092	Loss: 98.200
+60800/69092	Loss: 100.960
+64000/69092	Loss: 100.765
+67200/69092	Loss: 101.017
+Training time 0:10:40.205976
+Epoch: 67 Average loss: 99.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 218)
+0/69092	Loss: 109.803
+3200/69092	Loss: 99.957
+6400/69092	Loss: 99.134
+9600/69092	Loss: 100.166
+12800/69092	Loss: 98.530
+16000/69092	Loss: 98.898
+19200/69092	Loss: 98.245
+22400/69092	Loss: 100.597
+25600/69092	Loss: 100.457
+28800/69092	Loss: 98.862
+32000/69092	Loss: 97.467
+35200/69092	Loss: 99.263
+38400/69092	Loss: 99.180
+41600/69092	Loss: 99.412
+44800/69092	Loss: 99.609
+48000/69092	Loss: 99.519
+51200/69092	Loss: 100.844
+54400/69092	Loss: 97.654
+57600/69092	Loss: 98.671
+60800/69092	Loss: 99.506
+64000/69092	Loss: 99.574
+67200/69092	Loss: 99.087
+Training time 0:10:28.822329
+Epoch: 68 Average loss: 99.31
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 219)
+0/69092	Loss: 97.867
+3200/69092	Loss: 98.609
+6400/69092	Loss: 98.641
+9600/69092	Loss: 99.894
+12800/69092	Loss: 100.005
+16000/69092	Loss: 99.819
+19200/69092	Loss: 98.976
+22400/69092	Loss: 98.451
+25600/69092	Loss: 98.603
+28800/69092	Loss: 98.912
+32000/69092	Loss: 99.339
+35200/69092	Loss: 101.135
+38400/69092	Loss: 99.092
+41600/69092	Loss: 98.658
+44800/69092	Loss: 98.752
+48000/69092	Loss: 97.118
+51200/69092	Loss: 100.844
+54400/69092	Loss: 99.823
+57600/69092	Loss: 99.695
+60800/69092	Loss: 101.050
+64000/69092	Loss: 97.502
+67200/69092	Loss: 99.955
+Training time 0:10:18.164627
+Epoch: 69 Average loss: 99.31
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 220)
+0/69092	Loss: 94.395
+3200/69092	Loss: 100.399
+6400/69092	Loss: 100.678
+9600/69092	Loss: 99.434
+12800/69092	Loss: 100.388
+16000/69092	Loss: 99.588
+19200/69092	Loss: 99.382
+22400/69092	Loss: 97.942
+25600/69092	Loss: 99.185
+28800/69092	Loss: 98.890
+32000/69092	Loss: 99.167
+35200/69092	Loss: 100.040
+38400/69092	Loss: 99.774
+41600/69092	Loss: 98.856
+44800/69092	Loss: 99.065
+48000/69092	Loss: 98.722
+51200/69092	Loss: 97.716
+54400/69092	Loss: 100.949
+57600/69092	Loss: 98.078
+60800/69092	Loss: 99.115
+64000/69092	Loss: 99.518
+67200/69092	Loss: 98.646
+Training time 0:10:37.524317
+Epoch: 70 Average loss: 99.31
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 221)
+0/69092	Loss: 105.368
+3200/69092	Loss: 99.256
+6400/69092	Loss: 99.528
+9600/69092	Loss: 100.234
+12800/69092	Loss: 99.197
+16000/69092	Loss: 100.231
+19200/69092	Loss: 98.183
+22400/69092	Loss: 98.898
+25600/69092	Loss: 99.552
+28800/69092	Loss: 99.032
+32000/69092	Loss: 100.158
+35200/69092	Loss: 97.229
+38400/69092	Loss: 99.679
+41600/69092	Loss: 99.922
+44800/69092	Loss: 99.412
+48000/69092	Loss: 99.900
+51200/69092	Loss: 99.628
+54400/69092	Loss: 97.570
+57600/69092	Loss: 99.811
+60800/69092	Loss: 100.126
+64000/69092	Loss: 97.179
+67200/69092	Loss: 99.324
+Training time 0:10:31.258195
+Epoch: 71 Average loss: 99.31
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 222)
+0/69092	Loss: 104.108
+3200/69092	Loss: 98.577
+6400/69092	Loss: 99.775
+9600/69092	Loss: 100.890
+12800/69092	Loss: 97.435
+16000/69092	Loss: 97.928
+19200/69092	Loss: 98.478
+22400/69092	Loss: 100.490
+25600/69092	Loss: 99.116
+28800/69092	Loss: 99.096
+32000/69092	Loss: 97.359
+35200/69092	Loss: 99.158
+38400/69092	Loss: 101.062
+41600/69092	Loss: 99.293
+44800/69092	Loss: 99.071
+48000/69092	Loss: 100.375
+51200/69092	Loss: 101.212
+54400/69092	Loss: 99.896
+57600/69092	Loss: 99.020
+60800/69092	Loss: 99.228
+64000/69092	Loss: 99.576
+67200/69092	Loss: 98.851
+Training time 0:10:30.945296
+Epoch: 72 Average loss: 99.34
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 223)
+0/69092	Loss: 93.491
+3200/69092	Loss: 99.093
+6400/69092	Loss: 99.817
+9600/69092	Loss: 99.590
+12800/69092	Loss: 98.515
+16000/69092	Loss: 99.938
+19200/69092	Loss: 99.258
+22400/69092	Loss: 98.386
+25600/69092	Loss: 102.214
+28800/69092	Loss: 99.706
+32000/69092	Loss: 98.739
+35200/69092	Loss: 98.925
+38400/69092	Loss: 99.295
+41600/69092	Loss: 98.350
+44800/69092	Loss: 98.394
+48000/69092	Loss: 99.782
+51200/69092	Loss: 98.796
+54400/69092	Loss: 100.287
+57600/69092	Loss: 100.266
+60800/69092	Loss: 99.069
+64000/69092	Loss: 99.144
+67200/69092	Loss: 99.899
+Training time 0:10:31.165774
+Epoch: 73 Average loss: 99.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 224)
+0/69092	Loss: 106.387
+3200/69092	Loss: 98.902
+6400/69092	Loss: 100.000
+9600/69092	Loss: 98.327
+12800/69092	Loss: 99.572
+16000/69092	Loss: 99.375
+19200/69092	Loss: 98.281
+22400/69092	Loss: 99.901
+25600/69092	Loss: 99.264
+28800/69092	Loss: 98.952
+32000/69092	Loss: 100.325
+35200/69092	Loss: 99.743
+38400/69092	Loss: 99.838
+41600/69092	Loss: 100.191
+44800/69092	Loss: 99.107
+48000/69092	Loss: 98.932
+51200/69092	Loss: 99.173
+54400/69092	Loss: 98.154
+57600/69092	Loss: 99.257
+60800/69092	Loss: 98.945
+64000/69092	Loss: 99.543
+67200/69092	Loss: 99.801
+Training time 0:10:34.406944
+Epoch: 74 Average loss: 99.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 225)
+0/69092	Loss: 98.389
+3200/69092	Loss: 100.869
+6400/69092	Loss: 98.677
+9600/69092	Loss: 98.637
+12800/69092	Loss: 97.887
+16000/69092	Loss: 98.800
+19200/69092	Loss: 97.284
+22400/69092	Loss: 99.148
+25600/69092	Loss: 99.804
+28800/69092	Loss: 99.968
+32000/69092	Loss: 100.616
+35200/69092	Loss: 99.178
+38400/69092	Loss: 98.575
+41600/69092	Loss: 98.959
+44800/69092	Loss: 99.988
+48000/69092	Loss: 99.310
+51200/69092	Loss: 99.221
+54400/69092	Loss: 100.472
+57600/69092	Loss: 99.669
+60800/69092	Loss: 100.452
+64000/69092	Loss: 97.570
+67200/69092	Loss: 99.181
+Training time 0:10:17.411851
+Epoch: 75 Average loss: 99.22
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 226)
+0/69092	Loss: 98.780
+3200/69092	Loss: 99.397
+6400/69092	Loss: 99.242
+9600/69092	Loss: 100.508
+12800/69092	Loss: 99.479
+16000/69092	Loss: 100.158
+19200/69092	Loss: 99.054
+22400/69092	Loss: 98.258
+25600/69092	Loss: 98.245
+28800/69092	Loss: 99.051
+32000/69092	Loss: 98.291
+35200/69092	Loss: 99.707
+38400/69092	Loss: 99.244
+41600/69092	Loss: 100.194
+44800/69092	Loss: 98.354
+48000/69092	Loss: 99.872
+51200/69092	Loss: 99.970
+54400/69092	Loss: 98.065
+57600/69092	Loss: 98.466
+60800/69092	Loss: 98.341
+64000/69092	Loss: 99.715
+67200/69092	Loss: 100.325
+Training time 0:10:38.849781
+Epoch: 76 Average loss: 99.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 227)
+0/69092	Loss: 102.952
+3200/69092	Loss: 100.087
+6400/69092	Loss: 99.581
+9600/69092	Loss: 100.062
+12800/69092	Loss: 100.268
+16000/69092	Loss: 99.628
+19200/69092	Loss: 99.227
+22400/69092	Loss: 99.407
+25600/69092	Loss: 97.170
+28800/69092	Loss: 100.830
+32000/69092	Loss: 97.849
+35200/69092	Loss: 100.026
+38400/69092	Loss: 99.145
+41600/69092	Loss: 98.742
+44800/69092	Loss: 100.311
+48000/69092	Loss: 99.138
+51200/69092	Loss: 98.717
+54400/69092	Loss: 98.835
+57600/69092	Loss: 98.037
+60800/69092	Loss: 97.376
+64000/69092	Loss: 98.881
+67200/69092	Loss: 99.222
+Training time 0:10:26.673666
+Epoch: 77 Average loss: 99.19
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 228)
+0/69092	Loss: 87.921
+3200/69092	Loss: 100.402
+6400/69092	Loss: 99.976
+9600/69092	Loss: 98.764
+12800/69092	Loss: 98.846
+16000/69092	Loss: 100.066
+19200/69092	Loss: 98.141
+22400/69092	Loss: 99.022
+25600/69092	Loss: 97.897
+28800/69092	Loss: 99.372
+32000/69092	Loss: 100.833
+35200/69092	Loss: 99.021
+38400/69092	Loss: 99.166
+41600/69092	Loss: 99.064
+44800/69092	Loss: 98.650
+48000/69092	Loss: 100.626
+51200/69092	Loss: 99.083
+54400/69092	Loss: 99.847
+57600/69092	Loss: 98.998
+60800/69092	Loss: 98.627
+64000/69092	Loss: 98.806
+67200/69092	Loss: 99.728
+Training time 0:10:37.664902
+Epoch: 78 Average loss: 99.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 229)
+0/69092	Loss: 109.811
+3200/69092	Loss: 100.358
+6400/69092	Loss: 101.364
+9600/69092	Loss: 98.614
+12800/69092	Loss: 98.648
+16000/69092	Loss: 98.593
+19200/69092	Loss: 97.558
+22400/69092	Loss: 99.017
+25600/69092	Loss: 100.614
+28800/69092	Loss: 99.702
+32000/69092	Loss: 98.807
+35200/69092	Loss: 99.061
+38400/69092	Loss: 98.723
+41600/69092	Loss: 98.554
+44800/69092	Loss: 99.565
+48000/69092	Loss: 98.677
+51200/69092	Loss: 99.086
+54400/69092	Loss: 99.887
+57600/69092	Loss: 100.090
+60800/69092	Loss: 99.174
+64000/69092	Loss: 98.506
+67200/69092	Loss: 98.298
+Training time 0:10:33.331640
+Epoch: 79 Average loss: 99.22
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 230)
+0/69092	Loss: 94.283
+3200/69092	Loss: 99.549
+6400/69092	Loss: 98.015
+9600/69092	Loss: 98.759
+12800/69092	Loss: 99.363
+16000/69092	Loss: 100.129
+19200/69092	Loss: 99.409
+22400/69092	Loss: 99.431
+25600/69092	Loss: 100.150
+28800/69092	Loss: 99.732
+32000/69092	Loss: 100.437
+35200/69092	Loss: 98.752
+38400/69092	Loss: 97.004
+41600/69092	Loss: 98.458
+44800/69092	Loss: 99.319
+48000/69092	Loss: 98.833
+51200/69092	Loss: 99.067
+54400/69092	Loss: 98.386
+57600/69092	Loss: 98.963
+60800/69092	Loss: 99.550
+64000/69092	Loss: 100.058
+67200/69092	Loss: 100.280
+Training time 0:10:23.848317
+Epoch: 80 Average loss: 99.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 231)
+0/69092	Loss: 101.924
+3200/69092	Loss: 99.985
+6400/69092	Loss: 97.544
+9600/69092	Loss: 98.280
+12800/69092	Loss: 97.306
+16000/69092	Loss: 99.610
+19200/69092	Loss: 99.412
+22400/69092	Loss: 99.224
+25600/69092	Loss: 99.132
+28800/69092	Loss: 99.296
+32000/69092	Loss: 100.490
+35200/69092	Loss: 98.591
+38400/69092	Loss: 99.881
+41600/69092	Loss: 98.775
+44800/69092	Loss: 99.705
+48000/69092	Loss: 100.777
+51200/69092	Loss: 97.449
+54400/69092	Loss: 100.868
+57600/69092	Loss: 100.173
+60800/69092	Loss: 99.337
+64000/69092	Loss: 100.408
+67200/69092	Loss: 98.402
+Training time 0:10:36.524471
+Epoch: 81 Average loss: 99.28
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 232)
+0/69092	Loss: 103.526
+3200/69092	Loss: 99.547
+6400/69092	Loss: 98.269
+9600/69092	Loss: 98.637
+12800/69092	Loss: 99.514
+16000/69092	Loss: 99.068
+19200/69092	Loss: 99.232
+22400/69092	Loss: 99.161
+25600/69092	Loss: 98.426
+28800/69092	Loss: 100.371
+32000/69092	Loss: 99.635
+35200/69092	Loss: 99.191
+38400/69092	Loss: 97.908
+41600/69092	Loss: 100.038
+44800/69092	Loss: 99.239
+48000/69092	Loss: 99.931
+51200/69092	Loss: 97.986
+54400/69092	Loss: 99.182
+57600/69092	Loss: 99.678
+60800/69092	Loss: 99.397
+64000/69092	Loss: 98.969
+67200/69092	Loss: 100.575
+Training time 0:10:48.089806
+Epoch: 82 Average loss: 99.23
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 233)
+0/69092	Loss: 92.129
+3200/69092	Loss: 100.658
+6400/69092	Loss: 98.405
+9600/69092	Loss: 98.366
+12800/69092	Loss: 98.647
+16000/69092	Loss: 96.981
+19200/69092	Loss: 99.084
+22400/69092	Loss: 99.128
+25600/69092	Loss: 100.695
+28800/69092	Loss: 98.688
+32000/69092	Loss: 99.727
+35200/69092	Loss: 98.280
+38400/69092	Loss: 99.637
+41600/69092	Loss: 99.496
+44800/69092	Loss: 99.707
+48000/69092	Loss: 98.748
+51200/69092	Loss: 100.248
+54400/69092	Loss: 98.489
+57600/69092	Loss: 100.189
+60800/69092	Loss: 98.423
+64000/69092	Loss: 99.148
+67200/69092	Loss: 99.478
+Training time 0:09:45.925560
+Epoch: 83 Average loss: 99.20
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 234)
+0/69092	Loss: 93.463
+3200/69092	Loss: 99.626
+6400/69092	Loss: 97.580
+9600/69092	Loss: 98.217
+12800/69092	Loss: 98.922
+16000/69092	Loss: 99.757
+19200/69092	Loss: 100.830
+22400/69092	Loss: 99.100
+25600/69092	Loss: 99.799
+28800/69092	Loss: 100.161
+32000/69092	Loss: 100.623
+35200/69092	Loss: 97.484
+38400/69092	Loss: 97.975
+41600/69092	Loss: 97.973
+44800/69092	Loss: 99.185
+48000/69092	Loss: 99.038
+51200/69092	Loss: 99.636
+54400/69092	Loss: 99.811
+57600/69092	Loss: 100.309
+60800/69092	Loss: 97.666
+64000/69092	Loss: 97.866
+67200/69092	Loss: 99.766
+Training time 0:10:16.510681
+Epoch: 84 Average loss: 99.13
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 235)
+0/69092	Loss: 102.812
+3200/69092	Loss: 98.052
+6400/69092	Loss: 99.620
+9600/69092	Loss: 99.427
+12800/69092	Loss: 99.510
+16000/69092	Loss: 101.195
+19200/69092	Loss: 100.284
+22400/69092	Loss: 98.965
+25600/69092	Loss: 97.533
+28800/69092	Loss: 98.793
+32000/69092	Loss: 98.119
+35200/69092	Loss: 97.290
+38400/69092	Loss: 99.500
+41600/69092	Loss: 99.102
+44800/69092	Loss: 101.072
+48000/69092	Loss: 99.608
+51200/69092	Loss: 98.555
+54400/69092	Loss: 98.967
+57600/69092	Loss: 97.408
+60800/69092	Loss: 99.532
+64000/69092	Loss: 99.765
+67200/69092	Loss: 97.934
+Training time 0:10:15.160627
+Epoch: 85 Average loss: 99.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 236)
+0/69092	Loss: 102.621
+3200/69092	Loss: 99.022
+6400/69092	Loss: 98.307
+9600/69092	Loss: 100.852
+12800/69092	Loss: 99.912
+16000/69092	Loss: 99.109
+19200/69092	Loss: 100.314
+22400/69092	Loss: 97.830
+25600/69092	Loss: 100.599
+28800/69092	Loss: 99.092
+32000/69092	Loss: 99.244
+35200/69092	Loss: 97.937
+38400/69092	Loss: 100.204
+41600/69092	Loss: 99.820
+44800/69092	Loss: 99.690
+48000/69092	Loss: 98.882
+51200/69092	Loss: 97.975
+54400/69092	Loss: 98.407
+57600/69092	Loss: 98.634
+60800/69092	Loss: 99.031
+64000/69092	Loss: 99.036
+67200/69092	Loss: 98.991
+Training time 0:10:45.680722
+Epoch: 86 Average loss: 99.19
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 237)
+0/69092	Loss: 104.285
+3200/69092	Loss: 99.902
+6400/69092	Loss: 98.074
+9600/69092	Loss: 98.142
+12800/69092	Loss: 98.598
+16000/69092	Loss: 98.965
+19200/69092	Loss: 99.079
+22400/69092	Loss: 98.010
+25600/69092	Loss: 99.684
+28800/69092	Loss: 97.595
+32000/69092	Loss: 98.295
+35200/69092	Loss: 99.976
+38400/69092	Loss: 99.888
+41600/69092	Loss: 99.573
+44800/69092	Loss: 99.795
+48000/69092	Loss: 99.878
+51200/69092	Loss: 99.294
+54400/69092	Loss: 100.283
+57600/69092	Loss: 98.221
+60800/69092	Loss: 99.276
+64000/69092	Loss: 97.463
+67200/69092	Loss: 100.611
+Training time 0:10:12.430585
+Epoch: 87 Average loss: 99.09
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 238)
+0/69092	Loss: 101.892
+3200/69092	Loss: 100.164
+6400/69092	Loss: 99.467
+9600/69092	Loss: 98.335
+12800/69092	Loss: 99.113
+16000/69092	Loss: 99.338
+19200/69092	Loss: 99.825
+22400/69092	Loss: 100.239
+25600/69092	Loss: 98.354
+28800/69092	Loss: 97.892
+32000/69092	Loss: 98.672
+35200/69092	Loss: 98.835
+38400/69092	Loss: 98.258
+41600/69092	Loss: 100.696
+44800/69092	Loss: 98.587
+48000/69092	Loss: 99.385
+51200/69092	Loss: 98.473
+54400/69092	Loss: 98.644
+57600/69092	Loss: 100.082
+60800/69092	Loss: 99.625
+64000/69092	Loss: 99.819
+67200/69092	Loss: 99.417
+Training time 0:10:32.449104
+Epoch: 88 Average loss: 99.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 239)
+0/69092	Loss: 105.595
+3200/69092	Loss: 98.453
+6400/69092	Loss: 97.851
+9600/69092	Loss: 98.561
+12800/69092	Loss: 101.079
+16000/69092	Loss: 99.070
+19200/69092	Loss: 99.938
+22400/69092	Loss: 99.074
+25600/69092	Loss: 99.105
+28800/69092	Loss: 98.036
+32000/69092	Loss: 99.721
+35200/69092	Loss: 98.840
+38400/69092	Loss: 100.590
+41600/69092	Loss: 98.668
+44800/69092	Loss: 98.289
+48000/69092	Loss: 98.401
+51200/69092	Loss: 99.559
+54400/69092	Loss: 99.276
+57600/69092	Loss: 97.903
+60800/69092	Loss: 99.403
+64000/69092	Loss: 99.028
+67200/69092	Loss: 100.135
+Training time 0:10:34.555334
+Epoch: 89 Average loss: 99.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 240)
+0/69092	Loss: 95.125
+3200/69092	Loss: 99.690
+6400/69092	Loss: 97.846
+9600/69092	Loss: 97.319
+12800/69092	Loss: 99.719
+16000/69092	Loss: 99.222
+19200/69092	Loss: 99.902
+22400/69092	Loss: 99.044
+25600/69092	Loss: 97.726
+28800/69092	Loss: 99.980
+32000/69092	Loss: 98.695
+35200/69092	Loss: 99.287
+38400/69092	Loss: 99.201
+41600/69092	Loss: 98.397
+44800/69092	Loss: 99.932
+48000/69092	Loss: 99.465
+51200/69092	Loss: 99.647
+54400/69092	Loss: 97.407
+57600/69092	Loss: 100.467
+60800/69092	Loss: 99.159
+64000/69092	Loss: 100.879
+67200/69092	Loss: 97.347
+Training time 0:10:10.573935
+Epoch: 90 Average loss: 99.09
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 241)
+0/69092	Loss: 111.658
+3200/69092	Loss: 97.923
+6400/69092	Loss: 99.544
+9600/69092	Loss: 99.224
+12800/69092	Loss: 100.153
+16000/69092	Loss: 99.906
+19200/69092	Loss: 99.125
+22400/69092	Loss: 96.866
+25600/69092	Loss: 97.861
+28800/69092	Loss: 98.636
+32000/69092	Loss: 98.740
+35200/69092	Loss: 100.130
+38400/69092	Loss: 99.103
+41600/69092	Loss: 98.502
+44800/69092	Loss: 100.889
+48000/69092	Loss: 99.161
+51200/69092	Loss: 98.216
+54400/69092	Loss: 98.799
+57600/69092	Loss: 99.252
+60800/69092	Loss: 98.619
+64000/69092	Loss: 98.038
+67200/69092	Loss: 101.625
+Training time 0:10:26.970431
+Epoch: 91 Average loss: 99.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 242)
+0/69092	Loss: 97.840
+3200/69092	Loss: 99.273
+6400/69092	Loss: 98.959
+9600/69092	Loss: 99.583
+12800/69092	Loss: 98.686
+16000/69092	Loss: 99.050
+19200/69092	Loss: 98.815
+22400/69092	Loss: 97.071
+25600/69092	Loss: 98.985
+28800/69092	Loss: 99.336
+32000/69092	Loss: 98.921
+35200/69092	Loss: 98.031
+38400/69092	Loss: 99.580
+41600/69092	Loss: 99.806
+44800/69092	Loss: 99.071
+48000/69092	Loss: 97.771
+51200/69092	Loss: 99.534
+54400/69092	Loss: 98.068
+57600/69092	Loss: 98.452
+60800/69092	Loss: 98.951
+64000/69092	Loss: 99.077
+67200/69092	Loss: 99.067
+Training time 0:10:25.025753
+Epoch: 92 Average loss: 98.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 243)
+0/69092	Loss: 107.718
+3200/69092	Loss: 101.105
+6400/69092	Loss: 97.580
+9600/69092	Loss: 97.574
+12800/69092	Loss: 99.387
+16000/69092	Loss: 97.995
+19200/69092	Loss: 98.825
+22400/69092	Loss: 99.196
+25600/69092	Loss: 97.883
+28800/69092	Loss: 100.067
+32000/69092	Loss: 98.843
+35200/69092	Loss: 100.284
+38400/69092	Loss: 99.270
+41600/69092	Loss: 98.541
+44800/69092	Loss: 98.088
+48000/69092	Loss: 98.626
+51200/69092	Loss: 98.179
+54400/69092	Loss: 99.273
+57600/69092	Loss: 99.039
+60800/69092	Loss: 99.310
+64000/69092	Loss: 98.925
+67200/69092	Loss: 98.689
+Training time 0:10:25.323452
+Epoch: 93 Average loss: 98.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 244)
+0/69092	Loss: 86.214
+3200/69092	Loss: 98.565
+6400/69092	Loss: 99.478
+9600/69092	Loss: 98.690
+12800/69092	Loss: 98.257
+16000/69092	Loss: 98.812
+19200/69092	Loss: 97.820
+22400/69092	Loss: 98.563
+25600/69092	Loss: 99.713
+28800/69092	Loss: 98.386
+32000/69092	Loss: 100.239
+35200/69092	Loss: 98.999
+38400/69092	Loss: 98.993
+41600/69092	Loss: 98.289
+44800/69092	Loss: 99.814
+48000/69092	Loss: 99.835
+51200/69092	Loss: 98.398
+54400/69092	Loss: 100.137
+57600/69092	Loss: 98.619
+60800/69092	Loss: 100.086
+64000/69092	Loss: 98.693
+67200/69092	Loss: 98.451
+Training time 0:10:30.324973
+Epoch: 94 Average loss: 99.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 245)
+0/69092	Loss: 99.532
+3200/69092	Loss: 99.680
+6400/69092	Loss: 98.193
+9600/69092	Loss: 99.868
+12800/69092	Loss: 99.532
+16000/69092	Loss: 98.199
+19200/69092	Loss: 98.594
+22400/69092	Loss: 97.658
+25600/69092	Loss: 100.549
+28800/69092	Loss: 98.632
+32000/69092	Loss: 100.618
+35200/69092	Loss: 98.734
+38400/69092	Loss: 98.452
+41600/69092	Loss: 99.495
+44800/69092	Loss: 98.108
+48000/69092	Loss: 98.371
+51200/69092	Loss: 99.155
+54400/69092	Loss: 99.637
+57600/69092	Loss: 97.717
+60800/69092	Loss: 98.352
+64000/69092	Loss: 99.477
+67200/69092	Loss: 99.635
+Training time 0:10:29.572871
+Epoch: 95 Average loss: 98.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 246)
+0/69092	Loss: 95.001
+3200/69092	Loss: 99.029
+6400/69092	Loss: 98.986
+9600/69092	Loss: 99.667
+12800/69092	Loss: 98.571
+16000/69092	Loss: 98.138
+19200/69092	Loss: 99.715
+22400/69092	Loss: 98.078
+25600/69092	Loss: 99.314
+28800/69092	Loss: 99.503
+32000/69092	Loss: 97.795
+35200/69092	Loss: 99.282
+38400/69092	Loss: 98.624
+41600/69092	Loss: 99.043
+44800/69092	Loss: 98.546
+48000/69092	Loss: 98.368
+51200/69092	Loss: 97.927
+54400/69092	Loss: 98.224
+57600/69092	Loss: 99.160
+60800/69092	Loss: 100.036
+64000/69092	Loss: 99.130
+67200/69092	Loss: 97.335
+Training time 0:10:08.509580
+Epoch: 96 Average loss: 98.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 247)
+0/69092	Loss: 93.311
+3200/69092	Loss: 99.820
+6400/69092	Loss: 99.523
+9600/69092	Loss: 97.247
+12800/69092	Loss: 99.071
+16000/69092	Loss: 98.345
+19200/69092	Loss: 97.879
+22400/69092	Loss: 98.900
+25600/69092	Loss: 99.475
+28800/69092	Loss: 98.694
+32000/69092	Loss: 99.222
+35200/69092	Loss: 100.106
+38400/69092	Loss: 96.652
+41600/69092	Loss: 100.552
+44800/69092	Loss: 97.940
+48000/69092	Loss: 98.427
+51200/69092	Loss: 99.076
+54400/69092	Loss: 99.999
+57600/69092	Loss: 100.056
+60800/69092	Loss: 98.433
+64000/69092	Loss: 100.495
+67200/69092	Loss: 98.764
+Training time 0:10:22.063797
+Epoch: 97 Average loss: 98.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 248)
+0/69092	Loss: 98.693
+3200/69092	Loss: 100.855
+6400/69092	Loss: 98.262
+9600/69092	Loss: 99.731
+12800/69092	Loss: 98.220
+16000/69092	Loss: 97.726
+19200/69092	Loss: 99.780
+22400/69092	Loss: 99.159
+25600/69092	Loss: 98.670
+28800/69092	Loss: 99.235
+32000/69092	Loss: 98.775
+35200/69092	Loss: 96.842
+38400/69092	Loss: 97.729
+41600/69092	Loss: 100.913
+44800/69092	Loss: 99.267
+48000/69092	Loss: 98.531
+51200/69092	Loss: 98.822
+54400/69092	Loss: 98.035
+57600/69092	Loss: 99.868
+60800/69092	Loss: 100.472
+64000/69092	Loss: 99.601
+67200/69092	Loss: 97.966
+Training time 0:10:13.090204
+Epoch: 98 Average loss: 99.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 249)
+0/69092	Loss: 88.454
+3200/69092	Loss: 97.730
+6400/69092	Loss: 99.225
+9600/69092	Loss: 99.317
+12800/69092	Loss: 98.428
+16000/69092	Loss: 98.746
+19200/69092	Loss: 98.330
+22400/69092	Loss: 98.306
+25600/69092	Loss: 98.327
+28800/69092	Loss: 98.844
+32000/69092	Loss: 100.410
+35200/69092	Loss: 99.688
+38400/69092	Loss: 99.052
+41600/69092	Loss: 98.822
+44800/69092	Loss: 99.719
+48000/69092	Loss: 99.182
+51200/69092	Loss: 99.239
+54400/69092	Loss: 98.993
+57600/69092	Loss: 98.474
+60800/69092	Loss: 98.763
+64000/69092	Loss: 98.223
+67200/69092	Loss: 98.313
+Training time 0:10:27.496126
+Epoch: 99 Average loss: 98.87
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 250)
+0/69092	Loss: 102.590
+3200/69092	Loss: 98.479
+6400/69092	Loss: 99.874
+9600/69092	Loss: 97.540
+12800/69092	Loss: 98.293
+16000/69092	Loss: 98.983
+19200/69092	Loss: 98.369
+22400/69092	Loss: 99.900
+25600/69092	Loss: 97.751
+28800/69092	Loss: 99.351
+32000/69092	Loss: 97.763
+35200/69092	Loss: 98.322
+38400/69092	Loss: 98.047
+41600/69092	Loss: 99.253
+44800/69092	Loss: 99.355
+48000/69092	Loss: 99.390
+51200/69092	Loss: 99.517
+54400/69092	Loss: 100.238
+57600/69092	Loss: 98.731
+60800/69092	Loss: 100.086
+64000/69092	Loss: 99.195
+67200/69092	Loss: 100.533
+Training time 0:10:18.275978
+Epoch: 100 Average loss: 98.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 251)
+0/69092	Loss: 93.609
+3200/69092	Loss: 100.738
+6400/69092	Loss: 96.840
+9600/69092	Loss: 98.427
+12800/69092	Loss: 98.057
+16000/69092	Loss: 99.746
+19200/69092	Loss: 99.726
+22400/69092	Loss: 98.523
+25600/69092	Loss: 98.646
+28800/69092	Loss: 99.007
+32000/69092	Loss: 98.105
+35200/69092	Loss: 100.718
+38400/69092	Loss: 98.691
+41600/69092	Loss: 98.906
+44800/69092	Loss: 98.304
+48000/69092	Loss: 100.525
+51200/69092	Loss: 98.442
+54400/69092	Loss: 98.311
+57600/69092	Loss: 99.547
+60800/69092	Loss: 99.844
+64000/69092	Loss: 99.649
+67200/69092	Loss: 98.293
+Training time 0:10:31.567484
+Epoch: 101 Average loss: 98.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 252)
+0/69092	Loss: 94.362
+3200/69092	Loss: 98.184
+6400/69092	Loss: 100.606
+9600/69092	Loss: 97.213
+12800/69092	Loss: 97.817
+16000/69092	Loss: 98.551
+19200/69092	Loss: 100.620
+22400/69092	Loss: 100.030
+25600/69092	Loss: 98.031
+28800/69092	Loss: 99.267
+32000/69092	Loss: 99.198
+35200/69092	Loss: 98.783
+38400/69092	Loss: 99.336
+41600/69092	Loss: 100.487
+44800/69092	Loss: 98.712
+48000/69092	Loss: 100.012
+51200/69092	Loss: 98.383
+54400/69092	Loss: 98.342
+57600/69092	Loss: 99.834
+60800/69092	Loss: 98.140
+64000/69092	Loss: 97.984
+67200/69092	Loss: 98.191
+Training time 0:10:37.234835
+Epoch: 102 Average loss: 98.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 253)
+0/69092	Loss: 97.374
+3200/69092	Loss: 97.769
+6400/69092	Loss: 98.464
+9600/69092	Loss: 98.917
+12800/69092	Loss: 99.658
+16000/69092	Loss: 96.673
+19200/69092	Loss: 98.784
+22400/69092	Loss: 98.609
+25600/69092	Loss: 99.417
+28800/69092	Loss: 98.932
+32000/69092	Loss: 98.814
+35200/69092	Loss: 98.513
+38400/69092	Loss: 98.504
+41600/69092	Loss: 99.014
+44800/69092	Loss: 100.019
+48000/69092	Loss: 98.961
+51200/69092	Loss: 99.899
+54400/69092	Loss: 98.945
+57600/69092	Loss: 98.474
+60800/69092	Loss: 99.327
+64000/69092	Loss: 99.894
+67200/69092	Loss: 98.659
+Training time 0:10:08.035781
+Epoch: 103 Average loss: 98.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 254)
+0/69092	Loss: 99.626
+3200/69092	Loss: 97.197
+6400/69092	Loss: 98.259
+9600/69092	Loss: 99.032
+12800/69092	Loss: 98.055
+16000/69092	Loss: 98.747
+19200/69092	Loss: 99.960
+22400/69092	Loss: 99.989
+25600/69092	Loss: 99.400
+28800/69092	Loss: 100.510
+32000/69092	Loss: 99.858
+35200/69092	Loss: 99.394
+38400/69092	Loss: 98.393
+41600/69092	Loss: 98.095
+44800/69092	Loss: 99.095
+48000/69092	Loss: 97.623
+51200/69092	Loss: 100.186
+54400/69092	Loss: 98.630
+57600/69092	Loss: 99.150
+60800/69092	Loss: 99.358
+64000/69092	Loss: 97.832
+67200/69092	Loss: 98.932
+Training time 0:10:28.218869
+Epoch: 104 Average loss: 98.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 255)
+0/69092	Loss: 94.488
+3200/69092	Loss: 99.937
+6400/69092	Loss: 99.457
+9600/69092	Loss: 99.375
+12800/69092	Loss: 98.323
+16000/69092	Loss: 97.700
+19200/69092	Loss: 99.237
+22400/69092	Loss: 97.971
+25600/69092	Loss: 100.020
+28800/69092	Loss: 98.505
+32000/69092	Loss: 96.550
+35200/69092	Loss: 98.845
+38400/69092	Loss: 99.345
+41600/69092	Loss: 99.848
+44800/69092	Loss: 100.902
+48000/69092	Loss: 97.708
+51200/69092	Loss: 96.901
+54400/69092	Loss: 100.179
+57600/69092	Loss: 97.890
+60800/69092	Loss: 97.009
+64000/69092	Loss: 99.320
+67200/69092	Loss: 98.929
+Training time 0:10:31.234475
+Epoch: 105 Average loss: 98.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 256)
+0/69092	Loss: 101.578
+3200/69092	Loss: 98.218
+6400/69092	Loss: 97.824
+9600/69092	Loss: 99.117
+12800/69092	Loss: 96.841
+16000/69092	Loss: 98.896
+19200/69092	Loss: 99.521
+22400/69092	Loss: 98.704
+25600/69092	Loss: 99.478
+28800/69092	Loss: 98.487
+32000/69092	Loss: 99.705
+35200/69092	Loss: 98.446
+38400/69092	Loss: 99.202
+41600/69092	Loss: 99.235
+44800/69092	Loss: 100.131
+48000/69092	Loss: 98.772
+51200/69092	Loss: 98.807
+54400/69092	Loss: 100.603
+57600/69092	Loss: 98.563
+60800/69092	Loss: 98.919
+64000/69092	Loss: 97.886
+67200/69092	Loss: 98.843
+Training time 0:10:25.889772
+Epoch: 106 Average loss: 98.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 257)
+0/69092	Loss: 99.491
+3200/69092	Loss: 99.610
+6400/69092	Loss: 98.347
+9600/69092	Loss: 98.265
+12800/69092	Loss: 99.069
+16000/69092	Loss: 98.850
+19200/69092	Loss: 98.376
+22400/69092	Loss: 98.158
+25600/69092	Loss: 98.114
+28800/69092	Loss: 99.623
+32000/69092	Loss: 98.381
+35200/69092	Loss: 98.226
+38400/69092	Loss: 98.138
+41600/69092	Loss: 99.238
+44800/69092	Loss: 98.165
+48000/69092	Loss: 99.429
+51200/69092	Loss: 98.098
+54400/69092	Loss: 97.925
+57600/69092	Loss: 98.783
+60800/69092	Loss: 99.652
+64000/69092	Loss: 100.639
+67200/69092	Loss: 99.100
+Training time 0:10:35.845565
+Epoch: 107 Average loss: 98.72
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 258)
+0/69092	Loss: 94.732
+3200/69092	Loss: 96.377
+6400/69092	Loss: 99.500
+9600/69092	Loss: 98.618
+12800/69092	Loss: 97.919
+16000/69092	Loss: 98.264
+19200/69092	Loss: 99.733
+22400/69092	Loss: 97.459
+25600/69092	Loss: 99.160
+28800/69092	Loss: 98.385
+32000/69092	Loss: 98.206
+35200/69092	Loss: 97.784
+38400/69092	Loss: 99.597
+41600/69092	Loss: 100.180
+44800/69092	Loss: 99.451
+48000/69092	Loss: 98.920
+51200/69092	Loss: 98.045
+54400/69092	Loss: 99.843
+57600/69092	Loss: 97.916
+60800/69092	Loss: 99.611
+64000/69092	Loss: 99.624
+67200/69092	Loss: 99.657
+Training time 0:10:46.319442
+Epoch: 108 Average loss: 98.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 259)
+0/69092	Loss: 110.590
+3200/69092	Loss: 99.784
+6400/69092	Loss: 99.346
+9600/69092	Loss: 98.343
+12800/69092	Loss: 98.832
+16000/69092	Loss: 96.803
+19200/69092	Loss: 98.279
+22400/69092	Loss: 98.313
+25600/69092	Loss: 99.064
+28800/69092	Loss: 98.987
+32000/69092	Loss: 100.291
+35200/69092	Loss: 98.616
+38400/69092	Loss: 99.924
+41600/69092	Loss: 99.383
+44800/69092	Loss: 99.305
+48000/69092	Loss: 98.644
+51200/69092	Loss: 98.700
+54400/69092	Loss: 98.429
+57600/69092	Loss: 98.916
+60800/69092	Loss: 99.116
+64000/69092	Loss: 98.253
+67200/69092	Loss: 97.839
+Training time 0:10:18.440703
+Epoch: 109 Average loss: 98.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 260)
+0/69092	Loss: 115.601
+3200/69092	Loss: 98.674
+6400/69092	Loss: 97.657
+9600/69092	Loss: 99.094
+12800/69092	Loss: 99.079
+16000/69092	Loss: 97.859
+19200/69092	Loss: 98.138
+22400/69092	Loss: 99.600
+25600/69092	Loss: 100.680
+28800/69092	Loss: 99.131
+32000/69092	Loss: 98.798
+35200/69092	Loss: 99.170
+38400/69092	Loss: 99.927
+41600/69092	Loss: 98.535
+44800/69092	Loss: 99.218
+48000/69092	Loss: 98.048
+51200/69092	Loss: 98.948
+54400/69092	Loss: 98.943
+57600/69092	Loss: 99.115
+60800/69092	Loss: 98.129
+64000/69092	Loss: 98.448
+67200/69092	Loss: 98.506
+Training time 0:10:26.736152
+Epoch: 110 Average loss: 98.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 261)
+0/69092	Loss: 94.403
+3200/69092	Loss: 99.228
+6400/69092	Loss: 98.565
+9600/69092	Loss: 98.569
+12800/69092	Loss: 98.821
+16000/69092	Loss: 98.912
+19200/69092	Loss: 98.084
+22400/69092	Loss: 97.886
+25600/69092	Loss: 99.759
+28800/69092	Loss: 98.914
+32000/69092	Loss: 99.195
+35200/69092	Loss: 97.876
+38400/69092	Loss: 98.064
+41600/69092	Loss: 98.249
+44800/69092	Loss: 96.990
+48000/69092	Loss: 98.236
+51200/69092	Loss: 98.676
+54400/69092	Loss: 98.936
+57600/69092	Loss: 101.399
+60800/69092	Loss: 100.339
+64000/69092	Loss: 99.687
+67200/69092	Loss: 98.807
+Training time 0:10:29.046351
+Epoch: 111 Average loss: 98.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 262)
+0/69092	Loss: 103.774
+3200/69092	Loss: 100.638
+6400/69092	Loss: 98.972
+9600/69092	Loss: 98.367
+12800/69092	Loss: 99.890
+16000/69092	Loss: 99.726
+19200/69092	Loss: 98.440
+22400/69092	Loss: 97.697
+25600/69092	Loss: 99.088
+28800/69092	Loss: 97.347
+32000/69092	Loss: 97.509
+35200/69092	Loss: 97.567
+38400/69092	Loss: 99.541
+41600/69092	Loss: 97.235
+44800/69092	Loss: 99.266
+48000/69092	Loss: 98.442
+51200/69092	Loss: 100.383
+54400/69092	Loss: 98.253
+57600/69092	Loss: 98.218
+60800/69092	Loss: 98.251
+64000/69092	Loss: 99.729
+67200/69092	Loss: 98.685
+Training time 0:10:35.961673
+Epoch: 112 Average loss: 98.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 263)
+0/69092	Loss: 109.545
+3200/69092	Loss: 97.657
+6400/69092	Loss: 98.942
+9600/69092	Loss: 97.782
+12800/69092	Loss: 98.704
+16000/69092	Loss: 98.309
+19200/69092	Loss: 100.616
+22400/69092	Loss: 98.134
+25600/69092	Loss: 97.824
+28800/69092	Loss: 99.474
+32000/69092	Loss: 98.873
+35200/69092	Loss: 99.349
+38400/69092	Loss: 98.306
+41600/69092	Loss: 99.802
+44800/69092	Loss: 97.853
+48000/69092	Loss: 100.459
+51200/69092	Loss: 98.803
+54400/69092	Loss: 98.975
+57600/69092	Loss: 98.562
+60800/69092	Loss: 98.699
+64000/69092	Loss: 98.975
+67200/69092	Loss: 97.911
+Training time 0:10:31.132783
+Epoch: 113 Average loss: 98.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 264)
+0/69092	Loss: 103.454
+3200/69092	Loss: 98.401
+6400/69092	Loss: 98.843
+9600/69092	Loss: 98.734
+12800/69092	Loss: 99.785
+16000/69092	Loss: 100.057
+19200/69092	Loss: 99.403
+22400/69092	Loss: 98.390
+25600/69092	Loss: 98.437
+28800/69092	Loss: 98.720
+32000/69092	Loss: 99.720
+35200/69092	Loss: 98.922
+38400/69092	Loss: 98.614
+41600/69092	Loss: 98.077
+44800/69092	Loss: 97.787
+48000/69092	Loss: 99.757
+51200/69092	Loss: 98.740
+54400/69092	Loss: 98.306
+57600/69092	Loss: 98.743
+60800/69092	Loss: 99.224
+64000/69092	Loss: 98.016
+67200/69092	Loss: 99.824
+Training time 0:10:24.936053
+Epoch: 114 Average loss: 98.87
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 265)
+0/69092	Loss: 98.865
+3200/69092	Loss: 98.951
+6400/69092	Loss: 98.716
+9600/69092	Loss: 98.896
+12800/69092	Loss: 98.418
+16000/69092	Loss: 99.490
+19200/69092	Loss: 98.408
+22400/69092	Loss: 98.574
+25600/69092	Loss: 98.328
+28800/69092	Loss: 98.546
+32000/69092	Loss: 98.182
+35200/69092	Loss: 98.733
+38400/69092	Loss: 98.931
+41600/69092	Loss: 98.965
+44800/69092	Loss: 98.981
+48000/69092	Loss: 99.097
+51200/69092	Loss: 99.452
+54400/69092	Loss: 98.928
+57600/69092	Loss: 98.436
+60800/69092	Loss: 97.488
+64000/69092	Loss: 100.692
+67200/69092	Loss: 99.162
+Training time 0:10:34.224755
+Epoch: 115 Average loss: 98.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 266)
+0/69092	Loss: 85.697
+3200/69092	Loss: 98.166
+6400/69092	Loss: 99.140
+9600/69092	Loss: 98.631
+12800/69092	Loss: 98.678
+16000/69092	Loss: 98.181
+19200/69092	Loss: 99.097
+22400/69092	Loss: 98.661
+25600/69092	Loss: 98.836
+28800/69092	Loss: 97.148
+32000/69092	Loss: 98.742
+35200/69092	Loss: 98.295
+38400/69092	Loss: 98.489
+41600/69092	Loss: 99.555
+44800/69092	Loss: 99.137
+48000/69092	Loss: 97.042
+51200/69092	Loss: 98.053
+54400/69092	Loss: 100.318
+57600/69092	Loss: 98.544
+60800/69092	Loss: 99.422
+64000/69092	Loss: 97.940
+67200/69092	Loss: 99.854
+Training time 0:10:15.185600
+Epoch: 116 Average loss: 98.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 267)
+0/69092	Loss: 88.505
+3200/69092	Loss: 98.396
+6400/69092	Loss: 98.087
+9600/69092	Loss: 100.591
+12800/69092	Loss: 98.791
+16000/69092	Loss: 99.759
+19200/69092	Loss: 98.374
+22400/69092	Loss: 98.124
+25600/69092	Loss: 98.916
+28800/69092	Loss: 99.692
+32000/69092	Loss: 97.827
+35200/69092	Loss: 99.124
+38400/69092	Loss: 97.897
+41600/69092	Loss: 96.897
+44800/69092	Loss: 98.948
+48000/69092	Loss: 98.237
+51200/69092	Loss: 97.524
+54400/69092	Loss: 98.083
+57600/69092	Loss: 98.497
+60800/69092	Loss: 99.602
+64000/69092	Loss: 99.660
+67200/69092	Loss: 98.344
+Training time 0:10:45.372155
+Epoch: 117 Average loss: 98.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 268)
+0/69092	Loss: 99.270
+3200/69092	Loss: 97.211
+6400/69092	Loss: 99.847
+9600/69092	Loss: 98.950
+12800/69092	Loss: 98.025
+16000/69092	Loss: 98.622
+19200/69092	Loss: 98.070
+22400/69092	Loss: 99.196
+25600/69092	Loss: 98.983
+28800/69092	Loss: 100.103
+32000/69092	Loss: 98.518
+35200/69092	Loss: 98.949
+38400/69092	Loss: 97.678
+41600/69092	Loss: 97.062
+44800/69092	Loss: 98.002
+48000/69092	Loss: 98.484
+51200/69092	Loss: 99.186
+54400/69092	Loss: 99.095
+57600/69092	Loss: 98.615
+60800/69092	Loss: 99.406
+64000/69092	Loss: 99.090
+67200/69092	Loss: 100.346
+Training time 0:10:25.266835
+Epoch: 118 Average loss: 98.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 269)
+0/69092	Loss: 99.660
+3200/69092	Loss: 98.231
+6400/69092	Loss: 98.274
+9600/69092	Loss: 100.041
+12800/69092	Loss: 99.512
+16000/69092	Loss: 98.146
+19200/69092	Loss: 98.281
+22400/69092	Loss: 98.315
+25600/69092	Loss: 97.663
+28800/69092	Loss: 98.510
+32000/69092	Loss: 98.154
+35200/69092	Loss: 99.951
+38400/69092	Loss: 98.099
+41600/69092	Loss: 99.442
+44800/69092	Loss: 98.226
+48000/69092	Loss: 100.145
+51200/69092	Loss: 98.799
+54400/69092	Loss: 96.772
+57600/69092	Loss: 100.247
+60800/69092	Loss: 97.223
+64000/69092	Loss: 99.750
+67200/69092	Loss: 97.982
+Training time 0:10:27.498358
+Epoch: 119 Average loss: 98.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 270)
+0/69092	Loss: 94.983
+3200/69092	Loss: 98.443
+6400/69092	Loss: 99.057
+9600/69092	Loss: 98.459
+12800/69092	Loss: 99.162
+16000/69092	Loss: 98.247
+19200/69092	Loss: 98.858
+22400/69092	Loss: 98.894
+25600/69092	Loss: 97.264
+28800/69092	Loss: 98.660
+32000/69092	Loss: 98.670
+35200/69092	Loss: 97.978
+38400/69092	Loss: 98.569
+41600/69092	Loss: 98.715
+44800/69092	Loss: 99.049
+48000/69092	Loss: 98.303
+51200/69092	Loss: 97.731
+54400/69092	Loss: 100.895
+57600/69092	Loss: 98.347
+60800/69092	Loss: 99.190
+64000/69092	Loss: 97.600
+67200/69092	Loss: 98.586
+Training time 0:10:27.809132
+Epoch: 120 Average loss: 98.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 271)
+0/69092	Loss: 101.818
+3200/69092	Loss: 98.286
+6400/69092	Loss: 98.266
+9600/69092	Loss: 98.556
+12800/69092	Loss: 98.669
+16000/69092	Loss: 98.633
+19200/69092	Loss: 99.275
+22400/69092	Loss: 97.456
+25600/69092	Loss: 98.470
+28800/69092	Loss: 99.459
+32000/69092	Loss: 98.363
+35200/69092	Loss: 98.356
+38400/69092	Loss: 98.960
+41600/69092	Loss: 97.701
+44800/69092	Loss: 99.724
+48000/69092	Loss: 98.626
+51200/69092	Loss: 98.387
+54400/69092	Loss: 98.564
+57600/69092	Loss: 97.938
+60800/69092	Loss: 99.437
+64000/69092	Loss: 99.516
+67200/69092	Loss: 98.770
+Training time 0:10:18.800496
+Epoch: 121 Average loss: 98.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 272)
+0/69092	Loss: 96.437
+3200/69092	Loss: 99.130
+6400/69092	Loss: 98.909
+9600/69092	Loss: 98.070
+12800/69092	Loss: 99.098
+16000/69092	Loss: 98.010
+19200/69092	Loss: 99.002
+22400/69092	Loss: 96.719
+25600/69092	Loss: 98.446
+28800/69092	Loss: 98.676
+32000/69092	Loss: 99.038
+35200/69092	Loss: 98.908
+38400/69092	Loss: 98.903
+41600/69092	Loss: 98.020
+44800/69092	Loss: 98.295
+48000/69092	Loss: 98.390
+51200/69092	Loss: 99.037
+54400/69092	Loss: 99.202
+57600/69092	Loss: 99.083
+60800/69092	Loss: 99.129
+64000/69092	Loss: 99.545
+67200/69092	Loss: 98.098
+Training time 0:10:28.101881
+Epoch: 122 Average loss: 98.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 273)
+0/69092	Loss: 101.104
+3200/69092	Loss: 97.900
+6400/69092	Loss: 97.458
+9600/69092	Loss: 99.173
+12800/69092	Loss: 98.348
+16000/69092	Loss: 99.288
+19200/69092	Loss: 99.352
+22400/69092	Loss: 99.387
+25600/69092	Loss: 97.231
+28800/69092	Loss: 100.906
+32000/69092	Loss: 99.274
+35200/69092	Loss: 100.112
+38400/69092	Loss: 98.376
+41600/69092	Loss: 98.328
+44800/69092	Loss: 97.700
+48000/69092	Loss: 99.080
+51200/69092	Loss: 98.462
+54400/69092	Loss: 98.649
+57600/69092	Loss: 97.769
+60800/69092	Loss: 98.053
+64000/69092	Loss: 98.871
+67200/69092	Loss: 98.753
+Training time 0:10:12.667619
+Epoch: 123 Average loss: 98.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 274)
+0/69092	Loss: 102.894
+3200/69092	Loss: 99.044
+6400/69092	Loss: 98.853
+9600/69092	Loss: 99.544
+12800/69092	Loss: 99.897
+16000/69092	Loss: 98.303
+19200/69092	Loss: 97.396
+22400/69092	Loss: 99.102
+25600/69092	Loss: 97.025
+28800/69092	Loss: 98.859
+32000/69092	Loss: 98.263
+35200/69092	Loss: 100.300
+38400/69092	Loss: 97.882
+41600/69092	Loss: 99.375
+44800/69092	Loss: 98.942
+48000/69092	Loss: 98.175
+51200/69092	Loss: 97.519
+54400/69092	Loss: 97.573
+57600/69092	Loss: 99.656
+60800/69092	Loss: 99.213
+64000/69092	Loss: 99.329
+67200/69092	Loss: 96.632
+Training time 0:10:38.487318
+Epoch: 124 Average loss: 98.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 275)
+0/69092	Loss: 97.808
+3200/69092	Loss: 95.900
+6400/69092	Loss: 98.032
+9600/69092	Loss: 96.562
+12800/69092	Loss: 98.402
+16000/69092	Loss: 100.517
+19200/69092	Loss: 98.362
+22400/69092	Loss: 99.075
+25600/69092	Loss: 97.855
+28800/69092	Loss: 98.702
+32000/69092	Loss: 98.910
+35200/69092	Loss: 99.569
+38400/69092	Loss: 99.370
+41600/69092	Loss: 97.321
+44800/69092	Loss: 99.075
+48000/69092	Loss: 98.568
+51200/69092	Loss: 98.374
+54400/69092	Loss: 99.082
+57600/69092	Loss: 98.001
+60800/69092	Loss: 99.141
+64000/69092	Loss: 98.745
+67200/69092	Loss: 97.701
+Training time 0:10:41.476743
+Epoch: 125 Average loss: 98.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 276)
+0/69092	Loss: 102.256
+3200/69092	Loss: 99.115
+6400/69092	Loss: 97.904
+9600/69092	Loss: 99.509
+12800/69092	Loss: 98.623
+16000/69092	Loss: 98.369
+19200/69092	Loss: 99.457
+22400/69092	Loss: 99.467
+25600/69092	Loss: 98.196
+28800/69092	Loss: 98.077
+32000/69092	Loss: 98.595
+35200/69092	Loss: 99.892
+38400/69092	Loss: 97.922
+41600/69092	Loss: 99.063
+44800/69092	Loss: 98.022
+48000/69092	Loss: 99.446
+51200/69092	Loss: 99.145
+54400/69092	Loss: 99.323
+57600/69092	Loss: 99.772
+60800/69092	Loss: 96.952
+64000/69092	Loss: 98.408
+67200/69092	Loss: 98.170
+Training time 0:10:31.423372
+Epoch: 126 Average loss: 98.71
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 277)
+0/69092	Loss: 97.958
+3200/69092	Loss: 98.819
+6400/69092	Loss: 97.799
+9600/69092	Loss: 98.747
+12800/69092	Loss: 98.379
+16000/69092	Loss: 98.692
+19200/69092	Loss: 97.661
+22400/69092	Loss: 98.691
+25600/69092	Loss: 100.230
+28800/69092	Loss: 97.506
+32000/69092	Loss: 97.221
+35200/69092	Loss: 98.100
+38400/69092	Loss: 99.038
+41600/69092	Loss: 98.308
+44800/69092	Loss: 99.725
+48000/69092	Loss: 99.213
+51200/69092	Loss: 98.948
+54400/69092	Loss: 99.543
+57600/69092	Loss: 98.551
+60800/69092	Loss: 99.690
+64000/69092	Loss: 98.492
+67200/69092	Loss: 98.971
+Training time 0:10:28.978466
+Epoch: 127 Average loss: 98.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 278)
+0/69092	Loss: 106.670
+3200/69092	Loss: 97.802
+6400/69092	Loss: 97.966
+9600/69092	Loss: 97.787
+12800/69092	Loss: 99.087
+16000/69092	Loss: 98.838
+19200/69092	Loss: 99.758
+22400/69092	Loss: 97.964
+25600/69092	Loss: 98.655
+28800/69092	Loss: 99.478
+32000/69092	Loss: 99.127
+35200/69092	Loss: 98.086
+38400/69092	Loss: 97.900
+41600/69092	Loss: 98.880
+44800/69092	Loss: 97.843
+48000/69092	Loss: 99.151
+51200/69092	Loss: 98.958
+54400/69092	Loss: 99.395
+57600/69092	Loss: 98.591
+60800/69092	Loss: 98.381
+64000/69092	Loss: 98.563
+67200/69092	Loss: 98.453
+Training time 0:10:29.193911
+Epoch: 128 Average loss: 98.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 279)
+0/69092	Loss: 101.359
+3200/69092	Loss: 97.391
+6400/69092	Loss: 97.292
+9600/69092	Loss: 97.842
+12800/69092	Loss: 97.984
+16000/69092	Loss: 98.537
+19200/69092	Loss: 98.032
+22400/69092	Loss: 98.464
+25600/69092	Loss: 99.194
+28800/69092	Loss: 98.746
+32000/69092	Loss: 98.544
+35200/69092	Loss: 97.388
+38400/69092	Loss: 99.068
+41600/69092	Loss: 98.491
+44800/69092	Loss: 98.757
+48000/69092	Loss: 98.400
+51200/69092	Loss: 99.418
+54400/69092	Loss: 98.476
+57600/69092	Loss: 98.492
+60800/69092	Loss: 99.015
+64000/69092	Loss: 99.371
+67200/69092	Loss: 98.891
+Training time 0:10:32.851927
+Epoch: 129 Average loss: 98.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 280)
+0/69092	Loss: 98.029
+3200/69092	Loss: 99.026
+6400/69092	Loss: 97.905
+9600/69092	Loss: 98.112
+12800/69092	Loss: 97.918
+16000/69092	Loss: 98.824
+19200/69092	Loss: 98.755
+22400/69092	Loss: 98.154
+25600/69092	Loss: 101.081
+28800/69092	Loss: 98.334
+32000/69092	Loss: 97.766
+35200/69092	Loss: 96.227
+38400/69092	Loss: 98.203
+41600/69092	Loss: 99.392
+44800/69092	Loss: 99.051
+48000/69092	Loss: 98.998
+51200/69092	Loss: 98.726
+54400/69092	Loss: 98.878
+57600/69092	Loss: 98.373
+60800/69092	Loss: 97.725
+64000/69092	Loss: 99.019
+67200/69092	Loss: 99.384
+Training time 0:10:41.214559
+Epoch: 130 Average loss: 98.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 281)
+0/69092	Loss: 100.678
+3200/69092	Loss: 98.059
+6400/69092	Loss: 99.675
+9600/69092	Loss: 98.551
+12800/69092	Loss: 97.614
+16000/69092	Loss: 97.759
+19200/69092	Loss: 98.724
+22400/69092	Loss: 98.811
+25600/69092	Loss: 96.727
+28800/69092	Loss: 99.437
+32000/69092	Loss: 98.063
+35200/69092	Loss: 99.031
+38400/69092	Loss: 99.057
+41600/69092	Loss: 98.237
+44800/69092	Loss: 99.694
+48000/69092	Loss: 98.055
+51200/69092	Loss: 97.867
+54400/69092	Loss: 99.231
+57600/69092	Loss: 98.162
+60800/69092	Loss: 98.853
+64000/69092	Loss: 99.195
+67200/69092	Loss: 97.849
+Training time 0:10:26.754492
+Epoch: 131 Average loss: 98.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 282)
+0/69092	Loss: 100.615
+3200/69092	Loss: 99.320
+6400/69092	Loss: 97.542
+9600/69092	Loss: 98.810
+12800/69092	Loss: 98.380
+16000/69092	Loss: 99.230
+19200/69092	Loss: 97.971
+22400/69092	Loss: 98.558
+25600/69092	Loss: 97.468
+28800/69092	Loss: 99.457
+32000/69092	Loss: 97.994
+35200/69092	Loss: 98.892
+38400/69092	Loss: 97.328
+41600/69092	Loss: 99.474
+44800/69092	Loss: 98.549
+48000/69092	Loss: 98.674
+51200/69092	Loss: 97.408
+54400/69092	Loss: 98.666
+57600/69092	Loss: 98.514
+60800/69092	Loss: 98.359
+64000/69092	Loss: 99.643
+67200/69092	Loss: 99.517
+Training time 0:10:27.167253
+Epoch: 132 Average loss: 98.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 283)
+0/69092	Loss: 89.895
+3200/69092	Loss: 98.919
+6400/69092	Loss: 97.937
+9600/69092	Loss: 97.707
+12800/69092	Loss: 99.383
+16000/69092	Loss: 99.259
+19200/69092	Loss: 99.148
+22400/69092	Loss: 98.974
+25600/69092	Loss: 99.648
+28800/69092	Loss: 98.567
+32000/69092	Loss: 98.732
+35200/69092	Loss: 96.210
+38400/69092	Loss: 100.812
+41600/69092	Loss: 99.828
+44800/69092	Loss: 97.758
+48000/69092	Loss: 98.541
+51200/69092	Loss: 98.438
+54400/69092	Loss: 96.690
+57600/69092	Loss: 99.386
+60800/69092	Loss: 98.561
+64000/69092	Loss: 97.414
+67200/69092	Loss: 97.860
+Training time 0:10:24.859007
+Epoch: 133 Average loss: 98.57
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 284)
+0/69092	Loss: 100.080
+3200/69092	Loss: 97.017
+6400/69092	Loss: 99.757
+9600/69092	Loss: 99.276
+12800/69092	Loss: 98.276
+16000/69092	Loss: 99.191
+19200/69092	Loss: 99.390
+22400/69092	Loss: 97.710
+25600/69092	Loss: 98.060
+28800/69092	Loss: 97.419
+32000/69092	Loss: 96.787
+35200/69092	Loss: 97.848
+38400/69092	Loss: 99.227
+41600/69092	Loss: 99.486
+44800/69092	Loss: 97.815
+48000/69092	Loss: 98.645
+51200/69092	Loss: 98.701
+54400/69092	Loss: 99.337
+57600/69092	Loss: 99.774
+60800/69092	Loss: 97.595
+64000/69092	Loss: 98.149
+67200/69092	Loss: 98.285
+Training time 0:10:16.761856
+Epoch: 134 Average loss: 98.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 285)
+0/69092	Loss: 105.237
+3200/69092	Loss: 98.529
+6400/69092	Loss: 98.428
+9600/69092	Loss: 97.423
+12800/69092	Loss: 97.184
+16000/69092	Loss: 99.279
+19200/69092	Loss: 98.273
+22400/69092	Loss: 99.237
+25600/69092	Loss: 97.066
+28800/69092	Loss: 98.408
+32000/69092	Loss: 98.637
+35200/69092	Loss: 98.477
+38400/69092	Loss: 98.687
+41600/69092	Loss: 97.425
+44800/69092	Loss: 98.174
+48000/69092	Loss: 98.884
+51200/69092	Loss: 100.182
+54400/69092	Loss: 98.017
+57600/69092	Loss: 99.281
+60800/69092	Loss: 97.644
+64000/69092	Loss: 99.423
+67200/69092	Loss: 99.320
+Training time 0:10:17.579363
+Epoch: 135 Average loss: 98.50
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 286)
+0/69092	Loss: 97.202
+3200/69092	Loss: 98.813
+6400/69092	Loss: 97.670
+9600/69092	Loss: 99.975
+12800/69092	Loss: 99.169
+16000/69092	Loss: 98.087
+19200/69092	Loss: 97.434
+22400/69092	Loss: 98.845
+25600/69092	Loss: 99.485
+28800/69092	Loss: 98.105
+32000/69092	Loss: 97.124
+35200/69092	Loss: 98.818
+38400/69092	Loss: 98.321
+41600/69092	Loss: 97.651
+44800/69092	Loss: 99.416
+48000/69092	Loss: 97.635
+51200/69092	Loss: 99.676
+54400/69092	Loss: 98.931
+57600/69092	Loss: 97.522
+60800/69092	Loss: 97.577
+64000/69092	Loss: 98.071
+67200/69092	Loss: 97.484
+Training time 0:10:24.271254
+Epoch: 136 Average loss: 98.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 287)
+0/69092	Loss: 103.737
+3200/69092	Loss: 98.677
+6400/69092	Loss: 98.604
+9600/69092	Loss: 97.905
+12800/69092	Loss: 97.756
+16000/69092	Loss: 99.539
+19200/69092	Loss: 98.145
+22400/69092	Loss: 99.369
+25600/69092	Loss: 97.996
+28800/69092	Loss: 98.759
+32000/69092	Loss: 96.655
+35200/69092	Loss: 98.155
+38400/69092	Loss: 98.803
+41600/69092	Loss: 98.039
+44800/69092	Loss: 98.440
+48000/69092	Loss: 99.315
+51200/69092	Loss: 100.570
+54400/69092	Loss: 98.031
+57600/69092	Loss: 96.842
+60800/69092	Loss: 99.460
+64000/69092	Loss: 99.473
+67200/69092	Loss: 97.046
+Training time 0:10:23.146550
+Epoch: 137 Average loss: 98.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 288)
+0/69092	Loss: 92.527
+3200/69092	Loss: 98.655
+6400/69092	Loss: 97.883
+9600/69092	Loss: 99.229
+12800/69092	Loss: 98.880
+16000/69092	Loss: 98.283
+19200/69092	Loss: 99.199
+22400/69092	Loss: 97.316
+25600/69092	Loss: 98.587
+28800/69092	Loss: 98.073
+32000/69092	Loss: 98.898
+35200/69092	Loss: 98.165
+38400/69092	Loss: 97.567
+41600/69092	Loss: 99.373
+44800/69092	Loss: 97.609
+48000/69092	Loss: 99.446
+51200/69092	Loss: 97.965
+54400/69092	Loss: 99.250
+57600/69092	Loss: 98.495
+60800/69092	Loss: 96.142
+64000/69092	Loss: 98.584
+67200/69092	Loss: 98.841
+Training time 0:10:37.106839
+Epoch: 138 Average loss: 98.45
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 289)
+0/69092	Loss: 99.328
+3200/69092	Loss: 99.179
+6400/69092	Loss: 98.470
+9600/69092	Loss: 99.869
+12800/69092	Loss: 97.914
+16000/69092	Loss: 98.960
+19200/69092	Loss: 99.191
+22400/69092	Loss: 98.092
+25600/69092	Loss: 100.163
+28800/69092	Loss: 98.588
+32000/69092	Loss: 97.221
+35200/69092	Loss: 97.644
+38400/69092	Loss: 97.014
+41600/69092	Loss: 97.451
+44800/69092	Loss: 98.982
+48000/69092	Loss: 98.598
+51200/69092	Loss: 97.818
+54400/69092	Loss: 97.614
+57600/69092	Loss: 98.327
+60800/69092	Loss: 98.403
+64000/69092	Loss: 97.821
+67200/69092	Loss: 98.665
+Training time 0:10:34.502115
+Epoch: 139 Average loss: 98.41
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 290)
+0/69092	Loss: 94.039
+3200/69092	Loss: 98.070
+6400/69092	Loss: 99.132
+9600/69092	Loss: 97.534
+12800/69092	Loss: 97.171
+16000/69092	Loss: 99.415
+19200/69092	Loss: 98.698
+22400/69092	Loss: 98.433
+25600/69092	Loss: 99.066
+28800/69092	Loss: 98.335
+32000/69092	Loss: 97.498
+35200/69092	Loss: 98.642
+38400/69092	Loss: 98.515
+41600/69092	Loss: 99.160
+44800/69092	Loss: 96.507
+48000/69092	Loss: 97.834
+51200/69092	Loss: 97.400
+54400/69092	Loss: 98.969
+57600/69092	Loss: 97.840
+60800/69092	Loss: 97.378
+64000/69092	Loss: 99.370
+67200/69092	Loss: 99.599
+Training time 0:10:57.252210
+Epoch: 140 Average loss: 98.34
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 291)
+0/69092	Loss: 101.593
+3200/69092	Loss: 98.785
+6400/69092	Loss: 97.931
+9600/69092	Loss: 99.381
+12800/69092	Loss: 97.848
+16000/69092	Loss: 97.517
+19200/69092	Loss: 98.539
+22400/69092	Loss: 98.114
+25600/69092	Loss: 98.551
+28800/69092	Loss: 99.319
+32000/69092	Loss: 97.925
+35200/69092	Loss: 97.890
+38400/69092	Loss: 99.090
+41600/69092	Loss: 97.863
+44800/69092	Loss: 98.007
+48000/69092	Loss: 100.040
+51200/69092	Loss: 99.104
+54400/69092	Loss: 97.189
+57600/69092	Loss: 98.525
+60800/69092	Loss: 96.958
+64000/69092	Loss: 99.238
+67200/69092	Loss: 100.164
+Training time 0:10:20.674060
+Epoch: 141 Average loss: 98.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 292)
+0/69092	Loss: 85.537
+3200/69092	Loss: 98.715
+6400/69092	Loss: 98.937
+9600/69092	Loss: 99.761
+12800/69092	Loss: 99.436
+16000/69092	Loss: 98.100
+19200/69092	Loss: 98.830
+22400/69092	Loss: 98.625
+25600/69092	Loss: 97.310
+28800/69092	Loss: 98.030
+32000/69092	Loss: 99.130
+35200/69092	Loss: 99.253
+38400/69092	Loss: 97.947
+41600/69092	Loss: 96.838
+44800/69092	Loss: 97.668
+48000/69092	Loss: 99.483
+51200/69092	Loss: 96.936
+54400/69092	Loss: 98.784
+57600/69092	Loss: 98.785
+60800/69092	Loss: 98.730
+64000/69092	Loss: 98.913
+67200/69092	Loss: 98.924
+Training time 0:10:37.186976
+Epoch: 142 Average loss: 98.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 293)
+0/69092	Loss: 94.435
+3200/69092	Loss: 97.969
+6400/69092	Loss: 98.976
+9600/69092	Loss: 97.173
+12800/69092	Loss: 97.825
+16000/69092	Loss: 98.651
+19200/69092	Loss: 98.510
+22400/69092	Loss: 98.659
+25600/69092	Loss: 97.602
+28800/69092	Loss: 100.083
+32000/69092	Loss: 99.947
+35200/69092	Loss: 98.868
+38400/69092	Loss: 97.315
+41600/69092	Loss: 98.191
+44800/69092	Loss: 97.384
+48000/69092	Loss: 96.543
+51200/69092	Loss: 98.852
+54400/69092	Loss: 98.953
+57600/69092	Loss: 98.563
+60800/69092	Loss: 98.152
+64000/69092	Loss: 98.745
+67200/69092	Loss: 98.965
+Training time 0:10:31.861825
+Epoch: 143 Average loss: 98.39
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 294)
+0/69092	Loss: 96.216
+3200/69092	Loss: 98.170
+6400/69092	Loss: 98.166
+9600/69092	Loss: 99.268
+12800/69092	Loss: 98.237
+16000/69092	Loss: 98.222
+19200/69092	Loss: 98.679
+22400/69092	Loss: 97.154
+25600/69092	Loss: 98.758
+28800/69092	Loss: 97.806
+32000/69092	Loss: 98.351
+35200/69092	Loss: 97.559
+38400/69092	Loss: 99.658
+41600/69092	Loss: 98.732
+44800/69092	Loss: 97.176
+48000/69092	Loss: 98.501
+51200/69092	Loss: 99.359
+54400/69092	Loss: 97.647
+57600/69092	Loss: 98.539
+60800/69092	Loss: 99.332
+64000/69092	Loss: 98.792
+67200/69092	Loss: 98.245
+Training time 0:10:30.650951
+Epoch: 144 Average loss: 98.37
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 295)
+0/69092	Loss: 102.145
+3200/69092	Loss: 98.363
+6400/69092	Loss: 97.904
+9600/69092	Loss: 98.767
+12800/69092	Loss: 99.173
+16000/69092	Loss: 98.887
+19200/69092	Loss: 98.632
+22400/69092	Loss: 98.926
+25600/69092	Loss: 96.997
+28800/69092	Loss: 100.028
+32000/69092	Loss: 98.836
+35200/69092	Loss: 98.990
+38400/69092	Loss: 96.708
+41600/69092	Loss: 97.499
+44800/69092	Loss: 98.089
+48000/69092	Loss: 99.078
+51200/69092	Loss: 99.274
+54400/69092	Loss: 95.953
+57600/69092	Loss: 98.308
+60800/69092	Loss: 99.239
+64000/69092	Loss: 98.664
+67200/69092	Loss: 97.616
+Training time 0:10:48.303826
+Epoch: 145 Average loss: 98.41
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 296)
+0/69092	Loss: 99.387
+3200/69092	Loss: 97.394
+6400/69092	Loss: 97.301
+9600/69092	Loss: 97.645
+12800/69092	Loss: 100.027
+16000/69092	Loss: 97.941
+19200/69092	Loss: 98.672
+22400/69092	Loss: 98.900
+25600/69092	Loss: 99.204
+28800/69092	Loss: 99.052
+32000/69092	Loss: 98.551
+35200/69092	Loss: 98.615
+38400/69092	Loss: 98.000
+41600/69092	Loss: 96.409
+44800/69092	Loss: 98.255
+48000/69092	Loss: 98.872
+51200/69092	Loss: 99.568
+54400/69092	Loss: 98.767
+57600/69092	Loss: 98.571
+60800/69092	Loss: 98.233
+64000/69092	Loss: 97.396
+67200/69092	Loss: 97.899
+Training time 0:10:49.425042
+Epoch: 146 Average loss: 98.37
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 297)
+0/69092	Loss: 98.357
+3200/69092	Loss: 99.496
+6400/69092	Loss: 99.227
+9600/69092	Loss: 98.636
+12800/69092	Loss: 97.246
+16000/69092	Loss: 97.778
+19200/69092	Loss: 97.675
+22400/69092	Loss: 98.415
+25600/69092	Loss: 98.900
+28800/69092	Loss: 98.005
+32000/69092	Loss: 98.163
+35200/69092	Loss: 98.116
+38400/69092	Loss: 98.168
+41600/69092	Loss: 98.462
+44800/69092	Loss: 98.854
+48000/69092	Loss: 97.907
+51200/69092	Loss: 97.429
+54400/69092	Loss: 98.364
+57600/69092	Loss: 98.297
+60800/69092	Loss: 99.846
+64000/69092	Loss: 96.692
+67200/69092	Loss: 97.110
+Training time 0:10:06.833043
+Epoch: 147 Average loss: 98.25
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 298)
+0/69092	Loss: 96.069
+3200/69092	Loss: 97.859
+6400/69092	Loss: 98.930
+9600/69092	Loss: 97.821
+12800/69092	Loss: 99.021
+16000/69092	Loss: 99.069
+19200/69092	Loss: 97.184
+22400/69092	Loss: 97.245
+25600/69092	Loss: 98.352
+28800/69092	Loss: 96.889
+32000/69092	Loss: 98.159
+35200/69092	Loss: 98.896
+38400/69092	Loss: 97.425
+41600/69092	Loss: 98.510
+44800/69092	Loss: 98.904
+48000/69092	Loss: 98.539
+51200/69092	Loss: 98.922
+54400/69092	Loss: 97.954
+57600/69092	Loss: 99.850
+60800/69092	Loss: 100.112
+64000/69092	Loss: 98.760
+67200/69092	Loss: 96.992
+Training time 0:10:27.090574
+Epoch: 148 Average loss: 98.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 299)
+0/69092	Loss: 108.348
+3200/69092	Loss: 97.272
+6400/69092	Loss: 98.914
+9600/69092	Loss: 96.968
+12800/69092	Loss: 97.904
+16000/69092	Loss: 97.084
+19200/69092	Loss: 97.373
+22400/69092	Loss: 98.297
+25600/69092	Loss: 98.165
+28800/69092	Loss: 99.564
+32000/69092	Loss: 99.031
+35200/69092	Loss: 97.925
+38400/69092	Loss: 97.819
+41600/69092	Loss: 99.011
+44800/69092	Loss: 99.046
+48000/69092	Loss: 98.453
+51200/69092	Loss: 97.966
+54400/69092	Loss: 99.508
+57600/69092	Loss: 98.384
+60800/69092	Loss: 97.129
+64000/69092	Loss: 97.142
+67200/69092	Loss: 99.113
+Training time 0:10:21.922799
+Epoch: 149 Average loss: 98.22
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 300)
+0/69092	Loss: 110.945
+3200/69092	Loss: 96.326
+6400/69092	Loss: 97.493
+9600/69092	Loss: 98.999
+12800/69092	Loss: 97.451
+16000/69092	Loss: 100.029
+19200/69092	Loss: 97.191
+22400/69092	Loss: 96.891
+25600/69092	Loss: 97.948
+28800/69092	Loss: 98.265
+32000/69092	Loss: 98.684
+35200/69092	Loss: 98.927
+38400/69092	Loss: 96.890
+41600/69092	Loss: 99.031
+44800/69092	Loss: 99.347
+48000/69092	Loss: 97.646
+51200/69092	Loss: 99.456
+54400/69092	Loss: 97.599
+57600/69092	Loss: 99.749
+60800/69092	Loss: 97.586
+64000/69092	Loss: 97.544
+67200/69092	Loss: 100.680
+Training time 0:10:15.347600
+Epoch: 150 Average loss: 98.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 301)
+0/69092	Loss: 109.307
+3200/69092	Loss: 98.101
+6400/69092	Loss: 97.161
+9600/69092	Loss: 99.357
+12800/69092	Loss: 96.355
+16000/69092	Loss: 98.253
+19200/69092	Loss: 98.471
+22400/69092	Loss: 98.589
+25600/69092	Loss: 98.359
+28800/69092	Loss: 97.120
+32000/69092	Loss: 98.567
+35200/69092	Loss: 97.941
+38400/69092	Loss: 97.811
+41600/69092	Loss: 96.742
+44800/69092	Loss: 99.476
+48000/69092	Loss: 97.908
+51200/69092	Loss: 98.560
+54400/69092	Loss: 98.548
+57600/69092	Loss: 98.758
+60800/69092	Loss: 97.784
+64000/69092	Loss: 99.288
+67200/69092	Loss: 97.976
+Training time 0:10:15.257413
+Epoch: 151 Average loss: 98.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 302)
+0/69092	Loss: 94.001
+3200/69092	Loss: 98.239
+6400/69092	Loss: 98.724
+9600/69092	Loss: 98.566
+12800/69092	Loss: 98.176
+16000/69092	Loss: 97.801
+19200/69092	Loss: 99.283
+22400/69092	Loss: 98.597
+25600/69092	Loss: 97.821
+28800/69092	Loss: 98.645
+32000/69092	Loss: 100.474
+35200/69092	Loss: 97.675
+38400/69092	Loss: 97.048
+41600/69092	Loss: 98.515
+44800/69092	Loss: 98.712
+48000/69092	Loss: 98.630
+51200/69092	Loss: 97.517
+54400/69092	Loss: 98.662
+57600/69092	Loss: 97.529
+60800/69092	Loss: 97.986
+64000/69092	Loss: 99.003
+67200/69092	Loss: 97.709
+Training time 0:10:34.425206
+Epoch: 152 Average loss: 98.34
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 303)
+0/69092	Loss: 102.046
+3200/69092	Loss: 98.243
+6400/69092	Loss: 99.078
+9600/69092	Loss: 98.772
+12800/69092	Loss: 99.060
+16000/69092	Loss: 98.515
+19200/69092	Loss: 99.940
+22400/69092	Loss: 97.495
+25600/69092	Loss: 97.657
+28800/69092	Loss: 98.360
+32000/69092	Loss: 97.212
+35200/69092	Loss: 97.612
+38400/69092	Loss: 97.888
+41600/69092	Loss: 97.036
+44800/69092	Loss: 97.052
+48000/69092	Loss: 98.905
+51200/69092	Loss: 98.694
+54400/69092	Loss: 99.106
+57600/69092	Loss: 98.671
+60800/69092	Loss: 98.324
+64000/69092	Loss: 97.433
+67200/69092	Loss: 99.143
+Training time 0:10:28.626121
+Epoch: 153 Average loss: 98.31
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 304)
+0/69092	Loss: 100.501
+3200/69092	Loss: 97.604
+6400/69092	Loss: 98.605
+9600/69092	Loss: 97.758
+12800/69092	Loss: 98.162
+16000/69092	Loss: 97.972
+19200/69092	Loss: 97.782
+22400/69092	Loss: 98.166
+25600/69092	Loss: 98.511
+28800/69092	Loss: 99.453
+32000/69092	Loss: 99.088
+35200/69092	Loss: 99.949
+38400/69092	Loss: 98.477
+41600/69092	Loss: 97.469
+44800/69092	Loss: 96.807
+48000/69092	Loss: 99.028
+51200/69092	Loss: 98.257
+54400/69092	Loss: 96.969
+57600/69092	Loss: 99.813
+60800/69092	Loss: 98.249
+64000/69092	Loss: 98.962
+67200/69092	Loss: 97.984
+Training time 0:10:13.843669
+Epoch: 154 Average loss: 98.37
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 305)
+0/69092	Loss: 97.084
+3200/69092	Loss: 98.443
+6400/69092	Loss: 99.652
+9600/69092	Loss: 97.663
+12800/69092	Loss: 98.178
+16000/69092	Loss: 97.596
+19200/69092	Loss: 97.024
+22400/69092	Loss: 97.737
+25600/69092	Loss: 99.803
+28800/69092	Loss: 98.216
+32000/69092	Loss: 97.949
+35200/69092	Loss: 98.836
+38400/69092	Loss: 99.411
+41600/69092	Loss: 97.976
+44800/69092	Loss: 98.455
+48000/69092	Loss: 99.194
+51200/69092	Loss: 98.135
+54400/69092	Loss: 96.989
+57600/69092	Loss: 98.332
+60800/69092	Loss: 97.931
+64000/69092	Loss: 98.652
+67200/69092	Loss: 97.984
+Training time 0:10:28.599627
+Epoch: 155 Average loss: 98.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 306)
+0/69092	Loss: 107.279
+3200/69092	Loss: 99.302
+6400/69092	Loss: 99.558
+9600/69092	Loss: 99.768
+12800/69092	Loss: 98.088
+16000/69092	Loss: 96.747
+19200/69092	Loss: 98.581
+22400/69092	Loss: 98.178
+25600/69092	Loss: 98.172
+28800/69092	Loss: 99.518
+32000/69092	Loss: 97.413
+35200/69092	Loss: 98.609
+38400/69092	Loss: 97.131
+41600/69092	Loss: 97.922
+44800/69092	Loss: 98.377
+48000/69092	Loss: 97.890
+51200/69092	Loss: 98.349
+54400/69092	Loss: 99.377
+57600/69092	Loss: 97.795
+60800/69092	Loss: 98.940
+64000/69092	Loss: 96.303
+67200/69092	Loss: 100.146
+Training time 0:10:41.862376
+Epoch: 156 Average loss: 98.38
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 307)
+0/69092	Loss: 102.525
+3200/69092	Loss: 98.392
+6400/69092	Loss: 97.438
+9600/69092	Loss: 96.778
+12800/69092	Loss: 96.937
+16000/69092	Loss: 96.735
+19200/69092	Loss: 97.385
+22400/69092	Loss: 100.006
+25600/69092	Loss: 97.696
+28800/69092	Loss: 98.371
+32000/69092	Loss: 98.732
+35200/69092	Loss: 97.810
+38400/69092	Loss: 98.441
+41600/69092	Loss: 98.206
+44800/69092	Loss: 98.781
+48000/69092	Loss: 99.793
+51200/69092	Loss: 97.651
+54400/69092	Loss: 98.632
+57600/69092	Loss: 97.181
+60800/69092	Loss: 98.633
+64000/69092	Loss: 97.575
+67200/69092	Loss: 99.577
+Training time 0:10:31.616132
+Epoch: 157 Average loss: 98.23
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 308)
+0/69092	Loss: 99.327
+3200/69092	Loss: 98.287
+6400/69092	Loss: 98.610
+9600/69092	Loss: 97.281
+12800/69092	Loss: 97.840
+16000/69092	Loss: 98.693
+19200/69092	Loss: 97.774
+22400/69092	Loss: 99.588
+25600/69092	Loss: 99.339
+28800/69092	Loss: 97.803
+32000/69092	Loss: 99.933
+35200/69092	Loss: 96.479
+38400/69092	Loss: 98.698
+41600/69092	Loss: 98.091
+44800/69092	Loss: 96.881
+48000/69092	Loss: 98.518
+51200/69092	Loss: 98.704
+54400/69092	Loss: 97.293
+57600/69092	Loss: 98.132
+60800/69092	Loss: 97.992
+64000/69092	Loss: 99.329
+67200/69092	Loss: 98.083
+Training time 0:10:23.959769
+Epoch: 158 Average loss: 98.24
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 309)
+0/69092	Loss: 93.983
+3200/69092	Loss: 97.368
+6400/69092	Loss: 100.395
+9600/69092	Loss: 98.142
+12800/69092	Loss: 98.373
+16000/69092	Loss: 100.137
+19200/69092	Loss: 97.934
+22400/69092	Loss: 98.226
+25600/69092	Loss: 96.776
+28800/69092	Loss: 98.399
+32000/69092	Loss: 97.609
+35200/69092	Loss: 98.009
+38400/69092	Loss: 97.960
+41600/69092	Loss: 99.538
+44800/69092	Loss: 98.594
+48000/69092	Loss: 96.821
+51200/69092	Loss: 97.301
+54400/69092	Loss: 98.321
+57600/69092	Loss: 98.153
+60800/69092	Loss: 97.221
+64000/69092	Loss: 99.593
+67200/69092	Loss: 97.517
+Training time 0:10:16.637672
+Epoch: 159 Average loss: 98.22
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 310)
+0/69092	Loss: 96.012
+3200/69092	Loss: 97.340
+6400/69092	Loss: 97.680
+9600/69092	Loss: 98.576
+12800/69092	Loss: 97.615
+16000/69092	Loss: 99.634
+19200/69092	Loss: 99.387
+22400/69092	Loss: 98.379
+25600/69092	Loss: 98.459
+28800/69092	Loss: 97.290
+32000/69092	Loss: 98.527
+35200/69092	Loss: 97.772
+38400/69092	Loss: 98.714
+41600/69092	Loss: 99.336
+44800/69092	Loss: 97.575
+48000/69092	Loss: 97.995
+51200/69092	Loss: 99.236
+54400/69092	Loss: 99.729
+57600/69092	Loss: 96.037
+60800/69092	Loss: 97.127
+64000/69092	Loss: 97.614
+67200/69092	Loss: 96.731
+Training time 0:10:44.079531
+Epoch: 160 Average loss: 98.15
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 311)
+0/69092	Loss: 112.640
+3200/69092	Loss: 99.934
+6400/69092	Loss: 97.467
+9600/69092	Loss: 98.054
+12800/69092	Loss: 98.297
+16000/69092	Loss: 98.461
+19200/69092	Loss: 98.143
+22400/69092	Loss: 98.465
+25600/69092	Loss: 99.428
+28800/69092	Loss: 96.475
+32000/69092	Loss: 98.502
+35200/69092	Loss: 98.954
+38400/69092	Loss: 99.319
+41600/69092	Loss: 97.561
+44800/69092	Loss: 97.548
+48000/69092	Loss: 98.486
+51200/69092	Loss: 97.166
+54400/69092	Loss: 98.884
+57600/69092	Loss: 97.741
+60800/69092	Loss: 98.200
+64000/69092	Loss: 97.814
+67200/69092	Loss: 98.132
+Training time 0:10:50.559813
+Epoch: 161 Average loss: 98.23
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 312)
+0/69092	Loss: 94.173
+3200/69092	Loss: 97.410
+6400/69092	Loss: 96.475
+9600/69092	Loss: 98.185
+12800/69092	Loss: 96.671
+16000/69092	Loss: 98.491
+19200/69092	Loss: 97.583
+22400/69092	Loss: 98.252
+25600/69092	Loss: 99.322
+28800/69092	Loss: 98.044
+32000/69092	Loss: 100.112
+35200/69092	Loss: 99.285
+38400/69092	Loss: 98.923
+41600/69092	Loss: 99.141
+44800/69092	Loss: 97.089
+48000/69092	Loss: 98.774
+51200/69092	Loss: 98.400
+54400/69092	Loss: 98.352
+57600/69092	Loss: 97.435
+60800/69092	Loss: 98.286
+64000/69092	Loss: 97.831
+67200/69092	Loss: 98.898
+Training time 0:11:08.525258
+Epoch: 162 Average loss: 98.20
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 313)
+0/69092	Loss: 95.671
+3200/69092	Loss: 97.893
+6400/69092	Loss: 98.044
+9600/69092	Loss: 97.302
+12800/69092	Loss: 97.660
+16000/69092	Loss: 98.089
+19200/69092	Loss: 98.233
+22400/69092	Loss: 96.830
+25600/69092	Loss: 98.003
+28800/69092	Loss: 98.802
+32000/69092	Loss: 98.502
+35200/69092	Loss: 98.406
+38400/69092	Loss: 98.020
+41600/69092	Loss: 98.801
+44800/69092	Loss: 97.595
+48000/69092	Loss: 98.753
+51200/69092	Loss: 98.745
+54400/69092	Loss: 97.978
+57600/69092	Loss: 97.811
+60800/69092	Loss: 98.615
+64000/69092	Loss: 100.102
+67200/69092	Loss: 99.495
+Training time 0:11:16.224858
+Epoch: 163 Average loss: 98.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 314)
+0/69092	Loss: 98.616
+3200/69092	Loss: 97.936
+6400/69092	Loss: 97.944
+9600/69092	Loss: 95.848
+12800/69092	Loss: 99.850
+16000/69092	Loss: 98.917
+19200/69092	Loss: 99.031
+22400/69092	Loss: 99.726
+25600/69092	Loss: 98.182
+28800/69092	Loss: 99.309
+32000/69092	Loss: 97.809
+35200/69092	Loss: 97.213
+38400/69092	Loss: 98.065
+41600/69092	Loss: 98.268
+44800/69092	Loss: 98.813
+48000/69092	Loss: 98.330
+51200/69092	Loss: 98.716
+54400/69092	Loss: 98.264
+57600/69092	Loss: 98.029
+60800/69092	Loss: 98.342
+64000/69092	Loss: 96.711
+67200/69092	Loss: 99.837
+Training time 0:10:33.351697
+Epoch: 164 Average loss: 98.31
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 315)
+0/69092	Loss: 92.416
+3200/69092	Loss: 97.405
+6400/69092	Loss: 97.930
+9600/69092	Loss: 96.540
+12800/69092	Loss: 98.906
+16000/69092	Loss: 99.651
+19200/69092	Loss: 98.192
+22400/69092	Loss: 98.803
+25600/69092	Loss: 98.830
+28800/69092	Loss: 97.878
+32000/69092	Loss: 98.335
+35200/69092	Loss: 99.160
+38400/69092	Loss: 98.621
+41600/69092	Loss: 98.579
+44800/69092	Loss: 96.659
+48000/69092	Loss: 98.567
+51200/69092	Loss: 98.634
+54400/69092	Loss: 97.512
+57600/69092	Loss: 98.730
+60800/69092	Loss: 97.594
+64000/69092	Loss: 98.190
+67200/69092	Loss: 97.129
+Training time 0:12:43.264850
+Epoch: 165 Average loss: 98.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 316)
+0/69092	Loss: 97.774
+3200/69092	Loss: 97.828
+6400/69092	Loss: 98.169
+9600/69092	Loss: 98.105
+12800/69092	Loss: 98.137
+16000/69092	Loss: 99.100
+19200/69092	Loss: 98.124
+22400/69092	Loss: 98.813
+25600/69092	Loss: 97.239
+28800/69092	Loss: 97.551
+32000/69092	Loss: 96.868
+35200/69092	Loss: 98.813
+38400/69092	Loss: 97.649
+41600/69092	Loss: 98.714
+44800/69092	Loss: 98.114
+48000/69092	Loss: 97.653
+51200/69092	Loss: 98.701
+54400/69092	Loss: 98.485
+57600/69092	Loss: 99.091
+60800/69092	Loss: 98.612
+64000/69092	Loss: 97.324
+67200/69092	Loss: 98.253
+Training time 0:13:24.917905
+Epoch: 166 Average loss: 98.16
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 317)
+0/69092	Loss: 94.077
+3200/69092	Loss: 99.126
+6400/69092	Loss: 97.794
+9600/69092	Loss: 98.755
+12800/69092	Loss: 97.960
+16000/69092	Loss: 98.922
+19200/69092	Loss: 97.375
+22400/69092	Loss: 99.253
+25600/69092	Loss: 99.195
+28800/69092	Loss: 97.207
+32000/69092	Loss: 98.464
+35200/69092	Loss: 97.130
+38400/69092	Loss: 95.987
+41600/69092	Loss: 98.964
+44800/69092	Loss: 98.555
+48000/69092	Loss: 97.369
+51200/69092	Loss: 98.525
+54400/69092	Loss: 97.068
+57600/69092	Loss: 98.455
+60800/69092	Loss: 99.489
+64000/69092	Loss: 97.640
+67200/69092	Loss: 97.681
+Training time 0:14:09.367848
+Epoch: 167 Average loss: 98.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 318)
+0/69092	Loss: 93.512
+3200/69092	Loss: 97.701
+6400/69092	Loss: 97.278
+9600/69092	Loss: 98.994
+12800/69092	Loss: 99.049
+16000/69092	Loss: 97.475
+19200/69092	Loss: 97.776
+22400/69092	Loss: 97.669
+25600/69092	Loss: 99.101
+28800/69092	Loss: 99.841
+32000/69092	Loss: 98.693
+35200/69092	Loss: 98.556
+38400/69092	Loss: 98.925
+41600/69092	Loss: 97.482
+44800/69092	Loss: 96.635
+48000/69092	Loss: 98.162
+51200/69092	Loss: 98.428
+54400/69092	Loss: 98.160
+57600/69092	Loss: 97.599
+60800/69092	Loss: 98.079
+64000/69092	Loss: 99.420
+67200/69092	Loss: 97.285
+Training time 0:10:34.036559
+Epoch: 168 Average loss: 98.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 319)
+0/69092	Loss: 103.887
+3200/69092	Loss: 98.155
+6400/69092	Loss: 98.173
+9600/69092	Loss: 98.513
+12800/69092	Loss: 95.892
+16000/69092	Loss: 98.028
+19200/69092	Loss: 97.630
+22400/69092	Loss: 98.138
+25600/69092	Loss: 98.080
+28800/69092	Loss: 97.712
+32000/69092	Loss: 99.004
+35200/69092	Loss: 97.991
+38400/69092	Loss: 98.123
+41600/69092	Loss: 99.218
+44800/69092	Loss: 98.908
+48000/69092	Loss: 96.220
+51200/69092	Loss: 99.173
+54400/69092	Loss: 98.415
+57600/69092	Loss: 98.235
+60800/69092	Loss: 99.162
+64000/69092	Loss: 98.697
+67200/69092	Loss: 98.868
+Training time 0:10:14.244180
+Epoch: 169 Average loss: 98.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 320)
+0/69092	Loss: 94.253
+3200/69092	Loss: 98.496
+6400/69092	Loss: 98.539
+9600/69092	Loss: 98.586
+12800/69092	Loss: 98.096
+16000/69092	Loss: 97.709
+19200/69092	Loss: 97.516
+22400/69092	Loss: 96.776
+25600/69092	Loss: 97.082
+28800/69092	Loss: 98.180
+32000/69092	Loss: 98.591
+35200/69092	Loss: 97.163
+38400/69092	Loss: 99.337
+41600/69092	Loss: 98.631
+44800/69092	Loss: 99.544
+48000/69092	Loss: 98.170
+51200/69092	Loss: 97.214
+54400/69092	Loss: 96.568
+57600/69092	Loss: 97.335
+60800/69092	Loss: 99.304
+64000/69092	Loss: 97.544
+67200/69092	Loss: 97.252
+Training time 0:10:35.787056
+Epoch: 170 Average loss: 97.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 321)
+0/69092	Loss: 95.024
+3200/69092	Loss: 97.308
+6400/69092	Loss: 96.921
+9600/69092	Loss: 98.798
+12800/69092	Loss: 98.268
+16000/69092	Loss: 97.637
+19200/69092	Loss: 99.079
+22400/69092	Loss: 98.449
+25600/69092	Loss: 99.124
+28800/69092	Loss: 98.336
+32000/69092	Loss: 96.917
+35200/69092	Loss: 99.851
+38400/69092	Loss: 96.948
+41600/69092	Loss: 96.668
+44800/69092	Loss: 98.954
+48000/69092	Loss: 97.796
+51200/69092	Loss: 98.903
+54400/69092	Loss: 97.784
+57600/69092	Loss: 98.566
+60800/69092	Loss: 98.480
+64000/69092	Loss: 99.075
+67200/69092	Loss: 99.186
+Training time 0:10:36.581540
+Epoch: 171 Average loss: 98.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 322)
+0/69092	Loss: 101.326
+3200/69092	Loss: 98.032
+6400/69092	Loss: 98.862
+9600/69092	Loss: 98.017
+12800/69092	Loss: 97.800
+16000/69092	Loss: 98.697
+19200/69092	Loss: 99.089
+22400/69092	Loss: 97.971
+25600/69092	Loss: 98.371
+28800/69092	Loss: 98.178
+32000/69092	Loss: 98.555
+35200/69092	Loss: 98.254
+38400/69092	Loss: 99.814
+41600/69092	Loss: 98.124
+44800/69092	Loss: 97.826
+48000/69092	Loss: 99.624
+51200/69092	Loss: 98.152
+54400/69092	Loss: 97.692
+57600/69092	Loss: 96.734
+60800/69092	Loss: 99.029
+64000/69092	Loss: 96.515
+67200/69092	Loss: 96.665
+Training time 0:10:24.525175
+Epoch: 172 Average loss: 98.13
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 323)
+0/69092	Loss: 92.380
+3200/69092	Loss: 98.063
+6400/69092	Loss: 98.860
+9600/69092	Loss: 97.082
+12800/69092	Loss: 98.747
+16000/69092	Loss: 98.258
+19200/69092	Loss: 98.613
+22400/69092	Loss: 100.499
+25600/69092	Loss: 97.583
+28800/69092	Loss: 98.128
+32000/69092	Loss: 97.839
+35200/69092	Loss: 97.443
+38400/69092	Loss: 97.941
+41600/69092	Loss: 98.619
+44800/69092	Loss: 98.128
+48000/69092	Loss: 97.087
+51200/69092	Loss: 97.866
+54400/69092	Loss: 99.180
+57600/69092	Loss: 96.889
+60800/69092	Loss: 98.515
+64000/69092	Loss: 99.746
+67200/69092	Loss: 97.253
+Training time 0:10:13.844486
+Epoch: 173 Average loss: 98.16
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 324)
+0/69092	Loss: 104.825
+3200/69092	Loss: 97.515
+6400/69092	Loss: 98.988
+9600/69092	Loss: 97.247
+12800/69092	Loss: 98.691
+16000/69092	Loss: 97.595
+19200/69092	Loss: 99.162
+22400/69092	Loss: 98.002
+25600/69092	Loss: 98.334
+28800/69092	Loss: 97.022
+32000/69092	Loss: 97.954
+35200/69092	Loss: 96.054
+38400/69092	Loss: 99.949
+41600/69092	Loss: 97.668
+44800/69092	Loss: 97.102
+48000/69092	Loss: 97.000
+51200/69092	Loss: 98.170
+54400/69092	Loss: 100.072
+57600/69092	Loss: 98.318
+60800/69092	Loss: 98.244
+64000/69092	Loss: 97.852
+67200/69092	Loss: 98.157
+Training time 0:10:25.395935
+Epoch: 174 Average loss: 98.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 325)
+0/69092	Loss: 95.461
+3200/69092	Loss: 98.727
+6400/69092	Loss: 97.471
+9600/69092	Loss: 99.072
+12800/69092	Loss: 97.924
+16000/69092	Loss: 98.807
+19200/69092	Loss: 97.924
+22400/69092	Loss: 96.782
+25600/69092	Loss: 97.791
+28800/69092	Loss: 97.544
+32000/69092	Loss: 97.709
+35200/69092	Loss: 97.729
+38400/69092	Loss: 98.362
+41600/69092	Loss: 98.389
+44800/69092	Loss: 97.310
+48000/69092	Loss: 99.556
+51200/69092	Loss: 97.419
+54400/69092	Loss: 99.490
+57600/69092	Loss: 97.560
+60800/69092	Loss: 98.428
+64000/69092	Loss: 97.345
+67200/69092	Loss: 97.150
+Training time 0:10:32.988209
+Epoch: 175 Average loss: 98.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 326)
+0/69092	Loss: 95.774
+3200/69092	Loss: 96.909
+6400/69092	Loss: 97.670
+9600/69092	Loss: 98.492
+12800/69092	Loss: 98.244
+16000/69092	Loss: 98.693
+19200/69092	Loss: 98.651
+22400/69092	Loss: 96.936
+25600/69092	Loss: 96.211
+28800/69092	Loss: 98.904
+32000/69092	Loss: 97.423
+35200/69092	Loss: 97.747
+38400/69092	Loss: 97.414
+41600/69092	Loss: 98.549
+44800/69092	Loss: 98.433
+48000/69092	Loss: 100.038
+51200/69092	Loss: 98.135
+54400/69092	Loss: 97.355
+57600/69092	Loss: 96.570
+60800/69092	Loss: 97.969
+64000/69092	Loss: 98.980
+67200/69092	Loss: 98.654
+Training time 0:10:21.617439
+Epoch: 176 Average loss: 98.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 327)
+0/69092	Loss: 105.659
+3200/69092	Loss: 98.557
+6400/69092	Loss: 97.608
+9600/69092	Loss: 98.763
+12800/69092	Loss: 98.059
+16000/69092	Loss: 98.490
+19200/69092	Loss: 97.642
+22400/69092	Loss: 98.409
+25600/69092	Loss: 98.616
+28800/69092	Loss: 96.312
+32000/69092	Loss: 98.706
+35200/69092	Loss: 96.496
+38400/69092	Loss: 99.041
+41600/69092	Loss: 99.345
+44800/69092	Loss: 97.950
+48000/69092	Loss: 98.456
+51200/69092	Loss: 97.258
+54400/69092	Loss: 97.572
+57600/69092	Loss: 99.140
+60800/69092	Loss: 97.441
+64000/69092	Loss: 97.064
+67200/69092	Loss: 97.635
+Training time 0:10:52.977585
+Epoch: 177 Average loss: 98.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 328)
+0/69092	Loss: 100.260
+3200/69092	Loss: 97.870
+6400/69092	Loss: 97.507
+9600/69092	Loss: 98.781
+12800/69092	Loss: 99.599
+16000/69092	Loss: 99.306
+19200/69092	Loss: 98.309
+22400/69092	Loss: 97.510
+25600/69092	Loss: 97.543
+28800/69092	Loss: 99.745
+32000/69092	Loss: 98.470
+35200/69092	Loss: 97.717
+38400/69092	Loss: 98.658
+41600/69092	Loss: 97.954
+44800/69092	Loss: 100.100
+48000/69092	Loss: 97.260
+51200/69092	Loss: 96.223
+54400/69092	Loss: 97.890
+57600/69092	Loss: 97.910
+60800/69092	Loss: 98.846
+64000/69092	Loss: 96.599
+67200/69092	Loss: 96.259
+Training time 0:10:30.435081
+Epoch: 178 Average loss: 98.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 329)
+0/69092	Loss: 100.609
+3200/69092	Loss: 97.095
+6400/69092	Loss: 98.219
+9600/69092	Loss: 99.088
+12800/69092	Loss: 98.063
+16000/69092	Loss: 97.975
+19200/69092	Loss: 98.779
+22400/69092	Loss: 98.486
+25600/69092	Loss: 98.405
+28800/69092	Loss: 98.183
+32000/69092	Loss: 97.464
+35200/69092	Loss: 97.266
+38400/69092	Loss: 97.498
+41600/69092	Loss: 97.087
+44800/69092	Loss: 97.639
+48000/69092	Loss: 98.185
+51200/69092	Loss: 97.865
+54400/69092	Loss: 96.195
+57600/69092	Loss: 97.484
+60800/69092	Loss: 99.810
+64000/69092	Loss: 97.416
+67200/69092	Loss: 97.201
+Training time 0:10:38.142472
+Epoch: 179 Average loss: 97.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 330)
+0/69092	Loss: 96.943
+3200/69092	Loss: 96.603
+6400/69092	Loss: 98.701
+9600/69092	Loss: 98.923
+12800/69092	Loss: 98.372
+16000/69092	Loss: 98.435
+19200/69092	Loss: 97.619
+22400/69092	Loss: 99.150
+25600/69092	Loss: 99.389
+28800/69092	Loss: 99.122
+32000/69092	Loss: 96.686
+35200/69092	Loss: 98.883
+38400/69092	Loss: 97.304
+41600/69092	Loss: 96.530
+44800/69092	Loss: 97.108
+48000/69092	Loss: 98.530
+51200/69092	Loss: 98.975
+54400/69092	Loss: 97.504
+57600/69092	Loss: 99.012
+60800/69092	Loss: 98.877
+64000/69092	Loss: 97.133
+67200/69092	Loss: 96.516
+Training time 0:10:02.390300
+Epoch: 180 Average loss: 98.08
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 331)
+0/69092	Loss: 88.820
+3200/69092	Loss: 96.257
+6400/69092	Loss: 97.321
+9600/69092	Loss: 96.604
+12800/69092	Loss: 99.226
+16000/69092	Loss: 96.869
+19200/69092	Loss: 97.724
+22400/69092	Loss: 97.475
+25600/69092	Loss: 98.080
+28800/69092	Loss: 98.804
+32000/69092	Loss: 97.523
+35200/69092	Loss: 98.680
+38400/69092	Loss: 98.864
+41600/69092	Loss: 97.495
+44800/69092	Loss: 99.304
+48000/69092	Loss: 97.814
+51200/69092	Loss: 98.917
+54400/69092	Loss: 96.779
+57600/69092	Loss: 99.296
+60800/69092	Loss: 98.977
+64000/69092	Loss: 98.939
+67200/69092	Loss: 98.346
+Training time 0:10:33.987920
+Epoch: 181 Average loss: 98.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 332)
+0/69092	Loss: 97.747
+3200/69092	Loss: 98.473
+6400/69092	Loss: 98.071
+9600/69092	Loss: 98.417
+12800/69092	Loss: 97.509
+16000/69092	Loss: 97.445
+19200/69092	Loss: 97.630
+22400/69092	Loss: 98.036
+25600/69092	Loss: 96.162
+28800/69092	Loss: 97.567
+32000/69092	Loss: 97.982
+35200/69092	Loss: 98.037
+38400/69092	Loss: 98.349
+41600/69092	Loss: 99.363
+44800/69092	Loss: 96.832
+48000/69092	Loss: 99.166
+51200/69092	Loss: 97.011
+54400/69092	Loss: 98.906
+57600/69092	Loss: 98.500
+60800/69092	Loss: 98.300
+64000/69092	Loss: 99.183
+67200/69092	Loss: 98.772
+Training time 0:10:08.792180
+Epoch: 182 Average loss: 98.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 333)
+0/69092	Loss: 96.913
+3200/69092	Loss: 96.387
+6400/69092	Loss: 100.573
+9600/69092	Loss: 97.668
+12800/69092	Loss: 98.330
+16000/69092	Loss: 97.493
+19200/69092	Loss: 99.429
+22400/69092	Loss: 98.247
+25600/69092	Loss: 96.254
+28800/69092	Loss: 97.794
+32000/69092	Loss: 97.240
+35200/69092	Loss: 97.468
+38400/69092	Loss: 99.131
+41600/69092	Loss: 98.339
+44800/69092	Loss: 98.618
+48000/69092	Loss: 98.992
+51200/69092	Loss: 98.526
+54400/69092	Loss: 98.435
+57600/69092	Loss: 98.435
+60800/69092	Loss: 97.758
+64000/69092	Loss: 97.085
+67200/69092	Loss: 96.175
+Training time 0:10:32.837426
+Epoch: 183 Average loss: 98.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 334)
+0/69092	Loss: 115.002
+3200/69092	Loss: 98.958
+6400/69092	Loss: 97.857
+9600/69092	Loss: 99.014
+12800/69092	Loss: 98.108
+16000/69092	Loss: 97.282
+19200/69092	Loss: 97.820
+22400/69092	Loss: 98.268
+25600/69092	Loss: 98.444
+28800/69092	Loss: 97.034
+32000/69092	Loss: 98.147
+35200/69092	Loss: 97.583
+38400/69092	Loss: 98.471
+41600/69092	Loss: 97.852
+44800/69092	Loss: 98.298
+48000/69092	Loss: 99.073
+51200/69092	Loss: 97.965
+54400/69092	Loss: 97.504
+57600/69092	Loss: 98.467
+60800/69092	Loss: 98.421
+64000/69092	Loss: 97.045
+67200/69092	Loss: 97.283
+Training time 0:10:40.812992
+Epoch: 184 Average loss: 98.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 335)
+0/69092	Loss: 95.924
+3200/69092	Loss: 96.572
+6400/69092	Loss: 97.020
+9600/69092	Loss: 97.838
+12800/69092	Loss: 97.814
+16000/69092	Loss: 97.843
+19200/69092	Loss: 98.173
+22400/69092	Loss: 98.884
+25600/69092	Loss: 99.090
+28800/69092	Loss: 98.278
+32000/69092	Loss: 96.425
+35200/69092	Loss: 98.154
+38400/69092	Loss: 97.862
+41600/69092	Loss: 99.277
+44800/69092	Loss: 97.498
+48000/69092	Loss: 99.522
+51200/69092	Loss: 99.470
+54400/69092	Loss: 97.273
+57600/69092	Loss: 96.970
+60800/69092	Loss: 98.124
+64000/69092	Loss: 97.301
+67200/69092	Loss: 97.058
+Training time 0:10:55.541279
+Epoch: 185 Average loss: 97.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 336)
+0/69092	Loss: 83.727
+3200/69092	Loss: 98.492
+6400/69092	Loss: 98.066
+9600/69092	Loss: 97.880
+12800/69092	Loss: 97.536
+16000/69092	Loss: 97.832
+19200/69092	Loss: 99.815
+22400/69092	Loss: 96.815
+25600/69092	Loss: 97.552
+28800/69092	Loss: 97.938
+32000/69092	Loss: 98.550
+35200/69092	Loss: 98.376
+38400/69092	Loss: 97.697
+41600/69092	Loss: 98.552
+44800/69092	Loss: 97.927
+48000/69092	Loss: 97.156
+51200/69092	Loss: 98.214
+54400/69092	Loss: 99.438
+57600/69092	Loss: 98.492
+60800/69092	Loss: 97.725
+64000/69092	Loss: 98.602
+67200/69092	Loss: 98.765
+Training time 0:10:24.438608
+Epoch: 186 Average loss: 98.12
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 337)
+0/69092	Loss: 92.979
+3200/69092	Loss: 97.604
+6400/69092	Loss: 98.249
+9600/69092	Loss: 98.921
+12800/69092	Loss: 97.965
+16000/69092	Loss: 98.428
+19200/69092	Loss: 97.862
+22400/69092	Loss: 96.876
+25600/69092	Loss: 98.547
+28800/69092	Loss: 98.908
+32000/69092	Loss: 98.379
+35200/69092	Loss: 97.194
+38400/69092	Loss: 97.365
+41600/69092	Loss: 99.197
+44800/69092	Loss: 96.762
+48000/69092	Loss: 98.557
+51200/69092	Loss: 98.386
+54400/69092	Loss: 98.735
+57600/69092	Loss: 96.891
+60800/69092	Loss: 97.820
+64000/69092	Loss: 97.124
+67200/69092	Loss: 96.989
+Training time 0:10:18.409025
+Epoch: 187 Average loss: 97.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 338)
+0/69092	Loss: 97.516
+3200/69092	Loss: 99.095
+6400/69092	Loss: 98.399
+9600/69092	Loss: 98.691
+12800/69092	Loss: 97.038
+16000/69092	Loss: 97.569
+19200/69092	Loss: 98.539
+22400/69092	Loss: 99.650
+25600/69092	Loss: 97.976
+28800/69092	Loss: 97.396
+32000/69092	Loss: 96.578
+35200/69092	Loss: 97.632
+38400/69092	Loss: 98.994
+41600/69092	Loss: 98.655
+44800/69092	Loss: 99.178
+48000/69092	Loss: 99.633
+51200/69092	Loss: 98.347
+54400/69092	Loss: 98.289
+57600/69092	Loss: 96.850
+60800/69092	Loss: 97.944
+64000/69092	Loss: 96.652
+67200/69092	Loss: 98.260
+Training time 0:10:25.715475
+Epoch: 188 Average loss: 98.15
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 339)
+0/69092	Loss: 101.824
+3200/69092	Loss: 97.819
+6400/69092	Loss: 98.402
+9600/69092	Loss: 97.668
+12800/69092	Loss: 95.909
+16000/69092	Loss: 98.196
+19200/69092	Loss: 97.940
+22400/69092	Loss: 99.174
+25600/69092	Loss: 97.898
+28800/69092	Loss: 99.509
+32000/69092	Loss: 98.409
+35200/69092	Loss: 97.470
+38400/69092	Loss: 98.635
+41600/69092	Loss: 97.413
+44800/69092	Loss: 98.501
+48000/69092	Loss: 98.064
+51200/69092	Loss: 97.456
+54400/69092	Loss: 98.637
+57600/69092	Loss: 97.086
+60800/69092	Loss: 97.561
+64000/69092	Loss: 96.761
+67200/69092	Loss: 98.108
+Training time 0:10:52.228950
+Epoch: 189 Average loss: 97.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 340)
+0/69092	Loss: 86.152
+3200/69092	Loss: 98.043
+6400/69092	Loss: 99.174
+9600/69092	Loss: 97.275
+12800/69092	Loss: 99.317
+16000/69092	Loss: 97.388
+19200/69092	Loss: 96.797
+22400/69092	Loss: 98.445
+25600/69092	Loss: 98.645
+28800/69092	Loss: 96.769
+32000/69092	Loss: 98.106
+35200/69092	Loss: 98.173
+38400/69092	Loss: 97.182
+41600/69092	Loss: 98.197
+44800/69092	Loss: 98.253
+48000/69092	Loss: 98.544
+51200/69092	Loss: 98.266
+54400/69092	Loss: 96.415
+57600/69092	Loss: 98.549
+60800/69092	Loss: 97.085
+64000/69092	Loss: 96.785
+67200/69092	Loss: 98.781
+Training time 0:10:20.197803
+Epoch: 190 Average loss: 97.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 341)
+0/69092	Loss: 98.072
+3200/69092	Loss: 97.119
+6400/69092	Loss: 97.593
+9600/69092	Loss: 99.705
+12800/69092	Loss: 98.692
+16000/69092	Loss: 97.643
+19200/69092	Loss: 96.582
+22400/69092	Loss: 98.620
+25600/69092	Loss: 98.305
+28800/69092	Loss: 98.110
+32000/69092	Loss: 98.872
+35200/69092	Loss: 97.149
+38400/69092	Loss: 98.614
+41600/69092	Loss: 98.579
+44800/69092	Loss: 97.584
+48000/69092	Loss: 96.324
+51200/69092	Loss: 98.902
+54400/69092	Loss: 96.874
+57600/69092	Loss: 99.538
+60800/69092	Loss: 97.361
+64000/69092	Loss: 98.255
+67200/69092	Loss: 97.632
+Training time 0:10:44.401777
+Epoch: 191 Average loss: 97.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 342)
+0/69092	Loss: 94.441
+3200/69092	Loss: 98.059
+6400/69092	Loss: 98.131
+9600/69092	Loss: 97.335
+12800/69092	Loss: 97.602
+16000/69092	Loss: 99.272
+19200/69092	Loss: 97.943
+22400/69092	Loss: 96.309
+25600/69092	Loss: 96.554
+28800/69092	Loss: 97.751
+32000/69092	Loss: 98.636
+35200/69092	Loss: 98.097
+38400/69092	Loss: 97.270
+41600/69092	Loss: 98.393
+44800/69092	Loss: 97.996
+48000/69092	Loss: 96.554
+51200/69092	Loss: 97.515
+54400/69092	Loss: 98.180
+57600/69092	Loss: 98.681
+60800/69092	Loss: 98.844
+64000/69092	Loss: 98.858
+67200/69092	Loss: 97.694
+Training time 0:10:32.081897
+Epoch: 192 Average loss: 97.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 343)
+0/69092	Loss: 96.472
+3200/69092	Loss: 97.645
+6400/69092	Loss: 98.490
+9600/69092	Loss: 97.526
+12800/69092	Loss: 98.333
+16000/69092	Loss: 97.153
+19200/69092	Loss: 97.306
+22400/69092	Loss: 98.635
+25600/69092	Loss: 97.469
+28800/69092	Loss: 98.038
+32000/69092	Loss: 97.387
+35200/69092	Loss: 98.271
+38400/69092	Loss: 97.678
+41600/69092	Loss: 98.379
+44800/69092	Loss: 97.652
+48000/69092	Loss: 97.200
+51200/69092	Loss: 98.087
+54400/69092	Loss: 98.409
+57600/69092	Loss: 98.387
+60800/69092	Loss: 97.629
+64000/69092	Loss: 98.820
+67200/69092	Loss: 97.312
+Training time 0:10:30.891479
+Epoch: 193 Average loss: 97.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 344)
+0/69092	Loss: 98.469
+3200/69092	Loss: 97.283
+6400/69092	Loss: 97.438
+9600/69092	Loss: 96.912
+12800/69092	Loss: 97.868
+16000/69092	Loss: 98.130
+19200/69092	Loss: 98.277
+22400/69092	Loss: 98.162
+25600/69092	Loss: 98.349
+28800/69092	Loss: 97.048
+32000/69092	Loss: 98.323
+35200/69092	Loss: 97.162
+38400/69092	Loss: 98.097
+41600/69092	Loss: 97.650
+44800/69092	Loss: 98.070
+48000/69092	Loss: 95.570
+51200/69092	Loss: 99.206
+54400/69092	Loss: 97.327
+57600/69092	Loss: 97.433
+60800/69092	Loss: 97.848
+64000/69092	Loss: 99.489
+67200/69092	Loss: 98.195
+Training time 0:10:39.120607
+Epoch: 194 Average loss: 97.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 345)
+0/69092	Loss: 86.333
+3200/69092	Loss: 97.974
+6400/69092	Loss: 99.585
+9600/69092	Loss: 97.048
+12800/69092	Loss: 97.467
+16000/69092	Loss: 97.703
+19200/69092	Loss: 97.812
+22400/69092	Loss: 98.048
+25600/69092	Loss: 98.004
+28800/69092	Loss: 98.876
+32000/69092	Loss: 97.479
+35200/69092	Loss: 98.245
+38400/69092	Loss: 97.552
+41600/69092	Loss: 97.420
+44800/69092	Loss: 98.804
+48000/69092	Loss: 97.136
+51200/69092	Loss: 96.495
+54400/69092	Loss: 97.353
+57600/69092	Loss: 97.528
+60800/69092	Loss: 98.153
+64000/69092	Loss: 98.409
+67200/69092	Loss: 99.141
+Training time 0:10:38.047377
+Epoch: 195 Average loss: 97.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 346)
+0/69092	Loss: 99.119
+3200/69092	Loss: 98.141
+6400/69092	Loss: 96.620
+9600/69092	Loss: 98.305
+12800/69092	Loss: 98.017
+16000/69092	Loss: 97.531
+19200/69092	Loss: 97.241
+22400/69092	Loss: 97.690
+25600/69092	Loss: 97.796
+28800/69092	Loss: 99.507
+32000/69092	Loss: 98.128
+35200/69092	Loss: 98.194
+38400/69092	Loss: 97.341
+41600/69092	Loss: 96.924
+44800/69092	Loss: 97.130
+48000/69092	Loss: 97.802
+51200/69092	Loss: 96.838
+54400/69092	Loss: 98.265
+57600/69092	Loss: 98.351
+60800/69092	Loss: 97.449
+64000/69092	Loss: 99.622
+67200/69092	Loss: 97.265
+Training time 0:10:34.787996
+Epoch: 196 Average loss: 97.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 347)
+0/69092	Loss: 95.408
+3200/69092	Loss: 97.688
+6400/69092	Loss: 97.898
+9600/69092	Loss: 98.392
+12800/69092	Loss: 97.737
+16000/69092	Loss: 97.542
+19200/69092	Loss: 97.926
+22400/69092	Loss: 98.490
+25600/69092	Loss: 97.883
+28800/69092	Loss: 95.956
+32000/69092	Loss: 98.769
+35200/69092	Loss: 97.105
+38400/69092	Loss: 97.668
+41600/69092	Loss: 97.119
+44800/69092	Loss: 100.023
+48000/69092	Loss: 98.737
+51200/69092	Loss: 99.350
+54400/69092	Loss: 98.811
+57600/69092	Loss: 97.783
+60800/69092	Loss: 98.435
+64000/69092	Loss: 97.226
+67200/69092	Loss: 95.603
+Training time 0:10:42.729827
+Epoch: 197 Average loss: 97.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 348)
+0/69092	Loss: 94.113
+3200/69092	Loss: 99.649
+6400/69092	Loss: 98.943
+9600/69092	Loss: 100.372
+12800/69092	Loss: 96.863
+16000/69092	Loss: 98.158
+19200/69092	Loss: 97.115
+22400/69092	Loss: 98.433
+25600/69092	Loss: 98.001
+28800/69092	Loss: 97.901
+32000/69092	Loss: 97.640
+35200/69092	Loss: 98.062
+38400/69092	Loss: 98.358
+41600/69092	Loss: 98.673
+44800/69092	Loss: 96.951
+48000/69092	Loss: 97.734
+51200/69092	Loss: 100.051
+54400/69092	Loss: 96.786
+57600/69092	Loss: 96.129
+60800/69092	Loss: 96.951
+64000/69092	Loss: 97.081
+67200/69092	Loss: 96.266
+Training time 0:10:27.510002
+Epoch: 198 Average loss: 97.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 349)
+0/69092	Loss: 104.497
+3200/69092	Loss: 97.216
+6400/69092	Loss: 98.226
+9600/69092	Loss: 99.271
+12800/69092	Loss: 97.410
+16000/69092	Loss: 97.223
+19200/69092	Loss: 97.969
+22400/69092	Loss: 97.534
+25600/69092	Loss: 98.070
+28800/69092	Loss: 97.627
+32000/69092	Loss: 96.902
+35200/69092	Loss: 97.853
+38400/69092	Loss: 97.673
+41600/69092	Loss: 98.188
+44800/69092	Loss: 98.555
+48000/69092	Loss: 98.012
+51200/69092	Loss: 99.784
+54400/69092	Loss: 100.155
+57600/69092	Loss: 97.122
+60800/69092	Loss: 98.559
+64000/69092	Loss: 96.351
+67200/69092	Loss: 97.841
+Training time 0:10:41.839104
+Epoch: 199 Average loss: 98.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 350)
+0/69092	Loss: 95.922
+3200/69092	Loss: 97.496
+6400/69092	Loss: 97.386
+9600/69092	Loss: 98.313
+12800/69092	Loss: 97.158
+16000/69092	Loss: 98.775
+19200/69092	Loss: 97.778
+22400/69092	Loss: 98.637
+25600/69092	Loss: 98.333
+28800/69092	Loss: 98.738
+32000/69092	Loss: 96.877
+35200/69092	Loss: 98.001
+38400/69092	Loss: 96.466
+41600/69092	Loss: 98.758
+44800/69092	Loss: 96.998
+48000/69092	Loss: 97.217
+51200/69092	Loss: 98.025
+54400/69092	Loss: 98.595
+57600/69092	Loss: 96.985
+60800/69092	Loss: 97.694
+64000/69092	Loss: 98.705
+67200/69092	Loss: 97.716
+Training time 0:10:27.551727
+Epoch: 200 Average loss: 97.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 351)
+0/69092	Loss: 91.509
+3200/69092	Loss: 97.435
+6400/69092	Loss: 98.897
+9600/69092	Loss: 96.761
+12800/69092	Loss: 97.232
+16000/69092	Loss: 96.543
+19200/69092	Loss: 99.271
+22400/69092	Loss: 97.821
+25600/69092	Loss: 97.965
+28800/69092	Loss: 98.099
+32000/69092	Loss: 97.253
+35200/69092	Loss: 97.722
+38400/69092	Loss: 96.786
+41600/69092	Loss: 98.450
+44800/69092	Loss: 99.835
+48000/69092	Loss: 97.886
+51200/69092	Loss: 99.599
+54400/69092	Loss: 98.938
+57600/69092	Loss: 96.867
+60800/69092	Loss: 97.954
+64000/69092	Loss: 98.348
+67200/69092	Loss: 97.235
+Training time 0:11:01.813552
+Epoch: 201 Average loss: 97.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 352)
+0/69092	Loss: 102.499
+3200/69092	Loss: 98.574
+6400/69092	Loss: 97.649
+9600/69092	Loss: 97.225
+12800/69092	Loss: 98.061
+16000/69092	Loss: 98.130
+19200/69092	Loss: 99.615
+22400/69092	Loss: 98.586
+25600/69092	Loss: 97.974
+28800/69092	Loss: 97.136
+32000/69092	Loss: 95.949
+35200/69092	Loss: 97.230
+38400/69092	Loss: 98.174
+41600/69092	Loss: 97.678
+44800/69092	Loss: 98.705
+48000/69092	Loss: 97.620
+51200/69092	Loss: 97.813
+54400/69092	Loss: 98.589
+57600/69092	Loss: 98.827
+60800/69092	Loss: 97.111
+64000/69092	Loss: 96.536
+67200/69092	Loss: 97.584
+Training time 0:10:31.163189
+Epoch: 202 Average loss: 97.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 353)
+0/69092	Loss: 109.693
+3200/69092	Loss: 97.077
+6400/69092	Loss: 97.594
+9600/69092	Loss: 98.576
+12800/69092	Loss: 98.821
+16000/69092	Loss: 96.185
+19200/69092	Loss: 97.421
+22400/69092	Loss: 98.388
+25600/69092	Loss: 98.489
+28800/69092	Loss: 97.288
+32000/69092	Loss: 98.274
+35200/69092	Loss: 98.240
+38400/69092	Loss: 96.641
+41600/69092	Loss: 99.368
+44800/69092	Loss: 97.768
+48000/69092	Loss: 95.759
+51200/69092	Loss: 97.804
+54400/69092	Loss: 97.744
+57600/69092	Loss: 98.908
+60800/69092	Loss: 97.468
+64000/69092	Loss: 98.823
+67200/69092	Loss: 96.620
+Training time 0:10:33.018121
+Epoch: 203 Average loss: 97.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 354)
+0/69092	Loss: 97.965
+3200/69092	Loss: 97.269
+6400/69092	Loss: 97.580
+9600/69092	Loss: 98.522
+12800/69092	Loss: 97.169
+16000/69092	Loss: 98.043
+19200/69092	Loss: 96.798
+22400/69092	Loss: 98.586
+25600/69092	Loss: 98.638
+28800/69092	Loss: 97.944
+32000/69092	Loss: 97.545
+35200/69092	Loss: 97.260
+38400/69092	Loss: 96.615
+41600/69092	Loss: 97.607
+44800/69092	Loss: 99.194
+48000/69092	Loss: 97.125
+51200/69092	Loss: 98.589
+54400/69092	Loss: 97.997
+57600/69092	Loss: 97.204
+60800/69092	Loss: 97.009
+64000/69092	Loss: 98.240
+67200/69092	Loss: 98.572
+Training time 0:10:10.687875
+Epoch: 204 Average loss: 97.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 355)
+0/69092	Loss: 98.507
+3200/69092	Loss: 98.386
+6400/69092	Loss: 97.213
+9600/69092	Loss: 98.662
+12800/69092	Loss: 96.034
+16000/69092	Loss: 97.866
+19200/69092	Loss: 96.961
+22400/69092	Loss: 98.053
+25600/69092	Loss: 97.088
+28800/69092	Loss: 97.881
+32000/69092	Loss: 97.400
+35200/69092	Loss: 100.212
+38400/69092	Loss: 98.334
+41600/69092	Loss: 97.652
+44800/69092	Loss: 97.892
+48000/69092	Loss: 97.527
+51200/69092	Loss: 97.728
+54400/69092	Loss: 97.826
+57600/69092	Loss: 97.310
+60800/69092	Loss: 97.911
+64000/69092	Loss: 98.249
+67200/69092	Loss: 98.853
+Training time 0:10:30.378191
+Epoch: 205 Average loss: 97.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 356)
+0/69092	Loss: 96.756
+3200/69092	Loss: 98.532
+6400/69092	Loss: 98.281
+9600/69092	Loss: 98.570
+12800/69092	Loss: 98.263
+16000/69092	Loss: 96.547
+19200/69092	Loss: 97.878
+22400/69092	Loss: 96.021
+25600/69092	Loss: 98.586
+28800/69092	Loss: 96.415
+32000/69092	Loss: 97.505
+35200/69092	Loss: 97.731
+38400/69092	Loss: 97.374
+41600/69092	Loss: 97.430
+44800/69092	Loss: 96.433
+48000/69092	Loss: 97.403
+51200/69092	Loss: 97.949
+54400/69092	Loss: 99.123
+57600/69092	Loss: 97.852
+60800/69092	Loss: 99.742
+64000/69092	Loss: 98.782
+67200/69092	Loss: 98.849
+Training time 0:10:51.129242
+Epoch: 206 Average loss: 97.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last' (iter 357)
+0/69092	Loss: 95.449
+3200/69092	Loss: 97.979
+6400/69092	Loss: 97.863
+9600/69092	Loss: 98.400
+12800/69092	Loss: 97.270
+16000/69092	Loss: 97.595
+19200/69092	Loss: 97.647
+22400/69092	Loss: 97.214
+25600/69092	Loss: 97.525
+28800/69092	Loss: 96.985
+32000/69092	Loss: 97.120
+35200/69092	Loss: 97.459
+38400/69092	Loss: 97.695
+41600/69092	Loss: 96.474
+44800/69092	Loss: 99.245
+48000/69092	Loss: 97.658
+51200/69092	Loss: 98.111
+54400/69092	Loss: 98.033
+57600/69092	Loss: 97.019
diff --git a/OAR.2073643.stderr b/OAR.2073643.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..8f70a76f45784adba8e6d01f48bc3e89cd128d8f
--- /dev/null
+++ b/OAR.2073643.stderr
@@ -0,0 +1,3 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+## OAR [2020-07-07 08:29:14] Job 2073643 KILLED ##
diff --git a/OAR.2073643.stdout b/OAR.2073643.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..c2c5585dee89bb259858bcc351f0268cffc42623
--- /dev/null
+++ b/OAR.2073643.stdout
@@ -0,0 +1,5103 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64_ls_40', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=40, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=80, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=40, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 788435
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last (iter 279)'
+0/69092	Loss: 90.062
+3200/69092	Loss: 92.127
+6400/69092	Loss: 93.724
+9600/69092	Loss: 93.963
+12800/69092	Loss: 94.650
+16000/69092	Loss: 94.306
+19200/69092	Loss: 94.823
+22400/69092	Loss: 93.715
+25600/69092	Loss: 95.173
+28800/69092	Loss: 95.067
+32000/69092	Loss: 95.303
+35200/69092	Loss: 94.709
+38400/69092	Loss: 94.902
+41600/69092	Loss: 92.377
+44800/69092	Loss: 95.477
+48000/69092	Loss: 94.952
+51200/69092	Loss: 95.302
+54400/69092	Loss: 94.206
+57600/69092	Loss: 94.081
+60800/69092	Loss: 95.543
+64000/69092	Loss: 95.627
+67200/69092	Loss: 95.776
+Training time 0:13:30.634241
+Epoch: 1 Average loss: 94.57
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 280)
+0/69092	Loss: 90.951
+3200/69092	Loss: 96.083
+6400/69092	Loss: 94.799
+9600/69092	Loss: 93.262
+12800/69092	Loss: 93.921
+16000/69092	Loss: 93.531
+19200/69092	Loss: 93.428
+22400/69092	Loss: 94.305
+25600/69092	Loss: 95.280
+28800/69092	Loss: 94.237
+32000/69092	Loss: 94.560
+35200/69092	Loss: 93.562
+38400/69092	Loss: 94.773
+41600/69092	Loss: 95.325
+44800/69092	Loss: 94.066
+48000/69092	Loss: 95.690
+51200/69092	Loss: 95.321
+54400/69092	Loss: 95.202
+57600/69092	Loss: 93.775
+60800/69092	Loss: 95.257
+64000/69092	Loss: 95.236
+67200/69092	Loss: 94.271
+Training time 0:10:22.101409
+Epoch: 2 Average loss: 94.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 281)
+0/69092	Loss: 97.683
+3200/69092	Loss: 92.747
+6400/69092	Loss: 93.986
+9600/69092	Loss: 94.415
+12800/69092	Loss: 95.132
+16000/69092	Loss: 93.981
+19200/69092	Loss: 92.975
+22400/69092	Loss: 94.128
+25600/69092	Loss: 95.040
+28800/69092	Loss: 93.717
+32000/69092	Loss: 95.277
+35200/69092	Loss: 93.803
+38400/69092	Loss: 94.774
+41600/69092	Loss: 95.887
+44800/69092	Loss: 93.361
+48000/69092	Loss: 94.360
+51200/69092	Loss: 93.718
+54400/69092	Loss: 94.478
+57600/69092	Loss: 95.977
+60800/69092	Loss: 94.555
+64000/69092	Loss: 94.732
+67200/69092	Loss: 95.300
+Training time 0:10:30.531983
+Epoch: 3 Average loss: 94.38
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 282)
+0/69092	Loss: 91.931
+3200/69092	Loss: 94.240
+6400/69092	Loss: 94.260
+9600/69092	Loss: 94.548
+12800/69092	Loss: 94.758
+16000/69092	Loss: 94.921
+19200/69092	Loss: 94.685
+22400/69092	Loss: 96.334
+25600/69092	Loss: 94.208
+28800/69092	Loss: 94.628
+32000/69092	Loss: 93.526
+35200/69092	Loss: 94.099
+38400/69092	Loss: 94.247
+41600/69092	Loss: 93.982
+44800/69092	Loss: 93.824
+48000/69092	Loss: 94.342
+51200/69092	Loss: 93.605
+54400/69092	Loss: 95.787
+57600/69092	Loss: 94.975
+60800/69092	Loss: 93.679
+64000/69092	Loss: 94.578
+67200/69092	Loss: 95.152
+Training time 0:10:29.827038
+Epoch: 4 Average loss: 94.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 283)
+0/69092	Loss: 90.517
+3200/69092	Loss: 93.376
+6400/69092	Loss: 94.892
+9600/69092	Loss: 94.142
+12800/69092	Loss: 95.824
+16000/69092	Loss: 94.210
+19200/69092	Loss: 93.727
+22400/69092	Loss: 94.493
+25600/69092	Loss: 94.132
+28800/69092	Loss: 94.704
+32000/69092	Loss: 93.185
+35200/69092	Loss: 95.027
+38400/69092	Loss: 94.719
+41600/69092	Loss: 93.959
+44800/69092	Loss: 95.454
+48000/69092	Loss: 95.132
+51200/69092	Loss: 94.695
+54400/69092	Loss: 95.315
+57600/69092	Loss: 95.112
+60800/69092	Loss: 93.908
+64000/69092	Loss: 94.693
+67200/69092	Loss: 95.416
+Training time 0:10:35.687181
+Epoch: 5 Average loss: 94.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 284)
+0/69092	Loss: 102.264
+3200/69092	Loss: 95.347
+6400/69092	Loss: 94.211
+9600/69092	Loss: 95.431
+12800/69092	Loss: 95.243
+16000/69092	Loss: 93.567
+19200/69092	Loss: 94.266
+22400/69092	Loss: 94.106
+25600/69092	Loss: 93.788
+28800/69092	Loss: 93.050
+32000/69092	Loss: 93.675
+35200/69092	Loss: 94.448
+38400/69092	Loss: 95.023
+41600/69092	Loss: 94.651
+44800/69092	Loss: 93.729
+48000/69092	Loss: 94.630
+51200/69092	Loss: 94.486
+54400/69092	Loss: 93.786
+57600/69092	Loss: 93.810
+60800/69092	Loss: 94.318
+64000/69092	Loss: 94.251
+67200/69092	Loss: 95.064
+Training time 0:10:58.632172
+Epoch: 6 Average loss: 94.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 285)
+0/69092	Loss: 89.557
+3200/69092	Loss: 93.906
+6400/69092	Loss: 94.836
+9600/69092	Loss: 93.274
+12800/69092	Loss: 95.897
+16000/69092	Loss: 96.075
+19200/69092	Loss: 93.992
+22400/69092	Loss: 93.822
+25600/69092	Loss: 95.243
+28800/69092	Loss: 95.421
+32000/69092	Loss: 93.787
+35200/69092	Loss: 94.358
+38400/69092	Loss: 94.404
+41600/69092	Loss: 93.337
+44800/69092	Loss: 95.039
+48000/69092	Loss: 93.211
+51200/69092	Loss: 94.632
+54400/69092	Loss: 94.891
+57600/69092	Loss: 94.976
+60800/69092	Loss: 93.462
+64000/69092	Loss: 94.408
+67200/69092	Loss: 94.039
+Training time 0:10:55.584807
+Epoch: 7 Average loss: 94.47
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 286)
+0/69092	Loss: 89.352
+3200/69092	Loss: 92.762
+6400/69092	Loss: 94.771
+9600/69092	Loss: 94.339
+12800/69092	Loss: 94.957
+16000/69092	Loss: 95.579
+19200/69092	Loss: 92.809
+22400/69092	Loss: 94.711
+25600/69092	Loss: 92.725
+28800/69092	Loss: 94.606
+32000/69092	Loss: 95.029
+35200/69092	Loss: 93.435
+38400/69092	Loss: 94.479
+41600/69092	Loss: 94.267
+44800/69092	Loss: 95.211
+48000/69092	Loss: 93.675
+51200/69092	Loss: 94.738
+54400/69092	Loss: 94.714
+57600/69092	Loss: 93.979
+60800/69092	Loss: 95.250
+64000/69092	Loss: 94.338
+67200/69092	Loss: 93.909
+Training time 0:10:48.878921
+Epoch: 8 Average loss: 94.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 287)
+0/69092	Loss: 90.621
+3200/69092	Loss: 94.090
+6400/69092	Loss: 94.171
+9600/69092	Loss: 95.123
+12800/69092	Loss: 95.265
+16000/69092	Loss: 94.843
+19200/69092	Loss: 92.990
+22400/69092	Loss: 94.017
+25600/69092	Loss: 94.433
+28800/69092	Loss: 93.810
+32000/69092	Loss: 94.122
+35200/69092	Loss: 93.692
+38400/69092	Loss: 94.331
+41600/69092	Loss: 93.690
+44800/69092	Loss: 95.067
+48000/69092	Loss: 95.660
+51200/69092	Loss: 95.810
+54400/69092	Loss: 95.727
+57600/69092	Loss: 95.705
+60800/69092	Loss: 94.158
+64000/69092	Loss: 93.369
+67200/69092	Loss: 92.778
+Training time 0:10:24.506099
+Epoch: 9 Average loss: 94.41
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 288)
+0/69092	Loss: 91.054
+3200/69092	Loss: 94.535
+6400/69092	Loss: 94.008
+9600/69092	Loss: 93.659
+12800/69092	Loss: 93.564
+16000/69092	Loss: 96.651
+19200/69092	Loss: 95.015
+22400/69092	Loss: 96.180
+25600/69092	Loss: 94.190
+28800/69092	Loss: 93.314
+32000/69092	Loss: 93.923
+35200/69092	Loss: 94.088
+38400/69092	Loss: 93.784
+41600/69092	Loss: 93.139
+44800/69092	Loss: 94.075
+48000/69092	Loss: 93.511
+51200/69092	Loss: 94.008
+54400/69092	Loss: 95.164
+57600/69092	Loss: 96.185
+60800/69092	Loss: 94.715
+64000/69092	Loss: 92.108
+67200/69092	Loss: 93.921
+Training time 0:10:31.554608
+Epoch: 10 Average loss: 94.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 289)
+0/69092	Loss: 93.204
+3200/69092	Loss: 94.995
+6400/69092	Loss: 94.490
+9600/69092	Loss: 94.443
+12800/69092	Loss: 94.003
+16000/69092	Loss: 94.537
+19200/69092	Loss: 93.581
+22400/69092	Loss: 94.067
+25600/69092	Loss: 92.671
+28800/69092	Loss: 93.422
+32000/69092	Loss: 94.332
+35200/69092	Loss: 94.320
+38400/69092	Loss: 93.178
+41600/69092	Loss: 95.623
+44800/69092	Loss: 94.529
+48000/69092	Loss: 94.550
+51200/69092	Loss: 93.908
+54400/69092	Loss: 95.316
+57600/69092	Loss: 92.934
+60800/69092	Loss: 94.673
+64000/69092	Loss: 93.934
+67200/69092	Loss: 95.314
+Training time 0:10:25.657683
+Epoch: 11 Average loss: 94.23
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 290)
+0/69092	Loss: 99.109
+3200/69092	Loss: 94.751
+6400/69092	Loss: 94.757
+9600/69092	Loss: 94.364
+12800/69092	Loss: 94.417
+16000/69092	Loss: 95.638
+19200/69092	Loss: 92.656
+22400/69092	Loss: 94.072
+25600/69092	Loss: 95.199
+28800/69092	Loss: 95.556
+32000/69092	Loss: 93.645
+35200/69092	Loss: 94.451
+38400/69092	Loss: 94.337
+41600/69092	Loss: 93.353
+44800/69092	Loss: 95.311
+48000/69092	Loss: 94.620
+51200/69092	Loss: 93.632
+54400/69092	Loss: 93.475
+57600/69092	Loss: 94.060
+60800/69092	Loss: 94.199
+64000/69092	Loss: 94.110
+67200/69092	Loss: 94.039
+Training time 0:10:49.936370
+Epoch: 12 Average loss: 94.36
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 291)
+0/69092	Loss: 102.801
+3200/69092	Loss: 94.418
+6400/69092	Loss: 96.271
+9600/69092	Loss: 94.013
+12800/69092	Loss: 94.636
+16000/69092	Loss: 95.640
+19200/69092	Loss: 94.740
+22400/69092	Loss: 93.915
+25600/69092	Loss: 93.762
+28800/69092	Loss: 93.424
+32000/69092	Loss: 94.651
+35200/69092	Loss: 94.494
+38400/69092	Loss: 93.475
+41600/69092	Loss: 95.305
+44800/69092	Loss: 93.138
+48000/69092	Loss: 93.580
+51200/69092	Loss: 94.607
+54400/69092	Loss: 93.940
+57600/69092	Loss: 93.794
+60800/69092	Loss: 91.554
+64000/69092	Loss: 94.278
+67200/69092	Loss: 94.153
+Training time 0:10:30.127103
+Epoch: 13 Average loss: 94.23
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 292)
+0/69092	Loss: 97.813
+3200/69092	Loss: 94.570
+6400/69092	Loss: 95.107
+9600/69092	Loss: 95.424
+12800/69092	Loss: 95.236
+16000/69092	Loss: 94.456
+19200/69092	Loss: 94.789
+22400/69092	Loss: 93.595
+25600/69092	Loss: 94.092
+28800/69092	Loss: 93.685
+32000/69092	Loss: 94.292
+35200/69092	Loss: 93.131
+38400/69092	Loss: 93.888
+41600/69092	Loss: 94.569
+44800/69092	Loss: 95.488
+48000/69092	Loss: 92.736
+51200/69092	Loss: 92.209
+54400/69092	Loss: 92.599
+57600/69092	Loss: 93.625
+60800/69092	Loss: 97.537
+64000/69092	Loss: 95.275
+67200/69092	Loss: 94.127
+Training time 0:10:20.730920
+Epoch: 14 Average loss: 94.32
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 293)
+0/69092	Loss: 92.929
+3200/69092	Loss: 93.241
+6400/69092	Loss: 93.330
+9600/69092	Loss: 94.250
+12800/69092	Loss: 94.991
+16000/69092	Loss: 95.790
+19200/69092	Loss: 94.748
+22400/69092	Loss: 94.071
+25600/69092	Loss: 93.631
+28800/69092	Loss: 94.931
+32000/69092	Loss: 95.609
+35200/69092	Loss: 95.746
+38400/69092	Loss: 95.259
+41600/69092	Loss: 93.472
+44800/69092	Loss: 94.526
+48000/69092	Loss: 93.954
+51200/69092	Loss: 93.832
+54400/69092	Loss: 94.496
+57600/69092	Loss: 93.355
+60800/69092	Loss: 93.306
+64000/69092	Loss: 94.493
+67200/69092	Loss: 93.216
+Training time 0:10:28.250658
+Epoch: 15 Average loss: 94.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 294)
+0/69092	Loss: 95.393
+3200/69092	Loss: 94.157
+6400/69092	Loss: 93.741
+9600/69092	Loss: 93.715
+12800/69092	Loss: 95.003
+16000/69092	Loss: 93.440
+19200/69092	Loss: 95.051
+22400/69092	Loss: 93.532
+25600/69092	Loss: 95.343
+28800/69092	Loss: 94.239
+32000/69092	Loss: 93.302
+35200/69092	Loss: 94.442
+38400/69092	Loss: 94.246
+41600/69092	Loss: 94.406
+44800/69092	Loss: 94.621
+48000/69092	Loss: 92.936
+51200/69092	Loss: 92.757
+54400/69092	Loss: 93.988
+57600/69092	Loss: 93.822
+60800/69092	Loss: 94.382
+64000/69092	Loss: 94.957
+67200/69092	Loss: 94.552
+Training time 0:10:29.129736
+Epoch: 16 Average loss: 94.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 295)
+0/69092	Loss: 86.593
+3200/69092	Loss: 95.287
+6400/69092	Loss: 94.160
+9600/69092	Loss: 93.123
+12800/69092	Loss: 92.906
+16000/69092	Loss: 94.603
+19200/69092	Loss: 94.526
+22400/69092	Loss: 93.770
+25600/69092	Loss: 96.173
+28800/69092	Loss: 94.388
+32000/69092	Loss: 94.031
+35200/69092	Loss: 93.333
+38400/69092	Loss: 94.892
+41600/69092	Loss: 94.177
+44800/69092	Loss: 94.670
+48000/69092	Loss: 93.633
+51200/69092	Loss: 93.732
+54400/69092	Loss: 93.265
+57600/69092	Loss: 94.181
+60800/69092	Loss: 94.458
+64000/69092	Loss: 93.650
+67200/69092	Loss: 95.634
+Training time 0:10:28.383342
+Epoch: 17 Average loss: 94.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 296)
+0/69092	Loss: 81.037
+3200/69092	Loss: 94.363
+6400/69092	Loss: 94.314
+9600/69092	Loss: 94.396
+12800/69092	Loss: 93.673
+16000/69092	Loss: 93.163
+19200/69092	Loss: 94.376
+22400/69092	Loss: 92.470
+25600/69092	Loss: 92.443
+28800/69092	Loss: 94.757
+32000/69092	Loss: 94.372
+35200/69092	Loss: 95.580
+38400/69092	Loss: 94.350
+41600/69092	Loss: 94.296
+44800/69092	Loss: 93.922
+48000/69092	Loss: 94.408
+51200/69092	Loss: 95.380
+54400/69092	Loss: 93.608
+57600/69092	Loss: 95.070
+60800/69092	Loss: 94.955
+64000/69092	Loss: 94.112
+67200/69092	Loss: 96.193
+Training time 0:10:38.745453
+Epoch: 18 Average loss: 94.28
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 297)
+0/69092	Loss: 93.908
+3200/69092	Loss: 94.368
+6400/69092	Loss: 94.409
+9600/69092	Loss: 95.082
+12800/69092	Loss: 93.833
+16000/69092	Loss: 94.199
+19200/69092	Loss: 94.719
+22400/69092	Loss: 94.627
+25600/69092	Loss: 94.982
+28800/69092	Loss: 93.910
+32000/69092	Loss: 92.852
+35200/69092	Loss: 93.515
+38400/69092	Loss: 93.511
+41600/69092	Loss: 94.768
+44800/69092	Loss: 93.140
+48000/69092	Loss: 94.372
+51200/69092	Loss: 94.120
+54400/69092	Loss: 94.566
+57600/69092	Loss: 94.570
+60800/69092	Loss: 95.180
+64000/69092	Loss: 93.900
+67200/69092	Loss: 94.121
+Training time 0:10:45.134890
+Epoch: 19 Average loss: 94.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 298)
+0/69092	Loss: 95.812
+3200/69092	Loss: 94.678
+6400/69092	Loss: 94.021
+9600/69092	Loss: 93.892
+12800/69092	Loss: 93.107
+16000/69092	Loss: 95.708
+19200/69092	Loss: 92.913
+22400/69092	Loss: 94.806
+25600/69092	Loss: 93.961
+28800/69092	Loss: 95.161
+32000/69092	Loss: 94.426
+35200/69092	Loss: 93.957
+38400/69092	Loss: 93.731
+41600/69092	Loss: 94.069
+44800/69092	Loss: 95.331
+48000/69092	Loss: 94.701
+51200/69092	Loss: 93.854
+54400/69092	Loss: 95.016
+57600/69092	Loss: 92.991
+60800/69092	Loss: 93.896
+64000/69092	Loss: 93.064
+67200/69092	Loss: 94.073
+Training time 0:11:00.403629
+Epoch: 20 Average loss: 94.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 299)
+0/69092	Loss: 89.588
+3200/69092	Loss: 93.278
+6400/69092	Loss: 96.235
+9600/69092	Loss: 93.222
+12800/69092	Loss: 93.654
+16000/69092	Loss: 94.987
+19200/69092	Loss: 94.971
+22400/69092	Loss: 93.417
+25600/69092	Loss: 94.479
+28800/69092	Loss: 93.525
+32000/69092	Loss: 94.055
+35200/69092	Loss: 93.564
+38400/69092	Loss: 95.036
+41600/69092	Loss: 95.032
+44800/69092	Loss: 93.298
+48000/69092	Loss: 93.432
+51200/69092	Loss: 94.703
+54400/69092	Loss: 93.462
+57600/69092	Loss: 93.451
+60800/69092	Loss: 94.250
+64000/69092	Loss: 94.008
+67200/69092	Loss: 94.224
+Training time 0:10:30.457194
+Epoch: 21 Average loss: 94.12
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 300)
+0/69092	Loss: 89.474
+3200/69092	Loss: 93.320
+6400/69092	Loss: 93.639
+9600/69092	Loss: 94.005
+12800/69092	Loss: 93.445
+16000/69092	Loss: 93.968
+19200/69092	Loss: 94.719
+22400/69092	Loss: 94.857
+25600/69092	Loss: 93.765
+28800/69092	Loss: 96.977
+32000/69092	Loss: 91.818
+35200/69092	Loss: 93.080
+38400/69092	Loss: 92.996
+41600/69092	Loss: 92.983
+44800/69092	Loss: 95.323
+48000/69092	Loss: 93.522
+51200/69092	Loss: 93.380
+54400/69092	Loss: 95.464
+57600/69092	Loss: 95.885
+60800/69092	Loss: 95.609
+64000/69092	Loss: 93.769
+67200/69092	Loss: 95.229
+Training time 0:10:49.630924
+Epoch: 22 Average loss: 94.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 301)
+0/69092	Loss: 96.493
+3200/69092	Loss: 94.153
+6400/69092	Loss: 93.156
+9600/69092	Loss: 94.911
+12800/69092	Loss: 94.657
+16000/69092	Loss: 94.565
+19200/69092	Loss: 92.726
+22400/69092	Loss: 94.688
+25600/69092	Loss: 94.343
+28800/69092	Loss: 93.823
+32000/69092	Loss: 95.017
+35200/69092	Loss: 94.691
+38400/69092	Loss: 94.541
+41600/69092	Loss: 95.187
+44800/69092	Loss: 93.248
+48000/69092	Loss: 94.871
+51200/69092	Loss: 93.162
+54400/69092	Loss: 92.747
+57600/69092	Loss: 92.467
+60800/69092	Loss: 95.027
+64000/69092	Loss: 95.520
+67200/69092	Loss: 93.740
+Training time 0:10:50.953666
+Epoch: 23 Average loss: 94.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 302)
+0/69092	Loss: 101.088
+3200/69092	Loss: 93.482
+6400/69092	Loss: 93.258
+9600/69092	Loss: 93.316
+12800/69092	Loss: 93.475
+16000/69092	Loss: 93.925
+19200/69092	Loss: 94.067
+22400/69092	Loss: 93.826
+25600/69092	Loss: 93.931
+28800/69092	Loss: 94.234
+32000/69092	Loss: 94.437
+35200/69092	Loss: 94.203
+38400/69092	Loss: 95.815
+41600/69092	Loss: 93.341
+44800/69092	Loss: 93.926
+48000/69092	Loss: 93.442
+51200/69092	Loss: 93.138
+54400/69092	Loss: 94.481
+57600/69092	Loss: 94.592
+60800/69092	Loss: 93.437
+64000/69092	Loss: 93.474
+67200/69092	Loss: 94.584
+Training time 0:10:30.408554
+Epoch: 24 Average loss: 94.01
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 303)
+0/69092	Loss: 100.640
+3200/69092	Loss: 94.266
+6400/69092	Loss: 94.227
+9600/69092	Loss: 93.327
+12800/69092	Loss: 93.505
+16000/69092	Loss: 94.949
+19200/69092	Loss: 95.621
+22400/69092	Loss: 94.061
+25600/69092	Loss: 93.607
+28800/69092	Loss: 93.687
+32000/69092	Loss: 93.864
+35200/69092	Loss: 94.900
+38400/69092	Loss: 94.223
+41600/69092	Loss: 95.471
+44800/69092	Loss: 93.960
+48000/69092	Loss: 95.435
+51200/69092	Loss: 92.648
+54400/69092	Loss: 94.453
+57600/69092	Loss: 94.473
+60800/69092	Loss: 92.275
+64000/69092	Loss: 94.242
+67200/69092	Loss: 94.453
+Training time 0:10:51.076592
+Epoch: 25 Average loss: 94.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 304)
+0/69092	Loss: 88.775
+3200/69092	Loss: 94.757
+6400/69092	Loss: 93.794
+9600/69092	Loss: 93.371
+12800/69092	Loss: 94.524
+16000/69092	Loss: 94.112
+19200/69092	Loss: 93.324
+22400/69092	Loss: 94.696
+25600/69092	Loss: 93.885
+28800/69092	Loss: 94.023
+32000/69092	Loss: 94.264
+35200/69092	Loss: 93.104
+38400/69092	Loss: 93.689
+41600/69092	Loss: 94.124
+44800/69092	Loss: 94.872
+48000/69092	Loss: 94.566
+51200/69092	Loss: 96.347
+54400/69092	Loss: 92.798
+57600/69092	Loss: 93.758
+60800/69092	Loss: 93.838
+64000/69092	Loss: 92.867
+67200/69092	Loss: 94.021
+Training time 0:10:40.206415
+Epoch: 26 Average loss: 94.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 305)
+0/69092	Loss: 92.354
+3200/69092	Loss: 94.390
+6400/69092	Loss: 94.257
+9600/69092	Loss: 93.907
+12800/69092	Loss: 93.558
+16000/69092	Loss: 93.990
+19200/69092	Loss: 95.038
+22400/69092	Loss: 96.045
+25600/69092	Loss: 94.059
+28800/69092	Loss: 93.922
+32000/69092	Loss: 93.534
+35200/69092	Loss: 93.713
+38400/69092	Loss: 95.056
+41600/69092	Loss: 93.655
+44800/69092	Loss: 94.967
+48000/69092	Loss: 92.187
+51200/69092	Loss: 93.460
+54400/69092	Loss: 94.512
+57600/69092	Loss: 95.157
+60800/69092	Loss: 93.564
+64000/69092	Loss: 93.379
+67200/69092	Loss: 93.080
+Training time 0:10:29.219139
+Epoch: 27 Average loss: 94.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 306)
+0/69092	Loss: 90.003
+3200/69092	Loss: 94.164
+6400/69092	Loss: 93.748
+9600/69092	Loss: 93.214
+12800/69092	Loss: 93.978
+16000/69092	Loss: 94.132
+19200/69092	Loss: 93.207
+22400/69092	Loss: 93.649
+25600/69092	Loss: 94.456
+28800/69092	Loss: 93.758
+32000/69092	Loss: 92.961
+35200/69092	Loss: 94.443
+38400/69092	Loss: 93.744
+41600/69092	Loss: 93.153
+44800/69092	Loss: 92.916
+48000/69092	Loss: 94.093
+51200/69092	Loss: 95.057
+54400/69092	Loss: 95.187
+57600/69092	Loss: 94.597
+60800/69092	Loss: 95.053
+64000/69092	Loss: 93.444
+67200/69092	Loss: 94.923
+Training time 0:10:26.627547
+Epoch: 28 Average loss: 94.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 307)
+0/69092	Loss: 100.771
+3200/69092	Loss: 94.660
+6400/69092	Loss: 93.754
+9600/69092	Loss: 93.956
+12800/69092	Loss: 94.563
+16000/69092	Loss: 95.127
+19200/69092	Loss: 94.366
+22400/69092	Loss: 93.047
+25600/69092	Loss: 93.726
+28800/69092	Loss: 94.213
+32000/69092	Loss: 93.763
+35200/69092	Loss: 93.387
+38400/69092	Loss: 95.023
+41600/69092	Loss: 93.503
+44800/69092	Loss: 93.875
+48000/69092	Loss: 92.791
+51200/69092	Loss: 92.249
+54400/69092	Loss: 93.682
+57600/69092	Loss: 94.508
+60800/69092	Loss: 95.796
+64000/69092	Loss: 94.746
+67200/69092	Loss: 93.809
+Training time 0:10:36.289573
+Epoch: 29 Average loss: 94.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 308)
+0/69092	Loss: 96.888
+3200/69092	Loss: 93.222
+6400/69092	Loss: 94.509
+9600/69092	Loss: 93.478
+12800/69092	Loss: 95.061
+16000/69092	Loss: 93.410
+19200/69092	Loss: 94.674
+22400/69092	Loss: 94.888
+25600/69092	Loss: 94.629
+28800/69092	Loss: 93.529
+32000/69092	Loss: 93.122
+35200/69092	Loss: 93.818
+38400/69092	Loss: 94.058
+41600/69092	Loss: 95.044
+44800/69092	Loss: 93.375
+48000/69092	Loss: 95.014
+51200/69092	Loss: 93.816
+54400/69092	Loss: 95.248
+57600/69092	Loss: 93.815
+60800/69092	Loss: 94.455
+64000/69092	Loss: 93.377
+67200/69092	Loss: 94.519
+Training time 0:10:54.788735
+Epoch: 30 Average loss: 94.12
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 309)
+0/69092	Loss: 103.957
+3200/69092	Loss: 94.313
+6400/69092	Loss: 94.209
+9600/69092	Loss: 93.350
+12800/69092	Loss: 93.228
+16000/69092	Loss: 93.007
+19200/69092	Loss: 95.048
+22400/69092	Loss: 93.818
+25600/69092	Loss: 94.668
+28800/69092	Loss: 94.130
+32000/69092	Loss: 93.457
+35200/69092	Loss: 92.966
+38400/69092	Loss: 94.326
+41600/69092	Loss: 93.678
+44800/69092	Loss: 94.249
+48000/69092	Loss: 94.661
+51200/69092	Loss: 94.184
+54400/69092	Loss: 93.789
+57600/69092	Loss: 94.010
+60800/69092	Loss: 93.693
+64000/69092	Loss: 92.614
+67200/69092	Loss: 95.820
+Training time 0:10:41.256937
+Epoch: 31 Average loss: 94.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 310)
+0/69092	Loss: 96.519
+3200/69092	Loss: 95.154
+6400/69092	Loss: 94.012
+9600/69092	Loss: 94.815
+12800/69092	Loss: 93.738
+16000/69092	Loss: 93.837
+19200/69092	Loss: 94.652
+22400/69092	Loss: 94.056
+25600/69092	Loss: 93.506
+28800/69092	Loss: 93.725
+32000/69092	Loss: 94.850
+35200/69092	Loss: 94.285
+38400/69092	Loss: 94.121
+41600/69092	Loss: 95.157
+44800/69092	Loss: 93.979
+48000/69092	Loss: 94.338
+51200/69092	Loss: 93.361
+54400/69092	Loss: 93.352
+57600/69092	Loss: 93.057
+60800/69092	Loss: 92.999
+64000/69092	Loss: 93.894
+67200/69092	Loss: 92.925
+Training time 0:10:27.068294
+Epoch: 32 Average loss: 94.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 311)
+0/69092	Loss: 93.470
+3200/69092	Loss: 93.513
+6400/69092	Loss: 93.260
+9600/69092	Loss: 93.967
+12800/69092	Loss: 92.515
+16000/69092	Loss: 95.400
+19200/69092	Loss: 93.748
+22400/69092	Loss: 93.285
+25600/69092	Loss: 93.450
+28800/69092	Loss: 94.270
+32000/69092	Loss: 93.409
+35200/69092	Loss: 94.455
+38400/69092	Loss: 93.518
+41600/69092	Loss: 93.216
+44800/69092	Loss: 93.972
+48000/69092	Loss: 94.182
+51200/69092	Loss: 95.269
+54400/69092	Loss: 94.576
+57600/69092	Loss: 95.072
+60800/69092	Loss: 93.496
+64000/69092	Loss: 93.759
+67200/69092	Loss: 94.463
+Training time 0:10:16.913002
+Epoch: 33 Average loss: 93.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 312)
+0/69092	Loss: 92.650
+3200/69092	Loss: 93.411
+6400/69092	Loss: 92.568
+9600/69092	Loss: 93.373
+12800/69092	Loss: 94.506
+16000/69092	Loss: 94.164
+19200/69092	Loss: 91.653
+22400/69092	Loss: 95.103
+25600/69092	Loss: 93.660
+28800/69092	Loss: 94.945
+32000/69092	Loss: 94.570
+35200/69092	Loss: 94.760
+38400/69092	Loss: 95.807
+41600/69092	Loss: 94.614
+44800/69092	Loss: 93.025
+48000/69092	Loss: 92.880
+51200/69092	Loss: 93.670
+54400/69092	Loss: 95.694
+57600/69092	Loss: 94.117
+60800/69092	Loss: 93.031
+64000/69092	Loss: 92.123
+67200/69092	Loss: 94.501
+Training time 0:10:25.478866
+Epoch: 34 Average loss: 93.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 313)
+0/69092	Loss: 80.142
+3200/69092	Loss: 93.381
+6400/69092	Loss: 93.474
+9600/69092	Loss: 94.070
+12800/69092	Loss: 96.848
+16000/69092	Loss: 94.279
+19200/69092	Loss: 93.618
+22400/69092	Loss: 95.734
+25600/69092	Loss: 93.517
+28800/69092	Loss: 93.299
+32000/69092	Loss: 95.076
+35200/69092	Loss: 94.460
+38400/69092	Loss: 93.393
+41600/69092	Loss: 94.109
+44800/69092	Loss: 93.366
+48000/69092	Loss: 93.402
+51200/69092	Loss: 94.606
+54400/69092	Loss: 93.081
+57600/69092	Loss: 93.782
+60800/69092	Loss: 93.678
+64000/69092	Loss: 92.884
+67200/69092	Loss: 92.180
+Training time 0:10:48.334792
+Epoch: 35 Average loss: 93.87
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 314)
+0/69092	Loss: 91.645
+3200/69092	Loss: 94.449
+6400/69092	Loss: 92.176
+9600/69092	Loss: 93.584
+12800/69092	Loss: 95.331
+16000/69092	Loss: 94.522
+19200/69092	Loss: 93.280
+22400/69092	Loss: 94.975
+25600/69092	Loss: 94.475
+28800/69092	Loss: 94.589
+32000/69092	Loss: 93.709
+35200/69092	Loss: 93.841
+38400/69092	Loss: 93.641
+41600/69092	Loss: 93.983
+44800/69092	Loss: 95.004
+48000/69092	Loss: 93.206
+51200/69092	Loss: 92.587
+54400/69092	Loss: 94.150
+57600/69092	Loss: 92.740
+60800/69092	Loss: 92.728
+64000/69092	Loss: 95.103
+67200/69092	Loss: 94.123
+Training time 0:10:48.713966
+Epoch: 36 Average loss: 93.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 315)
+0/69092	Loss: 87.068
+3200/69092	Loss: 94.678
+6400/69092	Loss: 94.100
+9600/69092	Loss: 95.393
+12800/69092	Loss: 94.393
+16000/69092	Loss: 92.247
+19200/69092	Loss: 93.782
+22400/69092	Loss: 95.070
+25600/69092	Loss: 92.727
+28800/69092	Loss: 94.301
+32000/69092	Loss: 95.089
+35200/69092	Loss: 93.218
+38400/69092	Loss: 92.831
+41600/69092	Loss: 92.293
+44800/69092	Loss: 93.800
+48000/69092	Loss: 93.725
+51200/69092	Loss: 94.635
+54400/69092	Loss: 94.867
+57600/69092	Loss: 94.279
+60800/69092	Loss: 93.998
+64000/69092	Loss: 93.703
+67200/69092	Loss: 94.096
+Training time 0:10:50.714192
+Epoch: 37 Average loss: 93.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 316)
+0/69092	Loss: 97.875
+3200/69092	Loss: 93.623
+6400/69092	Loss: 93.877
+9600/69092	Loss: 93.865
+12800/69092	Loss: 95.129
+16000/69092	Loss: 93.284
+19200/69092	Loss: 93.721
+22400/69092	Loss: 93.877
+25600/69092	Loss: 93.348
+28800/69092	Loss: 94.354
+32000/69092	Loss: 93.045
+35200/69092	Loss: 94.670
+38400/69092	Loss: 93.021
+41600/69092	Loss: 93.430
+44800/69092	Loss: 93.097
+48000/69092	Loss: 92.507
+51200/69092	Loss: 94.753
+54400/69092	Loss: 93.890
+57600/69092	Loss: 95.244
+60800/69092	Loss: 95.188
+64000/69092	Loss: 93.751
+67200/69092	Loss: 94.579
+Training time 0:10:40.885305
+Epoch: 38 Average loss: 93.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 317)
+0/69092	Loss: 88.424
+3200/69092	Loss: 94.248
+6400/69092	Loss: 94.151
+9600/69092	Loss: 93.240
+12800/69092	Loss: 93.187
+16000/69092	Loss: 91.476
+19200/69092	Loss: 92.942
+22400/69092	Loss: 93.945
+25600/69092	Loss: 93.531
+28800/69092	Loss: 92.651
+32000/69092	Loss: 94.060
+35200/69092	Loss: 94.553
+38400/69092	Loss: 93.318
+41600/69092	Loss: 94.657
+44800/69092	Loss: 94.166
+48000/69092	Loss: 94.787
+51200/69092	Loss: 94.678
+54400/69092	Loss: 93.087
+57600/69092	Loss: 94.456
+60800/69092	Loss: 94.053
+64000/69092	Loss: 93.648
+67200/69092	Loss: 94.813
+Training time 0:10:47.817993
+Epoch: 39 Average loss: 93.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 318)
+0/69092	Loss: 94.965
+3200/69092	Loss: 94.969
+6400/69092	Loss: 93.172
+9600/69092	Loss: 94.174
+12800/69092	Loss: 94.615
+16000/69092	Loss: 93.682
+19200/69092	Loss: 93.186
+22400/69092	Loss: 93.061
+25600/69092	Loss: 94.124
+28800/69092	Loss: 92.944
+32000/69092	Loss: 94.999
+35200/69092	Loss: 93.597
+38400/69092	Loss: 94.263
+41600/69092	Loss: 94.084
+44800/69092	Loss: 95.346
+48000/69092	Loss: 93.892
+51200/69092	Loss: 91.671
+54400/69092	Loss: 95.098
+57600/69092	Loss: 93.045
+60800/69092	Loss: 93.489
+64000/69092	Loss: 93.430
+67200/69092	Loss: 93.228
+Training time 0:10:32.870865
+Epoch: 40 Average loss: 93.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 319)
+0/69092	Loss: 86.917
+3200/69092	Loss: 93.715
+6400/69092	Loss: 93.626
+9600/69092	Loss: 94.910
+12800/69092	Loss: 94.522
+16000/69092	Loss: 93.942
+19200/69092	Loss: 93.057
+22400/69092	Loss: 94.004
+25600/69092	Loss: 94.994
+28800/69092	Loss: 94.258
+32000/69092	Loss: 93.649
+35200/69092	Loss: 95.653
+38400/69092	Loss: 91.878
+41600/69092	Loss: 94.769
+44800/69092	Loss: 94.468
+48000/69092	Loss: 93.675
+51200/69092	Loss: 93.398
+54400/69092	Loss: 94.706
+57600/69092	Loss: 93.085
+60800/69092	Loss: 94.529
+64000/69092	Loss: 93.158
+67200/69092	Loss: 93.161
+Training time 0:10:43.638691
+Epoch: 41 Average loss: 93.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 320)
+0/69092	Loss: 87.768
+3200/69092	Loss: 94.699
+6400/69092	Loss: 93.527
+9600/69092	Loss: 94.223
+12800/69092	Loss: 93.342
+16000/69092	Loss: 92.859
+19200/69092	Loss: 93.052
+22400/69092	Loss: 94.519
+25600/69092	Loss: 93.413
+28800/69092	Loss: 93.617
+32000/69092	Loss: 93.733
+35200/69092	Loss: 94.451
+38400/69092	Loss: 94.345
+41600/69092	Loss: 94.210
+44800/69092	Loss: 94.269
+48000/69092	Loss: 94.442
+51200/69092	Loss: 93.162
+54400/69092	Loss: 93.156
+57600/69092	Loss: 92.932
+60800/69092	Loss: 93.738
+64000/69092	Loss: 93.713
+67200/69092	Loss: 95.445
+Training time 0:10:32.000321
+Epoch: 42 Average loss: 93.87
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 321)
+0/69092	Loss: 88.507
+3200/69092	Loss: 92.841
+6400/69092	Loss: 92.975
+9600/69092	Loss: 94.405
+12800/69092	Loss: 94.209
+16000/69092	Loss: 93.111
+19200/69092	Loss: 95.354
+22400/69092	Loss: 93.674
+25600/69092	Loss: 94.043
+28800/69092	Loss: 92.929
+32000/69092	Loss: 93.857
+35200/69092	Loss: 95.059
+38400/69092	Loss: 93.693
+41600/69092	Loss: 93.454
+44800/69092	Loss: 93.999
+48000/69092	Loss: 93.539
+51200/69092	Loss: 93.027
+54400/69092	Loss: 93.221
+57600/69092	Loss: 92.859
+60800/69092	Loss: 94.803
+64000/69092	Loss: 94.403
+67200/69092	Loss: 94.374
+Training time 0:10:44.552921
+Epoch: 43 Average loss: 93.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 322)
+0/69092	Loss: 107.069
+3200/69092	Loss: 94.490
+6400/69092	Loss: 93.673
+9600/69092	Loss: 91.984
+12800/69092	Loss: 94.495
+16000/69092	Loss: 93.666
+19200/69092	Loss: 93.649
+22400/69092	Loss: 94.771
+25600/69092	Loss: 95.232
+28800/69092	Loss: 94.001
+32000/69092	Loss: 95.673
+35200/69092	Loss: 94.528
+38400/69092	Loss: 94.192
+41600/69092	Loss: 92.761
+44800/69092	Loss: 93.199
+48000/69092	Loss: 94.364
+51200/69092	Loss: 94.319
+54400/69092	Loss: 95.102
+57600/69092	Loss: 93.310
+60800/69092	Loss: 93.831
+64000/69092	Loss: 93.343
+67200/69092	Loss: 92.768
+Training time 0:10:28.554288
+Epoch: 44 Average loss: 93.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 323)
+0/69092	Loss: 93.793
+3200/69092	Loss: 93.803
+6400/69092	Loss: 94.286
+9600/69092	Loss: 93.879
+12800/69092	Loss: 93.531
+16000/69092	Loss: 93.348
+19200/69092	Loss: 92.392
+22400/69092	Loss: 93.632
+25600/69092	Loss: 94.094
+28800/69092	Loss: 92.591
+32000/69092	Loss: 94.115
+35200/69092	Loss: 94.448
+38400/69092	Loss: 93.824
+41600/69092	Loss: 95.941
+44800/69092	Loss: 93.069
+48000/69092	Loss: 93.786
+51200/69092	Loss: 95.296
+54400/69092	Loss: 94.012
+57600/69092	Loss: 93.662
+60800/69092	Loss: 94.884
+64000/69092	Loss: 93.442
+67200/69092	Loss: 93.690
+Training time 0:10:36.744010
+Epoch: 45 Average loss: 93.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 324)
+0/69092	Loss: 94.660
+3200/69092	Loss: 93.649
+6400/69092	Loss: 94.423
+9600/69092	Loss: 94.346
+12800/69092	Loss: 93.043
+16000/69092	Loss: 93.049
+19200/69092	Loss: 94.619
+22400/69092	Loss: 93.491
+25600/69092	Loss: 94.080
+28800/69092	Loss: 94.317
+32000/69092	Loss: 92.625
+35200/69092	Loss: 95.222
+38400/69092	Loss: 93.880
+41600/69092	Loss: 94.808
+44800/69092	Loss: 92.622
+48000/69092	Loss: 95.024
+51200/69092	Loss: 94.033
+54400/69092	Loss: 93.735
+57600/69092	Loss: 93.349
+60800/69092	Loss: 93.479
+64000/69092	Loss: 92.826
+67200/69092	Loss: 93.137
+Training time 0:10:43.670530
+Epoch: 46 Average loss: 93.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 325)
+0/69092	Loss: 98.125
+3200/69092	Loss: 94.271
+6400/69092	Loss: 94.287
+9600/69092	Loss: 92.739
+12800/69092	Loss: 92.710
+16000/69092	Loss: 93.411
+19200/69092	Loss: 93.016
+22400/69092	Loss: 94.499
+25600/69092	Loss: 93.442
+28800/69092	Loss: 94.471
+32000/69092	Loss: 92.853
+35200/69092	Loss: 92.048
+38400/69092	Loss: 95.092
+41600/69092	Loss: 95.678
+44800/69092	Loss: 94.217
+48000/69092	Loss: 93.141
+51200/69092	Loss: 94.403
+54400/69092	Loss: 92.884
+57600/69092	Loss: 94.682
+60800/69092	Loss: 93.126
+64000/69092	Loss: 96.204
+67200/69092	Loss: 95.518
+Training time 0:10:43.610951
+Epoch: 47 Average loss: 93.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 326)
+0/69092	Loss: 87.553
+3200/69092	Loss: 94.290
+6400/69092	Loss: 93.089
+9600/69092	Loss: 92.226
+12800/69092	Loss: 92.421
+16000/69092	Loss: 93.151
+19200/69092	Loss: 94.758
+22400/69092	Loss: 94.134
+25600/69092	Loss: 94.610
+28800/69092	Loss: 94.296
+32000/69092	Loss: 94.332
+35200/69092	Loss: 93.665
+38400/69092	Loss: 92.983
+41600/69092	Loss: 94.154
+44800/69092	Loss: 93.543
+48000/69092	Loss: 93.819
+51200/69092	Loss: 93.420
+54400/69092	Loss: 94.570
+57600/69092	Loss: 94.479
+60800/69092	Loss: 94.079
+64000/69092	Loss: 94.093
+67200/69092	Loss: 94.628
+Training time 0:11:11.709011
+Epoch: 48 Average loss: 93.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 327)
+0/69092	Loss: 104.280
+3200/69092	Loss: 93.718
+6400/69092	Loss: 93.072
+9600/69092	Loss: 93.980
+12800/69092	Loss: 93.250
+16000/69092	Loss: 92.617
+19200/69092	Loss: 93.370
+22400/69092	Loss: 94.072
+25600/69092	Loss: 92.757
+28800/69092	Loss: 93.939
+32000/69092	Loss: 93.351
+35200/69092	Loss: 94.774
+38400/69092	Loss: 94.409
+41600/69092	Loss: 95.391
+44800/69092	Loss: 94.891
+48000/69092	Loss: 93.988
+51200/69092	Loss: 92.940
+54400/69092	Loss: 94.364
+57600/69092	Loss: 92.687
+60800/69092	Loss: 93.910
+64000/69092	Loss: 93.571
+67200/69092	Loss: 93.841
+Training time 0:10:46.446267
+Epoch: 49 Average loss: 93.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 328)
+0/69092	Loss: 85.613
+3200/69092	Loss: 92.660
+6400/69092	Loss: 91.070
+9600/69092	Loss: 93.964
+12800/69092	Loss: 94.087
+16000/69092	Loss: 94.567
+19200/69092	Loss: 92.924
+22400/69092	Loss: 94.953
+25600/69092	Loss: 94.798
+28800/69092	Loss: 94.329
+32000/69092	Loss: 94.662
+35200/69092	Loss: 92.155
+38400/69092	Loss: 93.715
+41600/69092	Loss: 94.913
+44800/69092	Loss: 94.578
+48000/69092	Loss: 93.348
+51200/69092	Loss: 92.859
+54400/69092	Loss: 95.280
+57600/69092	Loss: 93.593
+60800/69092	Loss: 93.226
+64000/69092	Loss: 93.532
+67200/69092	Loss: 93.291
+Training time 0:10:20.887831
+Epoch: 50 Average loss: 93.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 329)
+0/69092	Loss: 90.140
+3200/69092	Loss: 93.856
+6400/69092	Loss: 94.237
+9600/69092	Loss: 94.275
+12800/69092	Loss: 92.595
+16000/69092	Loss: 93.652
+19200/69092	Loss: 93.164
+22400/69092	Loss: 94.560
+25600/69092	Loss: 94.025
+28800/69092	Loss: 94.527
+32000/69092	Loss: 94.459
+35200/69092	Loss: 93.232
+38400/69092	Loss: 93.240
+41600/69092	Loss: 93.255
+44800/69092	Loss: 92.832
+48000/69092	Loss: 94.889
+51200/69092	Loss: 93.614
+54400/69092	Loss: 93.460
+57600/69092	Loss: 94.807
+60800/69092	Loss: 92.929
+64000/69092	Loss: 94.662
+67200/69092	Loss: 92.950
+Training time 0:10:44.235536
+Epoch: 51 Average loss: 93.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 330)
+0/69092	Loss: 104.381
+3200/69092	Loss: 93.802
+6400/69092	Loss: 93.638
+9600/69092	Loss: 95.066
+12800/69092	Loss: 93.497
+16000/69092	Loss: 93.339
+19200/69092	Loss: 94.026
+22400/69092	Loss: 94.118
+25600/69092	Loss: 93.668
+28800/69092	Loss: 92.626
+32000/69092	Loss: 93.066
+35200/69092	Loss: 93.379
+38400/69092	Loss: 93.780
+41600/69092	Loss: 93.851
+44800/69092	Loss: 93.368
+48000/69092	Loss: 94.458
+51200/69092	Loss: 95.296
+54400/69092	Loss: 92.985
+57600/69092	Loss: 92.921
+60800/69092	Loss: 95.247
+64000/69092	Loss: 93.265
+67200/69092	Loss: 93.007
+Training time 0:10:25.267321
+Epoch: 52 Average loss: 93.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 331)
+0/69092	Loss: 94.611
+3200/69092	Loss: 94.682
+6400/69092	Loss: 92.591
+9600/69092	Loss: 93.942
+12800/69092	Loss: 93.096
+16000/69092	Loss: 94.815
+19200/69092	Loss: 93.033
+22400/69092	Loss: 93.299
+25600/69092	Loss: 94.855
+28800/69092	Loss: 93.325
+32000/69092	Loss: 94.892
+35200/69092	Loss: 93.945
+38400/69092	Loss: 93.738
+41600/69092	Loss: 92.569
+44800/69092	Loss: 93.935
+48000/69092	Loss: 93.047
+51200/69092	Loss: 94.012
+54400/69092	Loss: 93.767
+57600/69092	Loss: 92.217
+60800/69092	Loss: 93.283
+64000/69092	Loss: 93.440
+67200/69092	Loss: 92.007
+Training time 0:11:12.081660
+Epoch: 53 Average loss: 93.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 332)
+0/69092	Loss: 91.799
+3200/69092	Loss: 94.342
+6400/69092	Loss: 92.949
+9600/69092	Loss: 94.042
+12800/69092	Loss: 92.989
+16000/69092	Loss: 93.149
+19200/69092	Loss: 93.480
+22400/69092	Loss: 93.612
+25600/69092	Loss: 93.186
+28800/69092	Loss: 92.968
+32000/69092	Loss: 95.336
+35200/69092	Loss: 93.970
+38400/69092	Loss: 93.371
+41600/69092	Loss: 94.509
+44800/69092	Loss: 93.293
+48000/69092	Loss: 95.765
+51200/69092	Loss: 93.389
+54400/69092	Loss: 94.413
+57600/69092	Loss: 93.011
+60800/69092	Loss: 94.563
+64000/69092	Loss: 95.267
+67200/69092	Loss: 93.826
+Training time 0:10:15.713979
+Epoch: 54 Average loss: 93.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 333)
+0/69092	Loss: 82.821
+3200/69092	Loss: 92.179
+6400/69092	Loss: 94.134
+9600/69092	Loss: 95.103
+12800/69092	Loss: 93.233
+16000/69092	Loss: 93.716
+19200/69092	Loss: 95.101
+22400/69092	Loss: 93.786
+25600/69092	Loss: 92.941
+28800/69092	Loss: 94.624
+32000/69092	Loss: 93.407
+35200/69092	Loss: 93.867
+38400/69092	Loss: 94.004
+41600/69092	Loss: 93.934
+44800/69092	Loss: 92.560
+48000/69092	Loss: 93.935
+51200/69092	Loss: 92.927
+54400/69092	Loss: 93.604
+57600/69092	Loss: 93.230
+60800/69092	Loss: 92.845
+64000/69092	Loss: 94.115
+67200/69092	Loss: 95.146
+Training time 0:10:46.281093
+Epoch: 55 Average loss: 93.71
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 334)
+0/69092	Loss: 83.000
+3200/69092	Loss: 94.618
+6400/69092	Loss: 93.545
+9600/69092	Loss: 93.158
+12800/69092	Loss: 92.242
+16000/69092	Loss: 94.265
+19200/69092	Loss: 92.946
+22400/69092	Loss: 93.535
+25600/69092	Loss: 93.044
+28800/69092	Loss: 93.854
+32000/69092	Loss: 93.857
+35200/69092	Loss: 94.083
+38400/69092	Loss: 93.601
+41600/69092	Loss: 94.777
+44800/69092	Loss: 94.328
+48000/69092	Loss: 92.966
+51200/69092	Loss: 94.225
+54400/69092	Loss: 92.348
+57600/69092	Loss: 93.390
+60800/69092	Loss: 93.468
+64000/69092	Loss: 94.404
+67200/69092	Loss: 92.891
+Training time 0:10:27.672323
+Epoch: 56 Average loss: 93.59
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 335)
+0/69092	Loss: 95.782
+3200/69092	Loss: 93.675
+6400/69092	Loss: 94.183
+9600/69092	Loss: 93.289
+12800/69092	Loss: 93.912
+16000/69092	Loss: 93.555
+19200/69092	Loss: 93.607
+22400/69092	Loss: 94.599
+25600/69092	Loss: 93.778
+28800/69092	Loss: 92.169
+32000/69092	Loss: 93.203
+35200/69092	Loss: 92.976
+38400/69092	Loss: 93.974
+41600/69092	Loss: 92.062
+44800/69092	Loss: 94.843
+48000/69092	Loss: 92.731
+51200/69092	Loss: 94.358
+54400/69092	Loss: 92.918
+57600/69092	Loss: 93.464
+60800/69092	Loss: 93.956
+64000/69092	Loss: 94.787
+67200/69092	Loss: 93.464
+Training time 0:10:47.121286
+Epoch: 57 Average loss: 93.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 336)
+0/69092	Loss: 90.839
+3200/69092	Loss: 94.247
+6400/69092	Loss: 94.569
+9600/69092	Loss: 93.034
+12800/69092	Loss: 91.728
+16000/69092	Loss: 93.733
+19200/69092	Loss: 92.902
+22400/69092	Loss: 93.387
+25600/69092	Loss: 93.770
+28800/69092	Loss: 95.099
+32000/69092	Loss: 94.297
+35200/69092	Loss: 94.988
+38400/69092	Loss: 91.945
+41600/69092	Loss: 94.340
+44800/69092	Loss: 93.725
+48000/69092	Loss: 92.993
+51200/69092	Loss: 94.025
+54400/69092	Loss: 94.224
+57600/69092	Loss: 94.774
+60800/69092	Loss: 92.468
+64000/69092	Loss: 92.612
+67200/69092	Loss: 93.712
+Training time 0:10:53.274171
+Epoch: 58 Average loss: 93.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 337)
+0/69092	Loss: 103.451
+3200/69092	Loss: 92.769
+6400/69092	Loss: 94.309
+9600/69092	Loss: 93.778
+12800/69092	Loss: 92.876
+16000/69092	Loss: 92.994
+19200/69092	Loss: 92.498
+22400/69092	Loss: 94.322
+25600/69092	Loss: 93.830
+28800/69092	Loss: 93.148
+32000/69092	Loss: 93.398
+35200/69092	Loss: 93.967
+38400/69092	Loss: 92.806
+41600/69092	Loss: 94.089
+44800/69092	Loss: 93.826
+48000/69092	Loss: 93.341
+51200/69092	Loss: 94.301
+54400/69092	Loss: 92.928
+57600/69092	Loss: 94.290
+60800/69092	Loss: 93.169
+64000/69092	Loss: 93.868
+67200/69092	Loss: 92.297
+Training time 0:10:47.736382
+Epoch: 59 Average loss: 93.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 338)
+0/69092	Loss: 93.654
+3200/69092	Loss: 93.087
+6400/69092	Loss: 94.411
+9600/69092	Loss: 93.600
+12800/69092	Loss: 94.434
+16000/69092	Loss: 92.525
+19200/69092	Loss: 93.344
+22400/69092	Loss: 95.188
+25600/69092	Loss: 95.582
+28800/69092	Loss: 94.093
+32000/69092	Loss: 93.263
+35200/69092	Loss: 92.677
+38400/69092	Loss: 94.232
+41600/69092	Loss: 93.526
+44800/69092	Loss: 92.630
+48000/69092	Loss: 93.196
+51200/69092	Loss: 92.544
+54400/69092	Loss: 93.112
+57600/69092	Loss: 94.689
+60800/69092	Loss: 93.489
+64000/69092	Loss: 93.710
+67200/69092	Loss: 92.706
+Training time 0:10:28.966380
+Epoch: 60 Average loss: 93.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 339)
+0/69092	Loss: 78.740
+3200/69092	Loss: 93.480
+6400/69092	Loss: 93.314
+9600/69092	Loss: 94.021
+12800/69092	Loss: 94.114
+16000/69092	Loss: 93.242
+19200/69092	Loss: 93.225
+22400/69092	Loss: 94.696
+25600/69092	Loss: 92.980
+28800/69092	Loss: 91.839
+32000/69092	Loss: 92.788
+35200/69092	Loss: 93.778
+38400/69092	Loss: 93.517
+41600/69092	Loss: 93.107
+44800/69092	Loss: 93.467
+48000/69092	Loss: 93.032
+51200/69092	Loss: 93.623
+54400/69092	Loss: 94.729
+57600/69092	Loss: 94.084
+60800/69092	Loss: 93.136
+64000/69092	Loss: 93.954
+67200/69092	Loss: 95.566
+Training time 0:10:43.183355
+Epoch: 61 Average loss: 93.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 340)
+0/69092	Loss: 91.613
+3200/69092	Loss: 93.946
+6400/69092	Loss: 92.747
+9600/69092	Loss: 93.448
+12800/69092	Loss: 93.313
+16000/69092	Loss: 93.559
+19200/69092	Loss: 93.056
+22400/69092	Loss: 93.715
+25600/69092	Loss: 92.430
+28800/69092	Loss: 93.267
+32000/69092	Loss: 95.508
+35200/69092	Loss: 93.233
+38400/69092	Loss: 94.355
+41600/69092	Loss: 95.457
+44800/69092	Loss: 94.100
+48000/69092	Loss: 92.964
+51200/69092	Loss: 94.300
+54400/69092	Loss: 93.156
+57600/69092	Loss: 94.397
+60800/69092	Loss: 94.424
+64000/69092	Loss: 94.050
+67200/69092	Loss: 91.892
+Training time 0:10:45.744916
+Epoch: 62 Average loss: 93.69
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 341)
+0/69092	Loss: 97.121
+3200/69092	Loss: 93.754
+6400/69092	Loss: 93.947
+9600/69092	Loss: 95.104
+12800/69092	Loss: 94.653
+16000/69092	Loss: 92.718
+19200/69092	Loss: 93.451
+22400/69092	Loss: 93.326
+25600/69092	Loss: 93.938
+28800/69092	Loss: 93.909
+32000/69092	Loss: 93.116
+35200/69092	Loss: 92.642
+38400/69092	Loss: 94.566
+41600/69092	Loss: 92.150
+44800/69092	Loss: 92.594
+48000/69092	Loss: 93.509
+51200/69092	Loss: 92.714
+54400/69092	Loss: 91.746
+57600/69092	Loss: 92.485
+60800/69092	Loss: 94.249
+64000/69092	Loss: 94.711
+67200/69092	Loss: 95.766
+Training time 0:10:18.249303
+Epoch: 63 Average loss: 93.59
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 342)
+0/69092	Loss: 91.275
+3200/69092	Loss: 93.367
+6400/69092	Loss: 92.896
+9600/69092	Loss: 94.132
+12800/69092	Loss: 93.990
+16000/69092	Loss: 95.226
+19200/69092	Loss: 93.667
+22400/69092	Loss: 93.977
+25600/69092	Loss: 93.667
+28800/69092	Loss: 93.275
+32000/69092	Loss: 93.369
+35200/69092	Loss: 94.473
+38400/69092	Loss: 93.676
+41600/69092	Loss: 92.817
+44800/69092	Loss: 93.642
+48000/69092	Loss: 92.691
+51200/69092	Loss: 93.612
+54400/69092	Loss: 93.220
+57600/69092	Loss: 93.291
+60800/69092	Loss: 93.362
+64000/69092	Loss: 93.798
+67200/69092	Loss: 94.131
+Training time 0:11:04.557626
+Epoch: 64 Average loss: 93.59
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 343)
+0/69092	Loss: 90.220
+3200/69092	Loss: 93.183
+6400/69092	Loss: 93.528
+9600/69092	Loss: 93.657
+12800/69092	Loss: 93.460
+16000/69092	Loss: 93.907
+19200/69092	Loss: 93.063
+22400/69092	Loss: 94.296
+25600/69092	Loss: 94.204
+28800/69092	Loss: 92.946
+32000/69092	Loss: 93.969
+35200/69092	Loss: 93.280
+38400/69092	Loss: 93.673
+41600/69092	Loss: 93.735
+44800/69092	Loss: 92.797
+48000/69092	Loss: 93.097
+51200/69092	Loss: 93.747
+54400/69092	Loss: 95.499
+57600/69092	Loss: 94.483
+60800/69092	Loss: 93.581
+64000/69092	Loss: 94.156
+67200/69092	Loss: 93.294
+Training time 0:10:48.512914
+Epoch: 65 Average loss: 93.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 344)
+0/69092	Loss: 90.981
+3200/69092	Loss: 94.630
+6400/69092	Loss: 93.270
+9600/69092	Loss: 93.398
+12800/69092	Loss: 92.333
+16000/69092	Loss: 93.434
+19200/69092	Loss: 93.049
+22400/69092	Loss: 94.175
+25600/69092	Loss: 94.450
+28800/69092	Loss: 93.623
+32000/69092	Loss: 92.720
+35200/69092	Loss: 94.464
+38400/69092	Loss: 92.684
+41600/69092	Loss: 94.409
+44800/69092	Loss: 93.357
+48000/69092	Loss: 92.763
+51200/69092	Loss: 93.720
+54400/69092	Loss: 93.593
+57600/69092	Loss: 95.032
+60800/69092	Loss: 92.524
+64000/69092	Loss: 93.596
+67200/69092	Loss: 94.064
+Training time 0:10:17.124985
+Epoch: 66 Average loss: 93.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 345)
+0/69092	Loss: 90.782
+3200/69092	Loss: 94.750
+6400/69092	Loss: 92.050
+9600/69092	Loss: 94.678
+12800/69092	Loss: 94.304
+16000/69092	Loss: 93.228
+19200/69092	Loss: 93.369
+22400/69092	Loss: 93.253
+25600/69092	Loss: 93.266
+28800/69092	Loss: 95.673
+32000/69092	Loss: 94.099
+35200/69092	Loss: 93.299
+38400/69092	Loss: 94.528
+41600/69092	Loss: 93.298
+44800/69092	Loss: 93.503
+48000/69092	Loss: 93.527
+51200/69092	Loss: 92.007
+54400/69092	Loss: 92.966
+57600/69092	Loss: 92.457
+60800/69092	Loss: 93.290
+64000/69092	Loss: 92.631
+67200/69092	Loss: 93.215
+Training time 0:10:44.966047
+Epoch: 67 Average loss: 93.54
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 346)
+0/69092	Loss: 98.519
+3200/69092	Loss: 93.010
+6400/69092	Loss: 92.382
+9600/69092	Loss: 95.853
+12800/69092	Loss: 92.674
+16000/69092	Loss: 93.336
+19200/69092	Loss: 94.292
+22400/69092	Loss: 92.968
+25600/69092	Loss: 94.035
+28800/69092	Loss: 93.809
+32000/69092	Loss: 93.663
+35200/69092	Loss: 93.719
+38400/69092	Loss: 93.585
+41600/69092	Loss: 94.165
+44800/69092	Loss: 92.985
+48000/69092	Loss: 93.080
+51200/69092	Loss: 93.261
+54400/69092	Loss: 93.419
+57600/69092	Loss: 92.706
+60800/69092	Loss: 94.022
+64000/69092	Loss: 94.465
+67200/69092	Loss: 92.091
+Training time 0:10:18.947311
+Epoch: 68 Average loss: 93.53
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 347)
+0/69092	Loss: 91.965
+3200/69092	Loss: 94.526
+6400/69092	Loss: 93.082
+9600/69092	Loss: 92.697
+12800/69092	Loss: 94.063
+16000/69092	Loss: 93.788
+19200/69092	Loss: 92.797
+22400/69092	Loss: 93.205
+25600/69092	Loss: 94.681
+28800/69092	Loss: 92.913
+32000/69092	Loss: 94.804
+35200/69092	Loss: 92.840
+38400/69092	Loss: 94.924
+41600/69092	Loss: 92.809
+44800/69092	Loss: 93.386
+48000/69092	Loss: 94.458
+51200/69092	Loss: 93.294
+54400/69092	Loss: 93.781
+57600/69092	Loss: 93.429
+60800/69092	Loss: 93.449
+64000/69092	Loss: 93.976
+67200/69092	Loss: 93.203
+Training time 0:10:51.205243
+Epoch: 69 Average loss: 93.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 348)
+0/69092	Loss: 104.108
+3200/69092	Loss: 92.725
+6400/69092	Loss: 93.064
+9600/69092	Loss: 92.727
+12800/69092	Loss: 93.658
+16000/69092	Loss: 93.335
+19200/69092	Loss: 93.741
+22400/69092	Loss: 93.193
+25600/69092	Loss: 94.980
+28800/69092	Loss: 93.892
+32000/69092	Loss: 94.744
+35200/69092	Loss: 95.291
+38400/69092	Loss: 93.873
+41600/69092	Loss: 92.612
+44800/69092	Loss: 93.855
+48000/69092	Loss: 93.433
+51200/69092	Loss: 92.960
+54400/69092	Loss: 93.434
+57600/69092	Loss: 92.983
+60800/69092	Loss: 93.999
+64000/69092	Loss: 93.278
+67200/69092	Loss: 94.061
+Training time 0:10:37.592550
+Epoch: 70 Average loss: 93.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 349)
+0/69092	Loss: 82.235
+3200/69092	Loss: 92.812
+6400/69092	Loss: 92.741
+9600/69092	Loss: 94.391
+12800/69092	Loss: 94.425
+16000/69092	Loss: 93.650
+19200/69092	Loss: 93.154
+22400/69092	Loss: 95.355
+25600/69092	Loss: 93.702
+28800/69092	Loss: 94.673
+32000/69092	Loss: 92.063
+35200/69092	Loss: 93.349
+38400/69092	Loss: 92.878
+41600/69092	Loss: 92.942
+44800/69092	Loss: 94.199
+48000/69092	Loss: 93.258
+51200/69092	Loss: 94.028
+54400/69092	Loss: 93.478
+57600/69092	Loss: 94.004
+60800/69092	Loss: 93.429
+64000/69092	Loss: 94.098
+67200/69092	Loss: 93.044
+Training time 0:11:04.850925
+Epoch: 71 Average loss: 93.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 350)
+0/69092	Loss: 100.796
+3200/69092	Loss: 93.263
+6400/69092	Loss: 94.184
+9600/69092	Loss: 93.715
+12800/69092	Loss: 93.848
+16000/69092	Loss: 93.524
+19200/69092	Loss: 94.057
+22400/69092	Loss: 94.713
+25600/69092	Loss: 93.748
+28800/69092	Loss: 92.868
+32000/69092	Loss: 93.377
+35200/69092	Loss: 92.899
+38400/69092	Loss: 93.682
+41600/69092	Loss: 92.089
+44800/69092	Loss: 93.360
+48000/69092	Loss: 93.175
+51200/69092	Loss: 93.489
+54400/69092	Loss: 93.405
+57600/69092	Loss: 93.629
+60800/69092	Loss: 93.500
+64000/69092	Loss: 92.478
+67200/69092	Loss: 93.935
+Training time 0:10:34.096643
+Epoch: 72 Average loss: 93.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 351)
+0/69092	Loss: 89.861
+3200/69092	Loss: 92.903
+6400/69092	Loss: 91.705
+9600/69092	Loss: 93.914
+12800/69092	Loss: 94.076
+16000/69092	Loss: 94.721
+19200/69092	Loss: 93.891
+22400/69092	Loss: 93.222
+25600/69092	Loss: 93.116
+28800/69092	Loss: 94.796
+32000/69092	Loss: 93.511
+35200/69092	Loss: 92.675
+38400/69092	Loss: 94.428
+41600/69092	Loss: 92.970
+44800/69092	Loss: 92.453
+48000/69092	Loss: 93.748
+51200/69092	Loss: 94.910
+54400/69092	Loss: 91.896
+57600/69092	Loss: 92.810
+60800/69092	Loss: 94.371
+64000/69092	Loss: 93.392
+67200/69092	Loss: 93.430
+Training time 0:10:04.464712
+Epoch: 73 Average loss: 93.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 352)
+0/69092	Loss: 95.843
+3200/69092	Loss: 93.184
+6400/69092	Loss: 93.751
+9600/69092	Loss: 94.840
+12800/69092	Loss: 92.201
+16000/69092	Loss: 93.448
+19200/69092	Loss: 93.396
+22400/69092	Loss: 94.736
+25600/69092	Loss: 93.537
+28800/69092	Loss: 94.030
+32000/69092	Loss: 93.660
+35200/69092	Loss: 93.655
+38400/69092	Loss: 94.503
+41600/69092	Loss: 93.255
+44800/69092	Loss: 92.909
+48000/69092	Loss: 92.781
+51200/69092	Loss: 92.169
+54400/69092	Loss: 92.230
+57600/69092	Loss: 95.200
+60800/69092	Loss: 91.602
+64000/69092	Loss: 93.138
+67200/69092	Loss: 93.071
+Training time 0:10:18.756998
+Epoch: 74 Average loss: 93.41
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 353)
+0/69092	Loss: 92.921
+3200/69092	Loss: 93.396
+6400/69092	Loss: 92.975
+9600/69092	Loss: 94.340
+12800/69092	Loss: 92.569
+16000/69092	Loss: 92.573
+19200/69092	Loss: 93.607
+22400/69092	Loss: 93.360
+25600/69092	Loss: 95.043
+28800/69092	Loss: 92.903
+32000/69092	Loss: 94.881
+35200/69092	Loss: 94.222
+38400/69092	Loss: 93.932
+41600/69092	Loss: 93.562
+44800/69092	Loss: 92.710
+48000/69092	Loss: 92.794
+51200/69092	Loss: 93.467
+54400/69092	Loss: 93.089
+57600/69092	Loss: 93.438
+60800/69092	Loss: 92.193
+64000/69092	Loss: 94.156
+67200/69092	Loss: 93.943
+Training time 0:10:16.165284
+Epoch: 75 Average loss: 93.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 354)
+0/69092	Loss: 95.177
+3200/69092	Loss: 92.442
+6400/69092	Loss: 94.267
+9600/69092	Loss: 92.330
+12800/69092	Loss: 94.030
+16000/69092	Loss: 92.451
+19200/69092	Loss: 94.075
+22400/69092	Loss: 93.067
+25600/69092	Loss: 93.337
+28800/69092	Loss: 94.821
+32000/69092	Loss: 93.224
+35200/69092	Loss: 93.146
+38400/69092	Loss: 94.790
+41600/69092	Loss: 92.286
+44800/69092	Loss: 93.207
+48000/69092	Loss: 93.340
+51200/69092	Loss: 94.035
+54400/69092	Loss: 92.794
+57600/69092	Loss: 93.137
+60800/69092	Loss: 93.927
+64000/69092	Loss: 94.569
+67200/69092	Loss: 92.188
+Training time 0:10:49.195784
+Epoch: 76 Average loss: 93.42
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 355)
+0/69092	Loss: 89.324
+3200/69092	Loss: 94.037
+6400/69092	Loss: 93.003
+9600/69092	Loss: 92.637
+12800/69092	Loss: 94.320
+16000/69092	Loss: 93.852
+19200/69092	Loss: 93.051
+22400/69092	Loss: 94.155
+25600/69092	Loss: 92.843
+28800/69092	Loss: 93.565
+32000/69092	Loss: 94.534
+35200/69092	Loss: 92.705
+38400/69092	Loss: 92.279
+41600/69092	Loss: 93.574
+44800/69092	Loss: 93.035
+48000/69092	Loss: 93.338
+51200/69092	Loss: 92.290
+54400/69092	Loss: 94.119
+57600/69092	Loss: 93.823
+60800/69092	Loss: 93.651
+64000/69092	Loss: 93.460
+67200/69092	Loss: 92.970
+Training time 0:10:05.405173
+Epoch: 77 Average loss: 93.41
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 356)
+0/69092	Loss: 85.505
+3200/69092	Loss: 93.821
+6400/69092	Loss: 93.204
+9600/69092	Loss: 92.696
+12800/69092	Loss: 94.265
+16000/69092	Loss: 94.397
+19200/69092	Loss: 92.243
+22400/69092	Loss: 93.589
+25600/69092	Loss: 94.552
+28800/69092	Loss: 92.744
+32000/69092	Loss: 92.802
+35200/69092	Loss: 92.272
+38400/69092	Loss: 94.469
+41600/69092	Loss: 93.443
+44800/69092	Loss: 92.450
+48000/69092	Loss: 94.336
+51200/69092	Loss: 94.288
+54400/69092	Loss: 93.237
+57600/69092	Loss: 92.444
+60800/69092	Loss: 93.364
+64000/69092	Loss: 94.600
+67200/69092	Loss: 93.644
+Training time 0:10:21.989771
+Epoch: 78 Average loss: 93.45
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 357)
+0/69092	Loss: 87.242
+3200/69092	Loss: 92.819
+6400/69092	Loss: 93.888
+9600/69092	Loss: 94.163
+12800/69092	Loss: 93.736
+16000/69092	Loss: 93.927
+19200/69092	Loss: 93.687
+22400/69092	Loss: 93.341
+25600/69092	Loss: 93.330
+28800/69092	Loss: 93.096
+32000/69092	Loss: 92.230
+35200/69092	Loss: 94.912
+38400/69092	Loss: 92.257
+41600/69092	Loss: 94.762
+44800/69092	Loss: 93.502
+48000/69092	Loss: 94.494
+51200/69092	Loss: 93.814
+54400/69092	Loss: 92.832
+57600/69092	Loss: 93.161
+60800/69092	Loss: 93.054
+64000/69092	Loss: 92.648
+67200/69092	Loss: 94.265
+Training time 0:10:29.106962
+Epoch: 79 Average loss: 93.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 358)
+0/69092	Loss: 95.626
+3200/69092	Loss: 92.874
+6400/69092	Loss: 92.411
+9600/69092	Loss: 95.036
+12800/69092	Loss: 93.458
+16000/69092	Loss: 94.352
+19200/69092	Loss: 93.344
+22400/69092	Loss: 94.011
+25600/69092	Loss: 92.603
+28800/69092	Loss: 93.313
+32000/69092	Loss: 92.520
+35200/69092	Loss: 92.456
+38400/69092	Loss: 93.778
+41600/69092	Loss: 94.948
+44800/69092	Loss: 94.949
+48000/69092	Loss: 92.678
+51200/69092	Loss: 93.405
+54400/69092	Loss: 93.366
+57600/69092	Loss: 92.806
+60800/69092	Loss: 93.200
+64000/69092	Loss: 93.024
+67200/69092	Loss: 92.731
+Training time 0:10:57.349828
+Epoch: 80 Average loss: 93.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 359)
+0/69092	Loss: 87.426
+3200/69092	Loss: 93.116
+6400/69092	Loss: 94.516
+9600/69092	Loss: 93.443
+12800/69092	Loss: 92.971
+16000/69092	Loss: 92.884
+19200/69092	Loss: 92.774
+22400/69092	Loss: 92.323
+25600/69092	Loss: 93.548
+28800/69092	Loss: 94.352
+32000/69092	Loss: 93.653
+35200/69092	Loss: 92.704
+38400/69092	Loss: 92.110
+41600/69092	Loss: 93.742
+44800/69092	Loss: 93.418
+48000/69092	Loss: 94.923
+51200/69092	Loss: 92.469
+54400/69092	Loss: 92.945
+57600/69092	Loss: 91.576
+60800/69092	Loss: 92.975
+64000/69092	Loss: 93.850
+67200/69092	Loss: 93.810
+Training time 0:10:13.115020
+Epoch: 81 Average loss: 93.31
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 360)
+0/69092	Loss: 88.595
+3200/69092	Loss: 95.700
+6400/69092	Loss: 93.163
+9600/69092	Loss: 93.252
+12800/69092	Loss: 93.610
+16000/69092	Loss: 92.514
+19200/69092	Loss: 94.053
+22400/69092	Loss: 94.457
+25600/69092	Loss: 92.067
+28800/69092	Loss: 92.828
+32000/69092	Loss: 92.876
+35200/69092	Loss: 92.619
+38400/69092	Loss: 92.744
+41600/69092	Loss: 94.729
+44800/69092	Loss: 94.009
+48000/69092	Loss: 92.407
+51200/69092	Loss: 93.996
+54400/69092	Loss: 93.670
+57600/69092	Loss: 93.544
+60800/69092	Loss: 93.276
+64000/69092	Loss: 93.250
+67200/69092	Loss: 92.561
+Training time 0:10:40.684723
+Epoch: 82 Average loss: 93.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 361)
+0/69092	Loss: 93.785
+3200/69092	Loss: 93.695
+6400/69092	Loss: 94.678
+9600/69092	Loss: 93.210
+12800/69092	Loss: 93.096
+16000/69092	Loss: 94.200
+19200/69092	Loss: 93.596
+22400/69092	Loss: 92.040
+25600/69092	Loss: 92.404
+28800/69092	Loss: 94.030
+32000/69092	Loss: 92.594
+35200/69092	Loss: 93.848
+38400/69092	Loss: 93.397
+41600/69092	Loss: 92.260
+44800/69092	Loss: 93.439
+48000/69092	Loss: 93.827
+51200/69092	Loss: 92.154
+54400/69092	Loss: 94.116
+57600/69092	Loss: 92.068
+60800/69092	Loss: 94.413
+64000/69092	Loss: 93.673
+67200/69092	Loss: 94.197
+Training time 0:10:35.844321
+Epoch: 83 Average loss: 93.39
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 362)
+0/69092	Loss: 92.934
+3200/69092	Loss: 93.670
+6400/69092	Loss: 93.369
+9600/69092	Loss: 93.842
+12800/69092	Loss: 92.851
+16000/69092	Loss: 93.542
+19200/69092	Loss: 92.557
+22400/69092	Loss: 92.931
+25600/69092	Loss: 93.982
+28800/69092	Loss: 93.119
+32000/69092	Loss: 95.363
+35200/69092	Loss: 94.018
+38400/69092	Loss: 94.180
+41600/69092	Loss: 93.164
+44800/69092	Loss: 94.118
+48000/69092	Loss: 92.912
+51200/69092	Loss: 93.462
+54400/69092	Loss: 93.054
+57600/69092	Loss: 93.863
+60800/69092	Loss: 93.283
+64000/69092	Loss: 92.327
+67200/69092	Loss: 92.859
+Training time 0:10:54.145131
+Epoch: 84 Average loss: 93.45
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 363)
+0/69092	Loss: 95.754
+3200/69092	Loss: 92.482
+6400/69092	Loss: 93.969
+9600/69092	Loss: 93.435
+12800/69092	Loss: 93.159
+16000/69092	Loss: 92.647
+19200/69092	Loss: 94.998
+22400/69092	Loss: 94.188
+25600/69092	Loss: 93.303
+28800/69092	Loss: 93.018
+32000/69092	Loss: 93.043
+35200/69092	Loss: 92.635
+38400/69092	Loss: 93.277
+41600/69092	Loss: 92.563
+44800/69092	Loss: 93.278
+48000/69092	Loss: 92.763
+51200/69092	Loss: 92.947
+54400/69092	Loss: 94.537
+57600/69092	Loss: 93.407
+60800/69092	Loss: 91.743
+64000/69092	Loss: 94.066
+67200/69092	Loss: 93.531
+Training time 0:10:34.161029
+Epoch: 85 Average loss: 93.32
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 364)
+0/69092	Loss: 96.530
+3200/69092	Loss: 93.022
+6400/69092	Loss: 92.420
+9600/69092	Loss: 94.596
+12800/69092	Loss: 92.947
+16000/69092	Loss: 93.145
+19200/69092	Loss: 93.278
+22400/69092	Loss: 94.265
+25600/69092	Loss: 93.723
+28800/69092	Loss: 93.386
+32000/69092	Loss: 93.487
+35200/69092	Loss: 94.597
+38400/69092	Loss: 93.526
+41600/69092	Loss: 93.846
+44800/69092	Loss: 92.769
+48000/69092	Loss: 92.951
+51200/69092	Loss: 92.333
+54400/69092	Loss: 92.112
+57600/69092	Loss: 92.950
+60800/69092	Loss: 94.800
+64000/69092	Loss: 94.437
+67200/69092	Loss: 93.722
+Training time 0:10:38.937684
+Epoch: 86 Average loss: 93.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 365)
+0/69092	Loss: 97.330
+3200/69092	Loss: 93.229
+6400/69092	Loss: 92.290
+9600/69092	Loss: 93.796
+12800/69092	Loss: 94.234
+16000/69092	Loss: 93.165
+19200/69092	Loss: 93.118
+22400/69092	Loss: 93.820
+25600/69092	Loss: 93.293
+28800/69092	Loss: 95.025
+32000/69092	Loss: 93.205
+35200/69092	Loss: 93.418
+38400/69092	Loss: 92.891
+41600/69092	Loss: 93.064
+44800/69092	Loss: 93.847
+48000/69092	Loss: 93.459
+51200/69092	Loss: 93.284
+54400/69092	Loss: 94.561
+57600/69092	Loss: 94.526
+60800/69092	Loss: 90.668
+64000/69092	Loss: 94.631
+67200/69092	Loss: 93.117
+Training time 0:10:50.356417
+Epoch: 87 Average loss: 93.45
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 366)
+0/69092	Loss: 94.543
+3200/69092	Loss: 94.212
+6400/69092	Loss: 93.966
+9600/69092	Loss: 93.539
+12800/69092	Loss: 94.239
+16000/69092	Loss: 94.081
+19200/69092	Loss: 92.671
+22400/69092	Loss: 94.137
+25600/69092	Loss: 95.149
+28800/69092	Loss: 94.142
+32000/69092	Loss: 93.541
+35200/69092	Loss: 92.719
+38400/69092	Loss: 92.652
+41600/69092	Loss: 94.204
+44800/69092	Loss: 91.114
+48000/69092	Loss: 91.702
+51200/69092	Loss: 93.539
+54400/69092	Loss: 93.712
+57600/69092	Loss: 92.674
+60800/69092	Loss: 93.194
+64000/69092	Loss: 92.666
+67200/69092	Loss: 94.341
+Training time 0:10:49.309912
+Epoch: 88 Average loss: 93.44
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 367)
+0/69092	Loss: 86.173
+3200/69092	Loss: 93.099
+6400/69092	Loss: 92.606
+9600/69092	Loss: 94.876
+12800/69092	Loss: 92.194
+16000/69092	Loss: 93.623
+19200/69092	Loss: 93.115
+22400/69092	Loss: 92.932
+25600/69092	Loss: 92.861
+28800/69092	Loss: 92.878
+32000/69092	Loss: 93.145
+35200/69092	Loss: 93.950
+38400/69092	Loss: 93.245
+41600/69092	Loss: 93.932
+44800/69092	Loss: 93.972
+48000/69092	Loss: 94.023
+51200/69092	Loss: 93.706
+54400/69092	Loss: 93.776
+57600/69092	Loss: 92.748
+60800/69092	Loss: 92.978
+64000/69092	Loss: 94.306
+67200/69092	Loss: 92.028
+Training time 0:10:30.747518
+Epoch: 89 Average loss: 93.38
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 368)
+0/69092	Loss: 97.815
+3200/69092	Loss: 93.206
+6400/69092	Loss: 92.617
+9600/69092	Loss: 91.872
+12800/69092	Loss: 92.346
+16000/69092	Loss: 91.508
+19200/69092	Loss: 91.624
+22400/69092	Loss: 95.040
+25600/69092	Loss: 93.901
+28800/69092	Loss: 94.224
+32000/69092	Loss: 92.994
+35200/69092	Loss: 93.151
+38400/69092	Loss: 93.251
+41600/69092	Loss: 93.677
+44800/69092	Loss: 94.083
+48000/69092	Loss: 92.831
+51200/69092	Loss: 94.215
+54400/69092	Loss: 94.062
+57600/69092	Loss: 94.467
+60800/69092	Loss: 93.354
+64000/69092	Loss: 93.449
+67200/69092	Loss: 93.560
+Training time 0:10:19.015547
+Epoch: 90 Average loss: 93.30
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 369)
+0/69092	Loss: 87.766
+3200/69092	Loss: 91.804
+6400/69092	Loss: 92.952
+9600/69092	Loss: 91.812
+12800/69092	Loss: 92.293
+16000/69092	Loss: 92.947
+19200/69092	Loss: 93.683
+22400/69092	Loss: 94.450
+25600/69092	Loss: 94.473
+28800/69092	Loss: 94.273
+32000/69092	Loss: 92.958
+35200/69092	Loss: 93.850
+38400/69092	Loss: 92.598
+41600/69092	Loss: 93.348
+44800/69092	Loss: 92.885
+48000/69092	Loss: 92.044
+51200/69092	Loss: 95.132
+54400/69092	Loss: 93.126
+57600/69092	Loss: 92.650
+60800/69092	Loss: 92.829
+64000/69092	Loss: 94.101
+67200/69092	Loss: 93.342
+Training time 0:10:17.918173
+Epoch: 91 Average loss: 93.24
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 370)
+0/69092	Loss: 90.838
+3200/69092	Loss: 92.117
+6400/69092	Loss: 94.715
+9600/69092	Loss: 94.004
+12800/69092	Loss: 94.227
+16000/69092	Loss: 93.608
+19200/69092	Loss: 93.524
+22400/69092	Loss: 92.143
+25600/69092	Loss: 93.169
+28800/69092	Loss: 93.174
+32000/69092	Loss: 93.853
+35200/69092	Loss: 91.713
+38400/69092	Loss: 93.433
+41600/69092	Loss: 94.185
+44800/69092	Loss: 93.540
+48000/69092	Loss: 93.354
+51200/69092	Loss: 93.178
+54400/69092	Loss: 93.200
+57600/69092	Loss: 92.983
+60800/69092	Loss: 93.639
+64000/69092	Loss: 93.720
+67200/69092	Loss: 92.330
+Training time 0:10:32.328375
+Epoch: 92 Average loss: 93.31
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 371)
+0/69092	Loss: 94.150
+3200/69092	Loss: 93.642
+6400/69092	Loss: 92.822
+9600/69092	Loss: 94.322
+12800/69092	Loss: 94.064
+16000/69092	Loss: 93.369
+19200/69092	Loss: 92.466
+22400/69092	Loss: 92.793
+25600/69092	Loss: 94.409
+28800/69092	Loss: 92.861
+32000/69092	Loss: 92.606
+35200/69092	Loss: 92.700
+38400/69092	Loss: 94.214
+41600/69092	Loss: 92.900
+44800/69092	Loss: 91.607
+48000/69092	Loss: 94.258
+51200/69092	Loss: 93.236
+54400/69092	Loss: 92.883
+57600/69092	Loss: 94.439
+60800/69092	Loss: 92.686
+64000/69092	Loss: 93.645
+67200/69092	Loss: 92.396
+Training time 0:10:22.161247
+Epoch: 93 Average loss: 93.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 372)
+0/69092	Loss: 89.555
+3200/69092	Loss: 95.058
+6400/69092	Loss: 93.503
+9600/69092	Loss: 93.409
+12800/69092	Loss: 91.083
+16000/69092	Loss: 92.802
+19200/69092	Loss: 93.026
+22400/69092	Loss: 92.553
+25600/69092	Loss: 93.463
+28800/69092	Loss: 92.431
+32000/69092	Loss: 93.631
+35200/69092	Loss: 94.406
+38400/69092	Loss: 93.383
+41600/69092	Loss: 93.139
+44800/69092	Loss: 92.231
+48000/69092	Loss: 93.091
+51200/69092	Loss: 94.125
+54400/69092	Loss: 93.199
+57600/69092	Loss: 94.166
+60800/69092	Loss: 91.734
+64000/69092	Loss: 93.253
+67200/69092	Loss: 92.737
+Training time 0:10:14.232471
+Epoch: 94 Average loss: 93.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 373)
+0/69092	Loss: 83.989
+3200/69092	Loss: 94.660
+6400/69092	Loss: 94.513
+9600/69092	Loss: 92.861
+12800/69092	Loss: 93.349
+16000/69092	Loss: 93.826
+19200/69092	Loss: 92.991
+22400/69092	Loss: 94.577
+25600/69092	Loss: 93.038
+28800/69092	Loss: 92.260
+32000/69092	Loss: 92.849
+35200/69092	Loss: 94.482
+38400/69092	Loss: 91.464
+41600/69092	Loss: 94.078
+44800/69092	Loss: 94.280
+48000/69092	Loss: 93.147
+51200/69092	Loss: 92.431
+54400/69092	Loss: 94.081
+57600/69092	Loss: 91.688
+60800/69092	Loss: 91.693
+64000/69092	Loss: 93.510
+67200/69092	Loss: 94.065
+Training time 0:10:36.824236
+Epoch: 95 Average loss: 93.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 374)
+0/69092	Loss: 96.164
+3200/69092	Loss: 93.377
+6400/69092	Loss: 92.605
+9600/69092	Loss: 94.189
+12800/69092	Loss: 92.072
+16000/69092	Loss: 92.690
+19200/69092	Loss: 94.215
+22400/69092	Loss: 92.605
+25600/69092	Loss: 93.772
+28800/69092	Loss: 92.963
+32000/69092	Loss: 93.318
+35200/69092	Loss: 95.218
+38400/69092	Loss: 92.291
+41600/69092	Loss: 94.312
+44800/69092	Loss: 94.576
+48000/69092	Loss: 92.322
+51200/69092	Loss: 93.366
+54400/69092	Loss: 93.770
+57600/69092	Loss: 92.244
+60800/69092	Loss: 91.873
+64000/69092	Loss: 93.404
+67200/69092	Loss: 94.060
+Training time 0:10:42.962750
+Epoch: 96 Average loss: 93.32
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 375)
+0/69092	Loss: 84.413
+3200/69092	Loss: 93.457
+6400/69092	Loss: 92.662
+9600/69092	Loss: 94.372
+12800/69092	Loss: 93.429
+16000/69092	Loss: 92.817
+19200/69092	Loss: 91.943
+22400/69092	Loss: 91.658
+25600/69092	Loss: 93.169
+28800/69092	Loss: 93.488
+32000/69092	Loss: 92.568
+35200/69092	Loss: 94.250
+38400/69092	Loss: 93.258
+41600/69092	Loss: 92.991
+44800/69092	Loss: 92.823
+48000/69092	Loss: 94.266
+51200/69092	Loss: 93.473
+54400/69092	Loss: 93.341
+57600/69092	Loss: 94.293
+60800/69092	Loss: 93.675
+64000/69092	Loss: 93.603
+67200/69092	Loss: 93.318
+Training time 0:10:21.682315
+Epoch: 97 Average loss: 93.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 376)
+0/69092	Loss: 98.388
+3200/69092	Loss: 92.533
+6400/69092	Loss: 93.545
+9600/69092	Loss: 94.627
+12800/69092	Loss: 94.389
+16000/69092	Loss: 93.306
+19200/69092	Loss: 91.969
+22400/69092	Loss: 93.434
+25600/69092	Loss: 92.900
+28800/69092	Loss: 92.817
+32000/69092	Loss: 93.684
+35200/69092	Loss: 93.093
+38400/69092	Loss: 92.636
+41600/69092	Loss: 93.225
+44800/69092	Loss: 93.836
+48000/69092	Loss: 93.190
+51200/69092	Loss: 94.696
+54400/69092	Loss: 92.536
+57600/69092	Loss: 92.526
+60800/69092	Loss: 93.463
+64000/69092	Loss: 93.073
+67200/69092	Loss: 92.885
+Training time 0:10:39.016477
+Epoch: 98 Average loss: 93.28
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 377)
+0/69092	Loss: 87.540
+3200/69092	Loss: 92.396
+6400/69092	Loss: 91.925
+9600/69092	Loss: 93.321
+12800/69092	Loss: 92.368
+16000/69092	Loss: 93.790
+19200/69092	Loss: 92.207
+22400/69092	Loss: 92.945
+25600/69092	Loss: 93.762
+28800/69092	Loss: 94.125
+32000/69092	Loss: 94.558
+35200/69092	Loss: 92.852
+38400/69092	Loss: 93.077
+41600/69092	Loss: 92.475
+44800/69092	Loss: 92.134
+48000/69092	Loss: 93.057
+51200/69092	Loss: 94.465
+54400/69092	Loss: 93.876
+57600/69092	Loss: 93.163
+60800/69092	Loss: 91.432
+64000/69092	Loss: 95.150
+67200/69092	Loss: 94.076
+Training time 0:10:20.850274
+Epoch: 99 Average loss: 93.22
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 378)
+0/69092	Loss: 97.614
+3200/69092	Loss: 93.088
+6400/69092	Loss: 92.352
+9600/69092	Loss: 91.916
+12800/69092	Loss: 93.096
+16000/69092	Loss: 92.663
+19200/69092	Loss: 93.151
+22400/69092	Loss: 92.147
+25600/69092	Loss: 93.913
+28800/69092	Loss: 94.454
+32000/69092	Loss: 93.530
+35200/69092	Loss: 94.338
+38400/69092	Loss: 92.459
+41600/69092	Loss: 93.448
+44800/69092	Loss: 92.937
+48000/69092	Loss: 93.509
+51200/69092	Loss: 92.862
+54400/69092	Loss: 94.531
+57600/69092	Loss: 93.318
+60800/69092	Loss: 93.863
+64000/69092	Loss: 93.527
+67200/69092	Loss: 92.795
+Training time 0:10:17.596621
+Epoch: 100 Average loss: 93.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 379)
+0/69092	Loss: 87.935
+3200/69092	Loss: 93.397
+6400/69092	Loss: 94.411
+9600/69092	Loss: 94.278
+12800/69092	Loss: 94.121
+16000/69092	Loss: 93.760
+19200/69092	Loss: 92.294
+22400/69092	Loss: 92.889
+25600/69092	Loss: 91.303
+28800/69092	Loss: 93.701
+32000/69092	Loss: 91.905
+35200/69092	Loss: 92.849
+38400/69092	Loss: 93.837
+41600/69092	Loss: 91.498
+44800/69092	Loss: 93.884
+48000/69092	Loss: 92.587
+51200/69092	Loss: 93.240
+54400/69092	Loss: 92.330
+57600/69092	Loss: 92.932
+60800/69092	Loss: 93.897
+64000/69092	Loss: 93.748
+67200/69092	Loss: 93.455
+Training time 0:10:18.915215
+Epoch: 101 Average loss: 93.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 380)
+0/69092	Loss: 93.243
+3200/69092	Loss: 94.220
+6400/69092	Loss: 94.624
+9600/69092	Loss: 92.951
+12800/69092	Loss: 93.796
+16000/69092	Loss: 92.441
+19200/69092	Loss: 91.993
+22400/69092	Loss: 92.123
+25600/69092	Loss: 93.954
+28800/69092	Loss: 93.799
+32000/69092	Loss: 93.025
+35200/69092	Loss: 93.269
+38400/69092	Loss: 92.431
+41600/69092	Loss: 91.693
+44800/69092	Loss: 93.827
+48000/69092	Loss: 94.016
+51200/69092	Loss: 92.687
+54400/69092	Loss: 92.480
+57600/69092	Loss: 94.146
+60800/69092	Loss: 93.695
+64000/69092	Loss: 93.799
+67200/69092	Loss: 92.996
+Training time 0:10:32.999726
+Epoch: 102 Average loss: 93.22
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 381)
+0/69092	Loss: 108.876
+3200/69092	Loss: 94.292
+6400/69092	Loss: 92.078
+9600/69092	Loss: 95.396
+12800/69092	Loss: 93.931
+16000/69092	Loss: 93.794
+19200/69092	Loss: 92.863
+22400/69092	Loss: 95.653
+25600/69092	Loss: 93.833
+28800/69092	Loss: 92.646
+32000/69092	Loss: 93.796
+35200/69092	Loss: 92.025
+38400/69092	Loss: 93.800
+41600/69092	Loss: 93.843
+44800/69092	Loss: 91.993
+48000/69092	Loss: 92.345
+51200/69092	Loss: 92.797
+54400/69092	Loss: 92.643
+57600/69092	Loss: 90.890
+60800/69092	Loss: 92.933
+64000/69092	Loss: 93.356
+67200/69092	Loss: 92.786
+Training time 0:10:50.960320
+Epoch: 103 Average loss: 93.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 382)
+0/69092	Loss: 89.526
+3200/69092	Loss: 92.887
+6400/69092	Loss: 92.039
+9600/69092	Loss: 93.266
+12800/69092	Loss: 92.443
+16000/69092	Loss: 92.459
+19200/69092	Loss: 93.064
+22400/69092	Loss: 94.990
+25600/69092	Loss: 91.917
+28800/69092	Loss: 93.694
+32000/69092	Loss: 92.197
+35200/69092	Loss: 92.531
+38400/69092	Loss: 92.136
+41600/69092	Loss: 93.338
+44800/69092	Loss: 93.354
+48000/69092	Loss: 92.719
+51200/69092	Loss: 92.902
+54400/69092	Loss: 93.501
+57600/69092	Loss: 94.066
+60800/69092	Loss: 93.344
+64000/69092	Loss: 93.143
+67200/69092	Loss: 94.855
+Training time 0:11:09.814920
+Epoch: 104 Average loss: 93.14
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 383)
+0/69092	Loss: 95.561
+3200/69092	Loss: 93.742
+6400/69092	Loss: 93.176
+9600/69092	Loss: 93.379
+12800/69092	Loss: 93.054
+16000/69092	Loss: 92.370
+19200/69092	Loss: 94.151
+22400/69092	Loss: 94.237
+25600/69092	Loss: 93.574
+28800/69092	Loss: 92.937
+32000/69092	Loss: 92.888
+35200/69092	Loss: 93.677
+38400/69092	Loss: 92.699
+41600/69092	Loss: 92.560
+44800/69092	Loss: 93.318
+48000/69092	Loss: 95.227
+51200/69092	Loss: 91.778
+54400/69092	Loss: 92.178
+57600/69092	Loss: 91.886
+60800/69092	Loss: 94.202
+64000/69092	Loss: 92.882
+67200/69092	Loss: 93.135
+Training time 0:10:40.158421
+Epoch: 105 Average loss: 93.23
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 384)
+0/69092	Loss: 98.050
+3200/69092	Loss: 91.779
+6400/69092	Loss: 93.130
+9600/69092	Loss: 92.072
+12800/69092	Loss: 94.323
+16000/69092	Loss: 91.280
+19200/69092	Loss: 92.840
+22400/69092	Loss: 92.747
+25600/69092	Loss: 93.052
+28800/69092	Loss: 92.560
+32000/69092	Loss: 95.072
+35200/69092	Loss: 93.046
+38400/69092	Loss: 94.286
+41600/69092	Loss: 93.489
+44800/69092	Loss: 92.134
+48000/69092	Loss: 93.374
+51200/69092	Loss: 93.179
+54400/69092	Loss: 92.706
+57600/69092	Loss: 93.548
+60800/69092	Loss: 93.596
+64000/69092	Loss: 92.708
+67200/69092	Loss: 93.568
+Training time 0:10:51.023876
+Epoch: 106 Average loss: 93.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 385)
+0/69092	Loss: 99.075
+3200/69092	Loss: 91.688
+6400/69092	Loss: 93.294
+9600/69092	Loss: 92.068
+12800/69092	Loss: 92.708
+16000/69092	Loss: 93.353
+19200/69092	Loss: 94.015
+22400/69092	Loss: 94.014
+25600/69092	Loss: 92.689
+28800/69092	Loss: 93.682
+32000/69092	Loss: 93.225
+35200/69092	Loss: 93.438
+38400/69092	Loss: 93.619
+41600/69092	Loss: 91.915
+44800/69092	Loss: 93.156
+48000/69092	Loss: 92.798
+51200/69092	Loss: 93.799
+54400/69092	Loss: 93.697
+57600/69092	Loss: 94.238
+60800/69092	Loss: 94.197
+64000/69092	Loss: 92.857
+67200/69092	Loss: 92.104
+Training time 0:10:29.527706
+Epoch: 107 Average loss: 93.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 386)
+0/69092	Loss: 89.326
+3200/69092	Loss: 92.230
+6400/69092	Loss: 92.167
+9600/69092	Loss: 92.387
+12800/69092	Loss: 92.049
+16000/69092	Loss: 93.047
+19200/69092	Loss: 93.672
+22400/69092	Loss: 92.070
+25600/69092	Loss: 94.433
+28800/69092	Loss: 92.233
+32000/69092	Loss: 93.321
+35200/69092	Loss: 94.089
+38400/69092	Loss: 93.188
+41600/69092	Loss: 93.962
+44800/69092	Loss: 93.079
+48000/69092	Loss: 93.290
+51200/69092	Loss: 92.913
+54400/69092	Loss: 93.311
+57600/69092	Loss: 92.095
+60800/69092	Loss: 94.072
+64000/69092	Loss: 93.965
+67200/69092	Loss: 93.204
+Training time 0:10:49.708456
+Epoch: 108 Average loss: 93.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 387)
+0/69092	Loss: 87.865
+3200/69092	Loss: 92.366
+6400/69092	Loss: 91.558
+9600/69092	Loss: 93.628
+12800/69092	Loss: 93.970
+16000/69092	Loss: 92.362
+19200/69092	Loss: 93.312
+22400/69092	Loss: 92.616
+25600/69092	Loss: 94.466
+28800/69092	Loss: 94.325
+32000/69092	Loss: 91.492
+35200/69092	Loss: 93.476
+38400/69092	Loss: 92.427
+41600/69092	Loss: 93.670
+44800/69092	Loss: 92.911
+48000/69092	Loss: 93.421
+51200/69092	Loss: 92.963
+54400/69092	Loss: 93.408
+57600/69092	Loss: 93.892
+60800/69092	Loss: 94.477
+64000/69092	Loss: 93.131
+67200/69092	Loss: 94.088
+Training time 0:10:44.515131
+Epoch: 109 Average loss: 93.20
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 388)
+0/69092	Loss: 89.751
+3200/69092	Loss: 92.979
+6400/69092	Loss: 92.594
+9600/69092	Loss: 93.847
+12800/69092	Loss: 93.643
+16000/69092	Loss: 94.281
+19200/69092	Loss: 93.882
+22400/69092	Loss: 92.724
+25600/69092	Loss: 94.097
+28800/69092	Loss: 93.811
+32000/69092	Loss: 93.824
+35200/69092	Loss: 91.924
+38400/69092	Loss: 91.544
+41600/69092	Loss: 92.576
+44800/69092	Loss: 93.398
+48000/69092	Loss: 92.276
+51200/69092	Loss: 92.337
+54400/69092	Loss: 92.222
+57600/69092	Loss: 94.228
+60800/69092	Loss: 91.604
+64000/69092	Loss: 95.424
+67200/69092	Loss: 92.890
+Training time 0:10:36.137533
+Epoch: 110 Average loss: 93.16
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 389)
+0/69092	Loss: 94.808
+3200/69092	Loss: 91.856
+6400/69092	Loss: 91.423
+9600/69092	Loss: 93.353
+12800/69092	Loss: 93.567
+16000/69092	Loss: 92.577
+19200/69092	Loss: 93.185
+22400/69092	Loss: 93.367
+25600/69092	Loss: 93.260
+28800/69092	Loss: 92.536
+32000/69092	Loss: 94.393
+35200/69092	Loss: 94.419
+38400/69092	Loss: 93.505
+41600/69092	Loss: 93.685
+44800/69092	Loss: 92.806
+48000/69092	Loss: 93.655
+51200/69092	Loss: 93.391
+54400/69092	Loss: 93.514
+57600/69092	Loss: 93.438
+60800/69092	Loss: 93.269
+64000/69092	Loss: 93.942
+67200/69092	Loss: 92.341
+Training time 0:10:45.578260
+Epoch: 111 Average loss: 93.20
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 390)
+0/69092	Loss: 88.081
+3200/69092	Loss: 92.803
+6400/69092	Loss: 93.073
+9600/69092	Loss: 92.147
+12800/69092	Loss: 93.128
+16000/69092	Loss: 92.517
+19200/69092	Loss: 92.602
+22400/69092	Loss: 92.353
+25600/69092	Loss: 94.206
+28800/69092	Loss: 92.127
+32000/69092	Loss: 93.050
+35200/69092	Loss: 92.023
+38400/69092	Loss: 92.767
+41600/69092	Loss: 92.940
+44800/69092	Loss: 93.283
+48000/69092	Loss: 93.302
+51200/69092	Loss: 93.715
+54400/69092	Loss: 94.356
+57600/69092	Loss: 94.043
+60800/69092	Loss: 94.796
+64000/69092	Loss: 93.478
+67200/69092	Loss: 91.771
+Training time 0:11:04.307800
+Epoch: 112 Average loss: 93.12
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 391)
+0/69092	Loss: 88.149
+3200/69092	Loss: 93.759
+6400/69092	Loss: 93.228
+9600/69092	Loss: 92.095
+12800/69092	Loss: 93.082
+16000/69092	Loss: 92.882
+19200/69092	Loss: 93.695
+22400/69092	Loss: 93.062
+25600/69092	Loss: 93.911
+28800/69092	Loss: 93.465
+32000/69092	Loss: 93.598
+35200/69092	Loss: 94.359
+38400/69092	Loss: 92.227
+41600/69092	Loss: 93.105
+44800/69092	Loss: 94.303
+48000/69092	Loss: 93.551
+51200/69092	Loss: 93.316
+54400/69092	Loss: 92.581
+57600/69092	Loss: 91.721
+60800/69092	Loss: 92.639
+64000/69092	Loss: 91.375
+67200/69092	Loss: 92.839
+Training time 0:10:48.253999
+Epoch: 113 Average loss: 93.13
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 392)
+0/69092	Loss: 98.237
+3200/69092	Loss: 91.908
+6400/69092	Loss: 92.181
+9600/69092	Loss: 92.891
+12800/69092	Loss: 92.179
+16000/69092	Loss: 94.107
+19200/69092	Loss: 91.840
+22400/69092	Loss: 94.854
+25600/69092	Loss: 92.926
+28800/69092	Loss: 94.183
+32000/69092	Loss: 93.174
+35200/69092	Loss: 93.321
+38400/69092	Loss: 92.210
+41600/69092	Loss: 92.549
+44800/69092	Loss: 92.444
+48000/69092	Loss: 95.022
+51200/69092	Loss: 92.186
+54400/69092	Loss: 92.679
+57600/69092	Loss: 94.080
+60800/69092	Loss: 92.168
+64000/69092	Loss: 94.054
+67200/69092	Loss: 92.729
+Training time 0:10:29.851312
+Epoch: 114 Average loss: 93.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 393)
+0/69092	Loss: 86.609
+3200/69092	Loss: 93.674
+6400/69092	Loss: 93.881
+9600/69092	Loss: 92.217
+12800/69092	Loss: 91.985
+16000/69092	Loss: 92.412
+19200/69092	Loss: 94.073
+22400/69092	Loss: 92.943
+25600/69092	Loss: 94.747
+28800/69092	Loss: 91.898
+32000/69092	Loss: 93.993
+35200/69092	Loss: 92.886
+38400/69092	Loss: 92.542
+41600/69092	Loss: 92.750
+44800/69092	Loss: 92.892
+48000/69092	Loss: 94.908
+51200/69092	Loss: 93.009
+54400/69092	Loss: 93.582
+57600/69092	Loss: 93.712
+60800/69092	Loss: 91.920
+64000/69092	Loss: 92.220
+67200/69092	Loss: 93.459
+Training time 0:10:40.600873
+Epoch: 115 Average loss: 93.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 394)
+0/69092	Loss: 94.926
+3200/69092	Loss: 92.642
+6400/69092	Loss: 94.107
+9600/69092	Loss: 91.696
+12800/69092	Loss: 94.893
+16000/69092	Loss: 93.190
+19200/69092	Loss: 93.737
+22400/69092	Loss: 93.238
+25600/69092	Loss: 92.427
+28800/69092	Loss: 93.149
+32000/69092	Loss: 93.052
+35200/69092	Loss: 92.421
+38400/69092	Loss: 92.784
+41600/69092	Loss: 92.562
+44800/69092	Loss: 93.329
+48000/69092	Loss: 92.789
+51200/69092	Loss: 93.117
+54400/69092	Loss: 92.468
+57600/69092	Loss: 93.375
+60800/69092	Loss: 93.003
+64000/69092	Loss: 93.221
+67200/69092	Loss: 93.009
+Training time 0:10:53.926276
+Epoch: 116 Average loss: 93.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 395)
+0/69092	Loss: 94.007
+3200/69092	Loss: 93.694
+6400/69092	Loss: 93.024
+9600/69092	Loss: 92.914
+12800/69092	Loss: 92.620
+16000/69092	Loss: 92.830
+19200/69092	Loss: 92.584
+22400/69092	Loss: 94.293
+25600/69092	Loss: 92.538
+28800/69092	Loss: 92.377
+32000/69092	Loss: 93.225
+35200/69092	Loss: 92.971
+38400/69092	Loss: 92.910
+41600/69092	Loss: 93.796
+44800/69092	Loss: 93.406
+48000/69092	Loss: 94.198
+51200/69092	Loss: 90.760
+54400/69092	Loss: 92.323
+57600/69092	Loss: 93.172
+60800/69092	Loss: 93.920
+64000/69092	Loss: 93.892
+67200/69092	Loss: 93.834
+Training time 0:10:17.078378
+Epoch: 117 Average loss: 93.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 396)
+0/69092	Loss: 89.664
+3200/69092	Loss: 92.027
+6400/69092	Loss: 93.108
+9600/69092	Loss: 92.048
+12800/69092	Loss: 92.275
+16000/69092	Loss: 92.081
+19200/69092	Loss: 92.479
+22400/69092	Loss: 92.895
+25600/69092	Loss: 92.499
+28800/69092	Loss: 93.346
+32000/69092	Loss: 93.775
+35200/69092	Loss: 94.435
+38400/69092	Loss: 94.060
+41600/69092	Loss: 94.301
+44800/69092	Loss: 93.337
+48000/69092	Loss: 93.531
+51200/69092	Loss: 94.846
+54400/69092	Loss: 92.542
+57600/69092	Loss: 91.542
+60800/69092	Loss: 93.113
+64000/69092	Loss: 93.243
+67200/69092	Loss: 92.793
+Training time 0:10:57.910485
+Epoch: 118 Average loss: 93.09
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 397)
+0/69092	Loss: 88.337
+3200/69092	Loss: 91.948
+6400/69092	Loss: 93.151
+9600/69092	Loss: 92.505
+12800/69092	Loss: 94.577
+16000/69092	Loss: 93.575
+19200/69092	Loss: 93.444
+22400/69092	Loss: 92.096
+25600/69092	Loss: 91.046
+28800/69092	Loss: 93.556
+32000/69092	Loss: 93.214
+35200/69092	Loss: 92.968
+38400/69092	Loss: 92.385
+41600/69092	Loss: 92.507
+44800/69092	Loss: 93.555
+48000/69092	Loss: 93.972
+51200/69092	Loss: 92.333
+54400/69092	Loss: 92.924
+57600/69092	Loss: 93.133
+60800/69092	Loss: 94.692
+64000/69092	Loss: 93.631
+67200/69092	Loss: 93.929
+Training time 0:10:42.323308
+Epoch: 119 Average loss: 93.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 398)
+0/69092	Loss: 91.245
+3200/69092	Loss: 92.356
+6400/69092	Loss: 93.430
+9600/69092	Loss: 93.024
+12800/69092	Loss: 93.941
+16000/69092	Loss: 92.007
+19200/69092	Loss: 92.801
+22400/69092	Loss: 92.910
+25600/69092	Loss: 92.494
+28800/69092	Loss: 92.386
+32000/69092	Loss: 92.848
+35200/69092	Loss: 92.557
+38400/69092	Loss: 93.233
+41600/69092	Loss: 92.927
+44800/69092	Loss: 93.097
+48000/69092	Loss: 91.985
+51200/69092	Loss: 93.202
+54400/69092	Loss: 94.537
+57600/69092	Loss: 93.491
+60800/69092	Loss: 93.098
+64000/69092	Loss: 93.099
+67200/69092	Loss: 94.546
+Training time 0:10:26.932577
+Epoch: 120 Average loss: 93.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 399)
+0/69092	Loss: 89.426
+3200/69092	Loss: 94.838
+6400/69092	Loss: 92.622
+9600/69092	Loss: 92.332
+12800/69092	Loss: 93.995
+16000/69092	Loss: 92.640
+19200/69092	Loss: 92.442
+22400/69092	Loss: 94.118
+25600/69092	Loss: 93.424
+28800/69092	Loss: 92.711
+32000/69092	Loss: 93.608
+35200/69092	Loss: 92.313
+38400/69092	Loss: 92.453
+41600/69092	Loss: 93.801
+44800/69092	Loss: 92.606
+48000/69092	Loss: 93.221
+51200/69092	Loss: 92.375
+54400/69092	Loss: 91.509
+57600/69092	Loss: 93.812
+60800/69092	Loss: 92.116
+64000/69092	Loss: 94.152
+67200/69092	Loss: 92.840
+Training time 0:10:27.257799
+Epoch: 121 Average loss: 93.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 400)
+0/69092	Loss: 97.193
+3200/69092	Loss: 91.592
+6400/69092	Loss: 92.902
+9600/69092	Loss: 94.000
+12800/69092	Loss: 93.285
+16000/69092	Loss: 93.834
+19200/69092	Loss: 92.712
+22400/69092	Loss: 93.901
+25600/69092	Loss: 93.045
+28800/69092	Loss: 93.403
+32000/69092	Loss: 93.258
+35200/69092	Loss: 92.264
+38400/69092	Loss: 92.838
+41600/69092	Loss: 92.269
+44800/69092	Loss: 93.020
+48000/69092	Loss: 94.076
+51200/69092	Loss: 93.069
+54400/69092	Loss: 94.148
+57600/69092	Loss: 92.873
+60800/69092	Loss: 94.485
+64000/69092	Loss: 92.589
+67200/69092	Loss: 92.385
+Training time 0:10:42.115896
+Epoch: 122 Average loss: 93.15
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 401)
+0/69092	Loss: 88.332
+3200/69092	Loss: 92.735
+6400/69092	Loss: 93.849
+9600/69092	Loss: 91.491
+12800/69092	Loss: 93.878
+16000/69092	Loss: 92.936
+19200/69092	Loss: 93.155
+22400/69092	Loss: 91.845
+25600/69092	Loss: 93.143
+28800/69092	Loss: 92.731
+32000/69092	Loss: 92.627
+35200/69092	Loss: 94.780
+38400/69092	Loss: 92.513
+41600/69092	Loss: 92.267
+44800/69092	Loss: 93.836
+48000/69092	Loss: 93.423
+51200/69092	Loss: 93.381
+54400/69092	Loss: 93.835
+57600/69092	Loss: 92.983
+60800/69092	Loss: 91.522
+64000/69092	Loss: 92.581
+67200/69092	Loss: 94.301
+Training time 0:10:38.127068
+Epoch: 123 Average loss: 93.01
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 402)
+0/69092	Loss: 92.243
+3200/69092	Loss: 92.621
+6400/69092	Loss: 92.776
+9600/69092	Loss: 93.160
+12800/69092	Loss: 93.042
+16000/69092	Loss: 91.590
+19200/69092	Loss: 93.035
+22400/69092	Loss: 92.473
+25600/69092	Loss: 93.589
+28800/69092	Loss: 93.776
+32000/69092	Loss: 93.274
+35200/69092	Loss: 93.864
+38400/69092	Loss: 92.742
+41600/69092	Loss: 93.702
+44800/69092	Loss: 92.730
+48000/69092	Loss: 92.770
+51200/69092	Loss: 92.466
+54400/69092	Loss: 94.704
+57600/69092	Loss: 92.089
+60800/69092	Loss: 92.548
+64000/69092	Loss: 92.184
+67200/69092	Loss: 92.784
+Training time 0:10:35.228475
+Epoch: 124 Average loss: 92.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 403)
+0/69092	Loss: 100.818
+3200/69092	Loss: 92.687
+6400/69092	Loss: 92.773
+9600/69092	Loss: 92.782
+12800/69092	Loss: 91.514
+16000/69092	Loss: 94.386
+19200/69092	Loss: 94.405
+22400/69092	Loss: 93.170
+25600/69092	Loss: 93.122
+28800/69092	Loss: 92.309
+32000/69092	Loss: 92.932
+35200/69092	Loss: 93.517
+38400/69092	Loss: 91.624
+41600/69092	Loss: 91.835
+44800/69092	Loss: 93.660
+48000/69092	Loss: 93.561
+51200/69092	Loss: 93.070
+54400/69092	Loss: 93.029
+57600/69092	Loss: 93.015
+60800/69092	Loss: 92.498
+64000/69092	Loss: 93.090
+67200/69092	Loss: 94.505
+Training time 0:10:17.123610
+Epoch: 125 Average loss: 93.04
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 404)
+0/69092	Loss: 104.049
+3200/69092	Loss: 92.856
+6400/69092	Loss: 92.192
+9600/69092	Loss: 93.618
+12800/69092	Loss: 93.275
+16000/69092	Loss: 93.292
+19200/69092	Loss: 94.127
+22400/69092	Loss: 92.421
+25600/69092	Loss: 91.846
+28800/69092	Loss: 94.998
+32000/69092	Loss: 92.040
+35200/69092	Loss: 93.367
+38400/69092	Loss: 92.792
+41600/69092	Loss: 92.259
+44800/69092	Loss: 92.135
+48000/69092	Loss: 93.271
+51200/69092	Loss: 94.114
+54400/69092	Loss: 93.362
+57600/69092	Loss: 92.816
+60800/69092	Loss: 92.795
+64000/69092	Loss: 91.757
+67200/69092	Loss: 93.204
+Training time 0:10:44.599854
+Epoch: 126 Average loss: 92.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 405)
+0/69092	Loss: 91.300
+3200/69092	Loss: 92.898
+6400/69092	Loss: 91.986
+9600/69092	Loss: 93.458
+12800/69092	Loss: 92.807
+16000/69092	Loss: 92.489
+19200/69092	Loss: 92.270
+22400/69092	Loss: 93.285
+25600/69092	Loss: 93.074
+28800/69092	Loss: 93.289
+32000/69092	Loss: 92.585
+35200/69092	Loss: 93.272
+38400/69092	Loss: 93.186
+41600/69092	Loss: 92.558
+44800/69092	Loss: 92.380
+48000/69092	Loss: 91.924
+51200/69092	Loss: 92.879
+54400/69092	Loss: 93.371
+57600/69092	Loss: 93.254
+60800/69092	Loss: 94.290
+64000/69092	Loss: 92.572
+67200/69092	Loss: 92.624
+Training time 0:10:34.105276
+Epoch: 127 Average loss: 92.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 406)
+0/69092	Loss: 83.986
+3200/69092	Loss: 92.417
+6400/69092	Loss: 93.875
+9600/69092	Loss: 94.722
+12800/69092	Loss: 92.962
+16000/69092	Loss: 92.808
+19200/69092	Loss: 93.143
+22400/69092	Loss: 93.782
+25600/69092	Loss: 91.485
+28800/69092	Loss: 93.670
+32000/69092	Loss: 94.345
+35200/69092	Loss: 93.397
+38400/69092	Loss: 92.906
+41600/69092	Loss: 92.286
+44800/69092	Loss: 91.499
+48000/69092	Loss: 92.866
+51200/69092	Loss: 92.817
+54400/69092	Loss: 93.149
+57600/69092	Loss: 93.320
+60800/69092	Loss: 91.789
+64000/69092	Loss: 93.931
+67200/69092	Loss: 91.805
+Training time 0:10:54.483345
+Epoch: 128 Average loss: 92.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 407)
+0/69092	Loss: 90.794
+3200/69092	Loss: 92.083
+6400/69092	Loss: 92.445
+9600/69092	Loss: 93.604
+12800/69092	Loss: 93.503
+16000/69092	Loss: 91.706
+19200/69092	Loss: 92.541
+22400/69092	Loss: 92.868
+25600/69092	Loss: 92.774
+28800/69092	Loss: 92.219
+32000/69092	Loss: 92.986
+35200/69092	Loss: 93.444
+38400/69092	Loss: 92.733
+41600/69092	Loss: 94.288
+44800/69092	Loss: 92.904
+48000/69092	Loss: 92.915
+51200/69092	Loss: 92.664
+54400/69092	Loss: 92.916
+57600/69092	Loss: 92.673
+60800/69092	Loss: 92.689
+64000/69092	Loss: 95.054
+67200/69092	Loss: 93.448
+Training time 0:10:48.198722
+Epoch: 129 Average loss: 93.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 408)
+0/69092	Loss: 90.181
+3200/69092	Loss: 93.975
+6400/69092	Loss: 92.188
+9600/69092	Loss: 92.333
+12800/69092	Loss: 92.765
+16000/69092	Loss: 92.159
+19200/69092	Loss: 93.249
+22400/69092	Loss: 92.388
+25600/69092	Loss: 93.475
+28800/69092	Loss: 93.020
+32000/69092	Loss: 91.649
+35200/69092	Loss: 93.006
+38400/69092	Loss: 93.334
+41600/69092	Loss: 92.615
+44800/69092	Loss: 94.136
+48000/69092	Loss: 92.207
+51200/69092	Loss: 92.943
+54400/69092	Loss: 93.218
+57600/69092	Loss: 93.575
+60800/69092	Loss: 91.072
+64000/69092	Loss: 93.338
+67200/69092	Loss: 94.143
+Training time 0:10:40.807683
+Epoch: 130 Average loss: 92.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 409)
+0/69092	Loss: 84.556
+3200/69092	Loss: 93.355
+6400/69092	Loss: 92.359
+9600/69092	Loss: 93.099
+12800/69092	Loss: 91.579
+16000/69092	Loss: 91.999
+19200/69092	Loss: 93.407
+22400/69092	Loss: 91.712
+25600/69092	Loss: 93.416
+28800/69092	Loss: 94.313
+32000/69092	Loss: 92.880
+35200/69092	Loss: 91.527
+38400/69092	Loss: 92.863
+41600/69092	Loss: 92.629
+44800/69092	Loss: 93.964
+48000/69092	Loss: 93.107
+51200/69092	Loss: 92.486
+54400/69092	Loss: 94.472
+57600/69092	Loss: 93.828
+60800/69092	Loss: 93.671
+64000/69092	Loss: 91.859
+67200/69092	Loss: 92.353
+Training time 0:10:26.909666
+Epoch: 131 Average loss: 92.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 410)
+0/69092	Loss: 97.387
+3200/69092	Loss: 92.917
+6400/69092	Loss: 92.521
+9600/69092	Loss: 94.050
+12800/69092	Loss: 92.133
+16000/69092	Loss: 92.038
+19200/69092	Loss: 92.344
+22400/69092	Loss: 94.058
+25600/69092	Loss: 93.527
+28800/69092	Loss: 92.044
+32000/69092	Loss: 93.721
+35200/69092	Loss: 93.522
+38400/69092	Loss: 93.740
+41600/69092	Loss: 92.677
+44800/69092	Loss: 92.292
+48000/69092	Loss: 93.323
+51200/69092	Loss: 92.423
+54400/69092	Loss: 93.030
+57600/69092	Loss: 93.527
+60800/69092	Loss: 92.770
+64000/69092	Loss: 91.827
+67200/69092	Loss: 93.940
+Training time 0:10:38.802806
+Epoch: 132 Average loss: 92.99
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 411)
+0/69092	Loss: 93.207
+3200/69092	Loss: 92.878
+6400/69092	Loss: 91.821
+9600/69092	Loss: 92.161
+12800/69092	Loss: 92.381
+16000/69092	Loss: 93.821
+19200/69092	Loss: 93.307
+22400/69092	Loss: 92.035
+25600/69092	Loss: 93.219
+28800/69092	Loss: 92.943
+32000/69092	Loss: 92.589
+35200/69092	Loss: 92.745
+38400/69092	Loss: 93.047
+41600/69092	Loss: 91.810
+44800/69092	Loss: 92.287
+48000/69092	Loss: 93.075
+51200/69092	Loss: 93.894
+54400/69092	Loss: 92.598
+57600/69092	Loss: 92.557
+60800/69092	Loss: 93.418
+64000/69092	Loss: 92.871
+67200/69092	Loss: 94.204
+Training time 0:10:04.269922
+Epoch: 133 Average loss: 92.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 412)
+0/69092	Loss: 95.815
+3200/69092	Loss: 91.796
+6400/69092	Loss: 93.268
+9600/69092	Loss: 92.160
+12800/69092	Loss: 93.307
+16000/69092	Loss: 92.116
+19200/69092	Loss: 93.080
+22400/69092	Loss: 92.102
+25600/69092	Loss: 93.933
+28800/69092	Loss: 92.353
+32000/69092	Loss: 92.734
+35200/69092	Loss: 93.464
+38400/69092	Loss: 94.395
+41600/69092	Loss: 93.934
+44800/69092	Loss: 93.643
+48000/69092	Loss: 93.663
+51200/69092	Loss: 92.442
+54400/69092	Loss: 91.788
+57600/69092	Loss: 92.589
+60800/69092	Loss: 93.192
+64000/69092	Loss: 94.311
+67200/69092	Loss: 93.025
+Training time 0:10:04.276959
+Epoch: 134 Average loss: 93.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 413)
+0/69092	Loss: 96.029
+3200/69092	Loss: 92.543
+6400/69092	Loss: 92.354
+9600/69092	Loss: 92.196
+12800/69092	Loss: 92.613
+16000/69092	Loss: 93.342
+19200/69092	Loss: 94.706
+22400/69092	Loss: 93.770
+25600/69092	Loss: 93.232
+28800/69092	Loss: 93.728
+32000/69092	Loss: 92.380
+35200/69092	Loss: 92.904
+38400/69092	Loss: 93.974
+41600/69092	Loss: 92.652
+44800/69092	Loss: 93.805
+48000/69092	Loss: 93.695
+51200/69092	Loss: 92.491
+54400/69092	Loss: 93.166
+57600/69092	Loss: 93.815
+60800/69092	Loss: 92.654
+64000/69092	Loss: 92.171
+67200/69092	Loss: 91.781
+Training time 0:10:59.850583
+Epoch: 135 Average loss: 93.01
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 414)
+0/69092	Loss: 95.098
+3200/69092	Loss: 94.281
+6400/69092	Loss: 93.102
+9600/69092	Loss: 92.027
+12800/69092	Loss: 94.561
+16000/69092	Loss: 91.357
+19200/69092	Loss: 92.438
+22400/69092	Loss: 93.048
+25600/69092	Loss: 94.280
+28800/69092	Loss: 91.933
+32000/69092	Loss: 93.188
+35200/69092	Loss: 92.309
+38400/69092	Loss: 94.220
+41600/69092	Loss: 92.865
+44800/69092	Loss: 92.582
+48000/69092	Loss: 92.289
+51200/69092	Loss: 92.623
+54400/69092	Loss: 92.547
+57600/69092	Loss: 94.436
+60800/69092	Loss: 92.077
+64000/69092	Loss: 92.514
+67200/69092	Loss: 93.932
+Training time 0:10:36.400766
+Epoch: 136 Average loss: 92.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 415)
+0/69092	Loss: 93.723
+3200/69092	Loss: 93.254
+6400/69092	Loss: 92.740
+9600/69092	Loss: 91.423
+12800/69092	Loss: 92.415
+16000/69092	Loss: 92.553
+19200/69092	Loss: 92.836
+22400/69092	Loss: 93.249
+25600/69092	Loss: 92.435
+28800/69092	Loss: 94.443
+32000/69092	Loss: 92.792
+35200/69092	Loss: 93.931
+38400/69092	Loss: 93.294
+41600/69092	Loss: 92.864
+44800/69092	Loss: 93.080
+48000/69092	Loss: 93.300
+51200/69092	Loss: 92.678
+54400/69092	Loss: 92.800
+57600/69092	Loss: 94.014
+60800/69092	Loss: 93.319
+64000/69092	Loss: 93.552
+67200/69092	Loss: 93.351
+Training time 0:10:46.625126
+Epoch: 137 Average loss: 93.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 416)
+0/69092	Loss: 83.073
+3200/69092	Loss: 92.685
+6400/69092	Loss: 94.249
+9600/69092	Loss: 91.166
+12800/69092	Loss: 93.139
+16000/69092	Loss: 94.625
+19200/69092	Loss: 93.245
+22400/69092	Loss: 92.896
+25600/69092	Loss: 93.215
+28800/69092	Loss: 92.936
+32000/69092	Loss: 93.682
+35200/69092	Loss: 93.277
+38400/69092	Loss: 92.487
+41600/69092	Loss: 92.163
+44800/69092	Loss: 92.388
+48000/69092	Loss: 92.107
+51200/69092	Loss: 93.174
+54400/69092	Loss: 93.597
+57600/69092	Loss: 93.263
+60800/69092	Loss: 92.878
+64000/69092	Loss: 91.622
+67200/69092	Loss: 92.843
+Training time 0:10:38.082873
+Epoch: 138 Average loss: 92.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 417)
+0/69092	Loss: 84.538
+3200/69092	Loss: 92.483
+6400/69092	Loss: 91.764
+9600/69092	Loss: 93.084
+12800/69092	Loss: 91.997
+16000/69092	Loss: 92.692
+19200/69092	Loss: 93.185
+22400/69092	Loss: 92.357
+25600/69092	Loss: 92.564
+28800/69092	Loss: 93.586
+32000/69092	Loss: 93.415
+35200/69092	Loss: 94.352
+38400/69092	Loss: 92.790
+41600/69092	Loss: 93.303
+44800/69092	Loss: 94.855
+48000/69092	Loss: 93.431
+51200/69092	Loss: 94.643
+54400/69092	Loss: 93.406
+57600/69092	Loss: 92.656
+60800/69092	Loss: 92.678
+64000/69092	Loss: 92.930
+67200/69092	Loss: 92.387
+Training time 0:10:31.526656
+Epoch: 139 Average loss: 93.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 418)
+0/69092	Loss: 89.698
+3200/69092	Loss: 93.729
+6400/69092	Loss: 92.970
+9600/69092	Loss: 92.804
+12800/69092	Loss: 92.160
+16000/69092	Loss: 92.843
+19200/69092	Loss: 93.642
+22400/69092	Loss: 92.238
+25600/69092	Loss: 92.019
+28800/69092	Loss: 92.808
+32000/69092	Loss: 91.063
+35200/69092	Loss: 94.019
+38400/69092	Loss: 92.879
+41600/69092	Loss: 92.326
+44800/69092	Loss: 92.767
+48000/69092	Loss: 91.848
+51200/69092	Loss: 93.054
+54400/69092	Loss: 93.977
+57600/69092	Loss: 93.319
+60800/69092	Loss: 93.594
+64000/69092	Loss: 92.563
+67200/69092	Loss: 93.264
+Training time 0:10:33.874226
+Epoch: 140 Average loss: 92.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 419)
+0/69092	Loss: 91.154
+3200/69092	Loss: 93.618
+6400/69092	Loss: 94.282
+9600/69092	Loss: 92.971
+12800/69092	Loss: 91.736
+16000/69092	Loss: 92.483
+19200/69092	Loss: 92.561
+22400/69092	Loss: 93.544
+25600/69092	Loss: 92.295
+28800/69092	Loss: 93.888
+32000/69092	Loss: 92.345
+35200/69092	Loss: 94.055
+38400/69092	Loss: 92.691
+41600/69092	Loss: 93.083
+44800/69092	Loss: 92.989
+48000/69092	Loss: 92.051
+51200/69092	Loss: 93.164
+54400/69092	Loss: 93.679
+57600/69092	Loss: 92.144
+60800/69092	Loss: 92.188
+64000/69092	Loss: 93.344
+67200/69092	Loss: 92.635
+Training time 0:10:36.839920
+Epoch: 141 Average loss: 92.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 420)
+0/69092	Loss: 83.899
+3200/69092	Loss: 92.778
+6400/69092	Loss: 92.069
+9600/69092	Loss: 92.756
+12800/69092	Loss: 91.874
+16000/69092	Loss: 93.649
+19200/69092	Loss: 92.758
+22400/69092	Loss: 92.600
+25600/69092	Loss: 92.993
+28800/69092	Loss: 93.549
+32000/69092	Loss: 94.084
+35200/69092	Loss: 93.365
+38400/69092	Loss: 94.286
+41600/69092	Loss: 91.596
+44800/69092	Loss: 92.703
+48000/69092	Loss: 92.240
+51200/69092	Loss: 92.672
+54400/69092	Loss: 92.783
+57600/69092	Loss: 92.782
+60800/69092	Loss: 93.148
+64000/69092	Loss: 91.929
+67200/69092	Loss: 92.755
+Training time 0:10:39.495611
+Epoch: 142 Average loss: 92.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 421)
+0/69092	Loss: 97.825
+3200/69092	Loss: 93.288
+6400/69092	Loss: 93.094
+9600/69092	Loss: 92.260
+12800/69092	Loss: 92.941
+16000/69092	Loss: 93.603
+19200/69092	Loss: 93.006
+22400/69092	Loss: 93.695
+25600/69092	Loss: 93.251
+28800/69092	Loss: 92.894
+32000/69092	Loss: 92.698
+35200/69092	Loss: 92.797
+38400/69092	Loss: 90.492
+41600/69092	Loss: 91.992
+44800/69092	Loss: 92.887
+48000/69092	Loss: 93.263
+51200/69092	Loss: 93.575
+54400/69092	Loss: 92.437
+57600/69092	Loss: 92.324
+60800/69092	Loss: 93.326
+64000/69092	Loss: 94.074
+67200/69092	Loss: 92.197
+Training time 0:10:38.455544
+Epoch: 143 Average loss: 92.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 422)
+0/69092	Loss: 90.894
+3200/69092	Loss: 91.916
+6400/69092	Loss: 91.427
+9600/69092	Loss: 93.712
+12800/69092	Loss: 94.001
+16000/69092	Loss: 93.151
+19200/69092	Loss: 92.549
+22400/69092	Loss: 92.010
+25600/69092	Loss: 92.871
+28800/69092	Loss: 93.270
+32000/69092	Loss: 94.491
+35200/69092	Loss: 92.157
+38400/69092	Loss: 93.929
+41600/69092	Loss: 91.636
+44800/69092	Loss: 93.549
+48000/69092	Loss: 92.356
+51200/69092	Loss: 93.653
+54400/69092	Loss: 93.757
+57600/69092	Loss: 91.801
+60800/69092	Loss: 93.015
+64000/69092	Loss: 92.028
+67200/69092	Loss: 93.175
+Training time 0:10:13.981074
+Epoch: 144 Average loss: 92.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 423)
+0/69092	Loss: 104.413
+3200/69092	Loss: 92.388
+6400/69092	Loss: 91.732
+9600/69092	Loss: 92.339
+12800/69092	Loss: 94.161
+16000/69092	Loss: 92.366
+19200/69092	Loss: 93.041
+22400/69092	Loss: 93.785
+25600/69092	Loss: 92.204
+28800/69092	Loss: 93.527
+32000/69092	Loss: 94.112
+35200/69092	Loss: 94.044
+38400/69092	Loss: 93.299
+41600/69092	Loss: 93.159
+44800/69092	Loss: 93.798
+48000/69092	Loss: 92.750
+51200/69092	Loss: 92.404
+54400/69092	Loss: 92.520
+57600/69092	Loss: 92.371
+60800/69092	Loss: 91.477
+64000/69092	Loss: 93.162
+67200/69092	Loss: 91.925
+Training time 0:10:35.682296
+Epoch: 145 Average loss: 92.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 424)
+0/69092	Loss: 89.356
+3200/69092	Loss: 93.536
+6400/69092	Loss: 92.218
+9600/69092	Loss: 92.449
+12800/69092	Loss: 92.867
+16000/69092	Loss: 91.542
+19200/69092	Loss: 91.271
+22400/69092	Loss: 91.859
+25600/69092	Loss: 92.772
+28800/69092	Loss: 93.386
+32000/69092	Loss: 93.342
+35200/69092	Loss: 93.441
+38400/69092	Loss: 93.085
+41600/69092	Loss: 93.765
+44800/69092	Loss: 92.729
+48000/69092	Loss: 93.216
+51200/69092	Loss: 92.087
+54400/69092	Loss: 92.072
+57600/69092	Loss: 93.404
+60800/69092	Loss: 93.825
+64000/69092	Loss: 93.335
+67200/69092	Loss: 93.914
+Training time 0:10:30.771325
+Epoch: 146 Average loss: 92.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 425)
+0/69092	Loss: 101.423
+3200/69092	Loss: 93.674
+6400/69092	Loss: 92.133
+9600/69092	Loss: 93.390
+12800/69092	Loss: 92.812
+16000/69092	Loss: 93.253
+19200/69092	Loss: 93.861
+22400/69092	Loss: 91.644
+25600/69092	Loss: 92.594
+28800/69092	Loss: 93.106
+32000/69092	Loss: 93.050
+35200/69092	Loss: 93.248
+38400/69092	Loss: 93.993
+41600/69092	Loss: 92.544
+44800/69092	Loss: 92.994
+48000/69092	Loss: 92.434
+51200/69092	Loss: 92.495
+54400/69092	Loss: 93.254
+57600/69092	Loss: 93.568
+60800/69092	Loss: 93.049
+64000/69092	Loss: 93.536
+67200/69092	Loss: 91.718
+Training time 0:10:39.887029
+Epoch: 147 Average loss: 93.01
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 426)
+0/69092	Loss: 82.522
+3200/69092	Loss: 92.492
+6400/69092	Loss: 92.481
+9600/69092	Loss: 92.860
+12800/69092	Loss: 92.540
+16000/69092	Loss: 92.853
+19200/69092	Loss: 93.533
+22400/69092	Loss: 93.401
+25600/69092	Loss: 93.694
+28800/69092	Loss: 92.160
+32000/69092	Loss: 93.058
+35200/69092	Loss: 93.053
+38400/69092	Loss: 92.013
+41600/69092	Loss: 92.034
+44800/69092	Loss: 91.935
+48000/69092	Loss: 92.554
+51200/69092	Loss: 91.733
+54400/69092	Loss: 92.891
+57600/69092	Loss: 93.490
+60800/69092	Loss: 93.728
+64000/69092	Loss: 92.161
+67200/69092	Loss: 92.819
+Training time 0:10:38.454582
+Epoch: 148 Average loss: 92.72
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 427)
+0/69092	Loss: 94.332
+3200/69092	Loss: 91.162
+6400/69092	Loss: 92.746
+9600/69092	Loss: 92.496
+12800/69092	Loss: 93.606
+16000/69092	Loss: 91.950
+19200/69092	Loss: 92.480
+22400/69092	Loss: 93.707
+25600/69092	Loss: 94.140
+28800/69092	Loss: 92.761
+32000/69092	Loss: 92.878
+35200/69092	Loss: 92.131
+38400/69092	Loss: 91.730
+41600/69092	Loss: 92.214
+44800/69092	Loss: 92.513
+48000/69092	Loss: 92.412
+51200/69092	Loss: 94.266
+54400/69092	Loss: 93.336
+57600/69092	Loss: 93.120
+60800/69092	Loss: 93.477
+64000/69092	Loss: 91.787
+67200/69092	Loss: 93.768
+Training time 0:10:51.682157
+Epoch: 149 Average loss: 92.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 428)
+0/69092	Loss: 97.419
+3200/69092	Loss: 93.700
+6400/69092	Loss: 92.978
+9600/69092	Loss: 92.343
+12800/69092	Loss: 92.202
+16000/69092	Loss: 93.202
+19200/69092	Loss: 91.335
+22400/69092	Loss: 92.251
+25600/69092	Loss: 92.886
+28800/69092	Loss: 93.881
+32000/69092	Loss: 93.772
+35200/69092	Loss: 93.186
+38400/69092	Loss: 93.336
+41600/69092	Loss: 93.024
+44800/69092	Loss: 92.387
+48000/69092	Loss: 92.079
+51200/69092	Loss: 91.588
+54400/69092	Loss: 92.114
+57600/69092	Loss: 92.234
+60800/69092	Loss: 94.003
+64000/69092	Loss: 93.736
+67200/69092	Loss: 93.493
+Training time 0:10:32.611799
+Epoch: 150 Average loss: 92.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 429)
+0/69092	Loss: 94.042
+3200/69092	Loss: 93.882
+6400/69092	Loss: 92.430
+9600/69092	Loss: 92.286
+12800/69092	Loss: 94.925
+16000/69092	Loss: 92.846
+19200/69092	Loss: 92.135
+22400/69092	Loss: 92.071
+25600/69092	Loss: 93.609
+28800/69092	Loss: 92.092
+32000/69092	Loss: 93.037
+35200/69092	Loss: 92.769
+38400/69092	Loss: 92.612
+41600/69092	Loss: 92.442
+44800/69092	Loss: 93.483
+48000/69092	Loss: 93.213
+51200/69092	Loss: 92.836
+54400/69092	Loss: 92.849
+57600/69092	Loss: 92.134
+60800/69092	Loss: 92.533
+64000/69092	Loss: 92.823
+67200/69092	Loss: 93.321
+Training time 0:10:53.980795
+Epoch: 151 Average loss: 92.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 430)
+0/69092	Loss: 88.658
+3200/69092	Loss: 92.810
+6400/69092	Loss: 93.345
+9600/69092	Loss: 93.535
+12800/69092	Loss: 92.969
+16000/69092	Loss: 94.599
+19200/69092	Loss: 93.207
+22400/69092	Loss: 93.485
+25600/69092	Loss: 92.813
+28800/69092	Loss: 91.258
+32000/69092	Loss: 92.441
+35200/69092	Loss: 92.333
+38400/69092	Loss: 93.291
+41600/69092	Loss: 92.246
+44800/69092	Loss: 92.190
+48000/69092	Loss: 92.565
+51200/69092	Loss: 92.379
+54400/69092	Loss: 93.843
+57600/69092	Loss: 93.077
+60800/69092	Loss: 93.615
+64000/69092	Loss: 92.499
+67200/69092	Loss: 91.966
+Training time 0:10:28.942846
+Epoch: 152 Average loss: 92.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 431)
+0/69092	Loss: 102.087
+3200/69092	Loss: 92.374
+6400/69092	Loss: 91.864
+9600/69092	Loss: 91.151
+12800/69092	Loss: 91.203
+16000/69092	Loss: 91.771
+19200/69092	Loss: 92.434
+22400/69092	Loss: 93.213
+25600/69092	Loss: 93.744
+28800/69092	Loss: 93.287
+32000/69092	Loss: 94.058
+35200/69092	Loss: 92.670
+38400/69092	Loss: 93.197
+41600/69092	Loss: 94.437
+44800/69092	Loss: 94.098
+48000/69092	Loss: 93.689
+51200/69092	Loss: 92.412
+54400/69092	Loss: 92.879
+57600/69092	Loss: 91.638
+60800/69092	Loss: 93.128
+64000/69092	Loss: 92.243
+67200/69092	Loss: 94.215
+Training time 0:10:30.490395
+Epoch: 153 Average loss: 92.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 432)
+0/69092	Loss: 83.173
+3200/69092	Loss: 93.030
+6400/69092	Loss: 93.077
+9600/69092	Loss: 94.095
+12800/69092	Loss: 91.667
+16000/69092	Loss: 92.354
+19200/69092	Loss: 93.146
+22400/69092	Loss: 91.985
+25600/69092	Loss: 92.529
+28800/69092	Loss: 93.015
+32000/69092	Loss: 92.307
+35200/69092	Loss: 92.896
+38400/69092	Loss: 92.455
+41600/69092	Loss: 93.323
+44800/69092	Loss: 92.593
+48000/69092	Loss: 92.467
+51200/69092	Loss: 93.519
+54400/69092	Loss: 92.836
+57600/69092	Loss: 93.026
+60800/69092	Loss: 93.938
+64000/69092	Loss: 92.617
+67200/69092	Loss: 92.414
+Training time 0:10:43.155449
+Epoch: 154 Average loss: 92.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 433)
+0/69092	Loss: 103.120
+3200/69092	Loss: 92.787
+6400/69092	Loss: 93.819
+9600/69092	Loss: 93.367
+12800/69092	Loss: 93.610
+16000/69092	Loss: 93.725
+19200/69092	Loss: 95.230
+22400/69092	Loss: 92.244
+25600/69092	Loss: 92.450
+28800/69092	Loss: 93.141
+32000/69092	Loss: 90.276
+35200/69092	Loss: 93.080
+38400/69092	Loss: 92.214
+41600/69092	Loss: 93.509
+44800/69092	Loss: 93.094
+48000/69092	Loss: 93.051
+51200/69092	Loss: 93.429
+54400/69092	Loss: 92.450
+57600/69092	Loss: 93.224
+60800/69092	Loss: 93.277
+64000/69092	Loss: 92.529
+67200/69092	Loss: 91.890
+Training time 0:10:38.340251
+Epoch: 155 Average loss: 92.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 434)
+0/69092	Loss: 90.987
+3200/69092	Loss: 92.740
+6400/69092	Loss: 92.512
+9600/69092	Loss: 94.668
+12800/69092	Loss: 92.736
+16000/69092	Loss: 91.533
+19200/69092	Loss: 92.426
+22400/69092	Loss: 92.731
+25600/69092	Loss: 92.565
+28800/69092	Loss: 92.953
+32000/69092	Loss: 92.791
+35200/69092	Loss: 92.574
+38400/69092	Loss: 91.891
+41600/69092	Loss: 93.508
+44800/69092	Loss: 91.257
+48000/69092	Loss: 93.105
+51200/69092	Loss: 91.657
+54400/69092	Loss: 92.872
+57600/69092	Loss: 93.037
+60800/69092	Loss: 92.898
+64000/69092	Loss: 92.788
+67200/69092	Loss: 94.447
+Training time 0:10:39.192905
+Epoch: 156 Average loss: 92.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 435)
+0/69092	Loss: 97.992
+3200/69092	Loss: 93.115
+6400/69092	Loss: 92.143
+9600/69092	Loss: 93.289
+12800/69092	Loss: 91.520
+16000/69092	Loss: 93.910
+19200/69092	Loss: 93.405
+22400/69092	Loss: 92.044
+25600/69092	Loss: 92.599
+28800/69092	Loss: 92.772
+32000/69092	Loss: 92.693
+35200/69092	Loss: 93.297
+38400/69092	Loss: 92.199
+41600/69092	Loss: 92.969
+44800/69092	Loss: 94.223
+48000/69092	Loss: 92.875
+51200/69092	Loss: 92.817
+54400/69092	Loss: 94.291
+57600/69092	Loss: 92.057
+60800/69092	Loss: 92.360
+64000/69092	Loss: 91.728
+67200/69092	Loss: 93.170
+Training time 0:11:35.168481
+Epoch: 157 Average loss: 92.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 436)
+0/69092	Loss: 92.065
+3200/69092	Loss: 92.700
+6400/69092	Loss: 93.842
+9600/69092	Loss: 93.038
+12800/69092	Loss: 91.883
+16000/69092	Loss: 92.705
+19200/69092	Loss: 91.840
+22400/69092	Loss: 93.197
+25600/69092	Loss: 92.719
+28800/69092	Loss: 92.529
+32000/69092	Loss: 92.895
+35200/69092	Loss: 91.699
+38400/69092	Loss: 92.395
+41600/69092	Loss: 94.089
+44800/69092	Loss: 92.500
+48000/69092	Loss: 92.667
+51200/69092	Loss: 93.456
+54400/69092	Loss: 91.206
+57600/69092	Loss: 92.393
+60800/69092	Loss: 93.445
+64000/69092	Loss: 92.554
+67200/69092	Loss: 93.267
+Training time 0:11:09.459121
+Epoch: 158 Average loss: 92.69
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 437)
+0/69092	Loss: 99.344
+3200/69092	Loss: 91.585
+6400/69092	Loss: 93.008
+9600/69092	Loss: 93.073
+12800/69092	Loss: 93.788
+16000/69092	Loss: 91.790
+19200/69092	Loss: 93.268
+22400/69092	Loss: 92.151
+25600/69092	Loss: 92.697
+28800/69092	Loss: 92.211
+32000/69092	Loss: 91.837
+35200/69092	Loss: 93.241
+38400/69092	Loss: 92.424
+41600/69092	Loss: 93.267
+44800/69092	Loss: 93.277
+48000/69092	Loss: 93.537
+51200/69092	Loss: 92.476
+54400/69092	Loss: 92.203
+57600/69092	Loss: 93.006
+60800/69092	Loss: 93.362
+64000/69092	Loss: 92.736
+67200/69092	Loss: 94.273
+Training time 0:11:22.310285
+Epoch: 159 Average loss: 92.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 438)
+0/69092	Loss: 90.908
+3200/69092	Loss: 91.694
+6400/69092	Loss: 92.887
+9600/69092	Loss: 92.846
+12800/69092	Loss: 93.420
+16000/69092	Loss: 90.729
+19200/69092	Loss: 93.893
+22400/69092	Loss: 91.621
+25600/69092	Loss: 92.845
+28800/69092	Loss: 91.687
+32000/69092	Loss: 92.533
+35200/69092	Loss: 92.680
+38400/69092	Loss: 93.147
+41600/69092	Loss: 92.878
+44800/69092	Loss: 92.820
+48000/69092	Loss: 93.196
+51200/69092	Loss: 92.597
+54400/69092	Loss: 94.920
+57600/69092	Loss: 92.636
+60800/69092	Loss: 93.071
+64000/69092	Loss: 91.582
+67200/69092	Loss: 93.103
+Training time 0:10:59.184643
+Epoch: 160 Average loss: 92.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 439)
+0/69092	Loss: 94.952
+3200/69092	Loss: 92.177
+6400/69092	Loss: 94.629
+9600/69092	Loss: 93.266
+12800/69092	Loss: 92.670
+16000/69092	Loss: 91.086
+19200/69092	Loss: 92.305
+22400/69092	Loss: 94.199
+25600/69092	Loss: 93.500
+28800/69092	Loss: 93.080
+32000/69092	Loss: 92.591
+35200/69092	Loss: 92.554
+38400/69092	Loss: 92.200
+41600/69092	Loss: 92.432
+44800/69092	Loss: 92.504
+48000/69092	Loss: 93.211
+51200/69092	Loss: 92.318
+54400/69092	Loss: 92.699
+57600/69092	Loss: 92.347
+60800/69092	Loss: 92.598
+64000/69092	Loss: 92.230
+67200/69092	Loss: 93.321
+Training time 0:11:21.028169
+Epoch: 161 Average loss: 92.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 440)
+0/69092	Loss: 92.402
+3200/69092	Loss: 92.545
+6400/69092	Loss: 92.410
+9600/69092	Loss: 92.444
+12800/69092	Loss: 93.641
+16000/69092	Loss: 91.989
+19200/69092	Loss: 92.751
+22400/69092	Loss: 91.664
+25600/69092	Loss: 92.504
+28800/69092	Loss: 93.056
+32000/69092	Loss: 92.495
+35200/69092	Loss: 92.511
+38400/69092	Loss: 92.549
+41600/69092	Loss: 92.764
+44800/69092	Loss: 93.110
+48000/69092	Loss: 93.157
+51200/69092	Loss: 92.351
+54400/69092	Loss: 94.744
+57600/69092	Loss: 92.229
+60800/69092	Loss: 91.876
+64000/69092	Loss: 93.223
+67200/69092	Loss: 92.951
+Training time 0:11:56.227905
+Epoch: 162 Average loss: 92.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 441)
+0/69092	Loss: 100.154
+3200/69092	Loss: 91.521
+6400/69092	Loss: 92.523
+9600/69092	Loss: 91.553
+12800/69092	Loss: 92.128
+16000/69092	Loss: 94.121
+19200/69092	Loss: 92.589
+22400/69092	Loss: 92.929
+25600/69092	Loss: 91.780
+28800/69092	Loss: 92.307
+32000/69092	Loss: 93.191
+35200/69092	Loss: 92.857
+38400/69092	Loss: 92.768
+41600/69092	Loss: 92.521
+44800/69092	Loss: 94.326
+48000/69092	Loss: 92.633
+51200/69092	Loss: 93.447
+54400/69092	Loss: 92.513
+57600/69092	Loss: 95.053
+60800/69092	Loss: 92.998
+64000/69092	Loss: 92.526
+67200/69092	Loss: 93.215
+Training time 0:14:26.862560
+Epoch: 163 Average loss: 92.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 442)
+0/69092	Loss: 90.839
+3200/69092	Loss: 91.524
+6400/69092	Loss: 92.355
+9600/69092	Loss: 92.871
+12800/69092	Loss: 91.255
+16000/69092	Loss: 92.741
+19200/69092	Loss: 92.673
+22400/69092	Loss: 92.434
+25600/69092	Loss: 91.646
+28800/69092	Loss: 92.801
+32000/69092	Loss: 92.603
+35200/69092	Loss: 94.120
+38400/69092	Loss: 92.599
+41600/69092	Loss: 92.280
+44800/69092	Loss: 93.647
+48000/69092	Loss: 93.144
+51200/69092	Loss: 92.409
+54400/69092	Loss: 93.433
+57600/69092	Loss: 93.739
+60800/69092	Loss: 94.157
+64000/69092	Loss: 92.826
+67200/69092	Loss: 92.880
+Training time 0:11:23.589847
+Epoch: 164 Average loss: 92.73
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 443)
+0/69092	Loss: 97.982
+3200/69092	Loss: 91.516
+6400/69092	Loss: 91.544
+9600/69092	Loss: 92.972
+12800/69092	Loss: 93.560
+16000/69092	Loss: 92.869
+19200/69092	Loss: 92.897
+22400/69092	Loss: 92.610
+25600/69092	Loss: 92.667
+28800/69092	Loss: 91.959
+32000/69092	Loss: 91.774
+35200/69092	Loss: 92.412
+38400/69092	Loss: 92.780
+41600/69092	Loss: 94.373
+44800/69092	Loss: 92.833
+48000/69092	Loss: 93.547
+51200/69092	Loss: 92.515
+54400/69092	Loss: 92.601
+57600/69092	Loss: 92.428
+60800/69092	Loss: 92.510
+64000/69092	Loss: 93.201
+67200/69092	Loss: 92.349
+Training time 0:11:07.633772
+Epoch: 165 Average loss: 92.72
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 444)
+0/69092	Loss: 90.887
+3200/69092	Loss: 93.536
+6400/69092	Loss: 92.283
+9600/69092	Loss: 91.533
+12800/69092	Loss: 92.279
+16000/69092	Loss: 91.654
+19200/69092	Loss: 90.824
+22400/69092	Loss: 93.798
+25600/69092	Loss: 93.047
+28800/69092	Loss: 93.303
+32000/69092	Loss: 92.739
+35200/69092	Loss: 93.785
+38400/69092	Loss: 91.458
+41600/69092	Loss: 91.973
+44800/69092	Loss: 92.394
+48000/69092	Loss: 91.556
+51200/69092	Loss: 92.645
+54400/69092	Loss: 93.173
+57600/69092	Loss: 93.159
+60800/69092	Loss: 93.056
+64000/69092	Loss: 92.762
+67200/69092	Loss: 93.991
+Training time 0:10:20.514311
+Epoch: 166 Average loss: 92.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 445)
+0/69092	Loss: 93.494
+3200/69092	Loss: 91.970
+6400/69092	Loss: 93.435
+9600/69092	Loss: 92.003
+12800/69092	Loss: 91.916
+16000/69092	Loss: 92.947
+19200/69092	Loss: 92.408
+22400/69092	Loss: 93.012
+25600/69092	Loss: 93.882
+28800/69092	Loss: 91.818
+32000/69092	Loss: 91.754
+35200/69092	Loss: 94.543
+38400/69092	Loss: 92.568
+41600/69092	Loss: 93.018
+44800/69092	Loss: 91.753
+48000/69092	Loss: 92.220
+51200/69092	Loss: 91.576
+54400/69092	Loss: 91.339
+57600/69092	Loss: 93.548
+60800/69092	Loss: 94.048
+64000/69092	Loss: 92.063
+67200/69092	Loss: 93.065
+Training time 0:10:56.164581
+Epoch: 167 Average loss: 92.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 446)
+0/69092	Loss: 90.560
+3200/69092	Loss: 91.919
+6400/69092	Loss: 92.691
+9600/69092	Loss: 93.532
+12800/69092	Loss: 93.153
+16000/69092	Loss: 93.061
+19200/69092	Loss: 92.376
+22400/69092	Loss: 92.599
+25600/69092	Loss: 92.373
+28800/69092	Loss: 93.244
+32000/69092	Loss: 92.755
+35200/69092	Loss: 92.788
+38400/69092	Loss: 93.401
+41600/69092	Loss: 93.271
+44800/69092	Loss: 93.963
+48000/69092	Loss: 92.309
+51200/69092	Loss: 93.145
+54400/69092	Loss: 93.192
+57600/69092	Loss: 91.803
+60800/69092	Loss: 92.540
+64000/69092	Loss: 93.315
+67200/69092	Loss: 91.833
+Training time 0:10:31.015599
+Epoch: 168 Average loss: 92.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 447)
+0/69092	Loss: 93.882
+3200/69092	Loss: 93.591
+6400/69092	Loss: 93.615
+9600/69092	Loss: 92.101
+12800/69092	Loss: 91.429
+16000/69092	Loss: 93.371
+19200/69092	Loss: 92.655
+22400/69092	Loss: 93.453
+25600/69092	Loss: 92.498
+28800/69092	Loss: 93.157
+32000/69092	Loss: 91.542
+35200/69092	Loss: 92.817
+38400/69092	Loss: 92.345
+41600/69092	Loss: 92.896
+44800/69092	Loss: 93.575
+48000/69092	Loss: 91.823
+51200/69092	Loss: 92.919
+54400/69092	Loss: 92.022
+57600/69092	Loss: 92.067
+60800/69092	Loss: 92.513
+64000/69092	Loss: 92.290
+67200/69092	Loss: 93.124
+Training time 0:10:21.042751
+Epoch: 169 Average loss: 92.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 448)
+0/69092	Loss: 103.285
+3200/69092	Loss: 93.666
+6400/69092	Loss: 93.684
+9600/69092	Loss: 91.306
+12800/69092	Loss: 92.302
+16000/69092	Loss: 93.916
+19200/69092	Loss: 92.740
+22400/69092	Loss: 91.915
+25600/69092	Loss: 91.330
+28800/69092	Loss: 92.101
+32000/69092	Loss: 90.521
+35200/69092	Loss: 91.957
+38400/69092	Loss: 92.475
+41600/69092	Loss: 93.507
+44800/69092	Loss: 92.725
+48000/69092	Loss: 93.816
+51200/69092	Loss: 92.967
+54400/69092	Loss: 92.237
+57600/69092	Loss: 92.127
+60800/69092	Loss: 93.455
+64000/69092	Loss: 92.980
+67200/69092	Loss: 92.201
+Training time 0:10:26.782398
+Epoch: 170 Average loss: 92.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 449)
+0/69092	Loss: 87.156
+3200/69092	Loss: 91.641
+6400/69092	Loss: 93.449
+9600/69092	Loss: 92.240
+12800/69092	Loss: 93.877
+16000/69092	Loss: 92.015
+19200/69092	Loss: 92.658
+22400/69092	Loss: 92.695
+25600/69092	Loss: 94.481
+28800/69092	Loss: 90.406
+32000/69092	Loss: 91.478
+35200/69092	Loss: 91.058
+38400/69092	Loss: 92.694
+41600/69092	Loss: 91.006
+44800/69092	Loss: 92.159
+48000/69092	Loss: 93.657
+51200/69092	Loss: 93.565
+54400/69092	Loss: 92.680
+57600/69092	Loss: 92.646
+60800/69092	Loss: 94.558
+64000/69092	Loss: 92.886
+67200/69092	Loss: 93.612
+Training time 0:10:42.963639
+Epoch: 171 Average loss: 92.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 450)
+0/69092	Loss: 84.385
+3200/69092	Loss: 93.089
+6400/69092	Loss: 91.851
+9600/69092	Loss: 92.672
+12800/69092	Loss: 93.035
+16000/69092	Loss: 92.405
+19200/69092	Loss: 92.007
+22400/69092	Loss: 92.916
+25600/69092	Loss: 91.622
+28800/69092	Loss: 93.539
+32000/69092	Loss: 93.928
+35200/69092	Loss: 93.043
+38400/69092	Loss: 92.519
+41600/69092	Loss: 92.308
+44800/69092	Loss: 92.966
+48000/69092	Loss: 92.310
+51200/69092	Loss: 92.362
+54400/69092	Loss: 92.594
+57600/69092	Loss: 91.638
+60800/69092	Loss: 91.898
+64000/69092	Loss: 93.718
+67200/69092	Loss: 92.159
+Training time 0:10:22.760602
+Epoch: 172 Average loss: 92.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 451)
+0/69092	Loss: 90.252
+3200/69092	Loss: 92.456
+6400/69092	Loss: 92.929
+9600/69092	Loss: 91.999
+12800/69092	Loss: 93.072
+16000/69092	Loss: 91.577
+19200/69092	Loss: 92.841
+22400/69092	Loss: 93.241
+25600/69092	Loss: 92.856
+28800/69092	Loss: 93.055
+32000/69092	Loss: 93.222
+35200/69092	Loss: 94.372
+38400/69092	Loss: 93.372
+41600/69092	Loss: 92.259
+44800/69092	Loss: 92.712
+48000/69092	Loss: 91.906
+51200/69092	Loss: 93.420
+54400/69092	Loss: 92.562
+57600/69092	Loss: 92.518
+60800/69092	Loss: 93.032
+64000/69092	Loss: 91.319
+67200/69092	Loss: 91.820
+Training time 0:10:57.946468
+Epoch: 173 Average loss: 92.71
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 452)
+0/69092	Loss: 91.930
+3200/69092	Loss: 93.453
+6400/69092	Loss: 91.731
+9600/69092	Loss: 92.870
+12800/69092	Loss: 91.697
+16000/69092	Loss: 92.753
+19200/69092	Loss: 92.857
+22400/69092	Loss: 93.258
+25600/69092	Loss: 92.915
+28800/69092	Loss: 92.205
+32000/69092	Loss: 93.165
+35200/69092	Loss: 92.251
+38400/69092	Loss: 93.386
+41600/69092	Loss: 93.801
+44800/69092	Loss: 92.312
+48000/69092	Loss: 92.315
+51200/69092	Loss: 92.373
+54400/69092	Loss: 92.062
+57600/69092	Loss: 92.035
+60800/69092	Loss: 93.666
+64000/69092	Loss: 92.560
+67200/69092	Loss: 91.099
+Training time 0:10:41.318035
+Epoch: 174 Average loss: 92.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 453)
+0/69092	Loss: 82.586
+3200/69092	Loss: 93.251
+6400/69092	Loss: 92.397
+9600/69092	Loss: 92.935
+12800/69092	Loss: 92.876
+16000/69092	Loss: 91.954
+19200/69092	Loss: 92.968
+22400/69092	Loss: 92.790
+25600/69092	Loss: 92.764
+28800/69092	Loss: 92.401
+32000/69092	Loss: 94.146
+35200/69092	Loss: 93.090
+38400/69092	Loss: 92.904
+41600/69092	Loss: 92.034
+44800/69092	Loss: 92.973
+48000/69092	Loss: 92.423
+51200/69092	Loss: 93.674
+54400/69092	Loss: 91.698
+57600/69092	Loss: 91.945
+60800/69092	Loss: 92.933
+64000/69092	Loss: 93.204
+67200/69092	Loss: 92.511
+Training time 0:10:45.669945
+Epoch: 175 Average loss: 92.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 454)
+0/69092	Loss: 88.391
+3200/69092	Loss: 92.528
+6400/69092	Loss: 92.982
+9600/69092	Loss: 92.507
+12800/69092	Loss: 93.359
+16000/69092	Loss: 91.904
+19200/69092	Loss: 92.416
+22400/69092	Loss: 92.454
+25600/69092	Loss: 93.473
+28800/69092	Loss: 92.864
+32000/69092	Loss: 91.651
+35200/69092	Loss: 92.862
+38400/69092	Loss: 91.972
+41600/69092	Loss: 93.798
+44800/69092	Loss: 92.918
+48000/69092	Loss: 93.156
+51200/69092	Loss: 92.729
+54400/69092	Loss: 94.296
+57600/69092	Loss: 92.130
+60800/69092	Loss: 92.243
+64000/69092	Loss: 92.266
+67200/69092	Loss: 92.665
+Training time 0:10:38.643054
+Epoch: 176 Average loss: 92.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 455)
+0/69092	Loss: 83.928
+3200/69092	Loss: 92.335
+6400/69092	Loss: 92.905
+9600/69092	Loss: 92.988
+12800/69092	Loss: 92.964
+16000/69092	Loss: 92.387
+19200/69092	Loss: 94.349
+22400/69092	Loss: 93.665
+25600/69092	Loss: 91.839
+28800/69092	Loss: 91.781
+32000/69092	Loss: 90.829
+35200/69092	Loss: 92.898
+38400/69092	Loss: 91.968
+41600/69092	Loss: 92.870
+44800/69092	Loss: 92.918
+48000/69092	Loss: 93.163
+51200/69092	Loss: 92.666
+54400/69092	Loss: 91.964
+57600/69092	Loss: 91.282
+60800/69092	Loss: 93.389
+64000/69092	Loss: 91.629
+67200/69092	Loss: 93.425
+Training time 0:11:11.368907
+Epoch: 177 Average loss: 92.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 456)
+0/69092	Loss: 83.436
+3200/69092	Loss: 93.696
+6400/69092	Loss: 91.353
+9600/69092	Loss: 91.755
+12800/69092	Loss: 92.184
+16000/69092	Loss: 92.313
+19200/69092	Loss: 92.749
+22400/69092	Loss: 90.866
+25600/69092	Loss: 93.148
+28800/69092	Loss: 92.560
+32000/69092	Loss: 92.564
+35200/69092	Loss: 92.717
+38400/69092	Loss: 92.202
+41600/69092	Loss: 93.448
+44800/69092	Loss: 91.946
+48000/69092	Loss: 93.629
+51200/69092	Loss: 92.672
+54400/69092	Loss: 93.566
+57600/69092	Loss: 92.906
+60800/69092	Loss: 92.986
+64000/69092	Loss: 93.440
+67200/69092	Loss: 92.533
+Training time 0:10:32.444736
+Epoch: 178 Average loss: 92.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 457)
+0/69092	Loss: 86.162
+3200/69092	Loss: 91.271
+6400/69092	Loss: 90.640
+9600/69092	Loss: 92.296
+12800/69092	Loss: 92.395
+16000/69092	Loss: 92.516
+19200/69092	Loss: 92.512
+22400/69092	Loss: 91.991
+25600/69092	Loss: 93.367
+28800/69092	Loss: 92.180
+32000/69092	Loss: 93.759
+35200/69092	Loss: 93.920
+38400/69092	Loss: 93.289
+41600/69092	Loss: 94.922
+44800/69092	Loss: 91.826
+48000/69092	Loss: 92.534
+51200/69092	Loss: 92.486
+54400/69092	Loss: 93.135
+57600/69092	Loss: 91.654
+60800/69092	Loss: 92.805
+64000/69092	Loss: 92.064
+67200/69092	Loss: 92.992
+Training time 0:10:31.600962
+Epoch: 179 Average loss: 92.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 458)
+0/69092	Loss: 89.158
+3200/69092	Loss: 93.148
+6400/69092	Loss: 92.906
+9600/69092	Loss: 91.583
+12800/69092	Loss: 92.373
+16000/69092	Loss: 91.599
+19200/69092	Loss: 92.637
+22400/69092	Loss: 92.869
+25600/69092	Loss: 92.410
+28800/69092	Loss: 92.777
+32000/69092	Loss: 93.002
+35200/69092	Loss: 93.796
+38400/69092	Loss: 92.593
+41600/69092	Loss: 92.165
+44800/69092	Loss: 91.496
+48000/69092	Loss: 93.085
+51200/69092	Loss: 92.728
+54400/69092	Loss: 93.376
+57600/69092	Loss: 91.856
+60800/69092	Loss: 93.537
+64000/69092	Loss: 92.197
+67200/69092	Loss: 92.791
+Training time 0:10:40.119288
+Epoch: 180 Average loss: 92.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 459)
+0/69092	Loss: 93.258
+3200/69092	Loss: 90.900
+6400/69092	Loss: 93.865
+9600/69092	Loss: 92.885
+12800/69092	Loss: 93.183
+16000/69092	Loss: 92.266
+19200/69092	Loss: 92.361
+22400/69092	Loss: 92.740
+25600/69092	Loss: 90.777
+28800/69092	Loss: 93.450
+32000/69092	Loss: 92.781
+35200/69092	Loss: 90.543
+38400/69092	Loss: 92.855
+41600/69092	Loss: 91.698
+44800/69092	Loss: 93.032
+48000/69092	Loss: 92.603
+51200/69092	Loss: 92.596
+54400/69092	Loss: 92.934
+57600/69092	Loss: 92.824
+60800/69092	Loss: 93.949
+64000/69092	Loss: 93.466
+67200/69092	Loss: 92.311
+Training time 0:10:52.512686
+Epoch: 181 Average loss: 92.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 460)
+0/69092	Loss: 86.120
+3200/69092	Loss: 92.113
+6400/69092	Loss: 92.283
+9600/69092	Loss: 93.856
+12800/69092	Loss: 92.229
+16000/69092	Loss: 93.213
+19200/69092	Loss: 92.442
+22400/69092	Loss: 93.274
+25600/69092	Loss: 91.560
+28800/69092	Loss: 93.002
+32000/69092	Loss: 91.572
+35200/69092	Loss: 92.197
+38400/69092	Loss: 90.301
+41600/69092	Loss: 93.663
+44800/69092	Loss: 93.376
+48000/69092	Loss: 92.500
+51200/69092	Loss: 92.471
+54400/69092	Loss: 91.995
+57600/69092	Loss: 92.888
+60800/69092	Loss: 91.116
+64000/69092	Loss: 93.169
+67200/69092	Loss: 92.923
+Training time 0:10:33.818379
+Epoch: 182 Average loss: 92.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 461)
+0/69092	Loss: 87.226
+3200/69092	Loss: 93.678
+6400/69092	Loss: 92.400
+9600/69092	Loss: 91.502
+12800/69092	Loss: 92.020
+16000/69092	Loss: 89.879
+19200/69092	Loss: 92.629
+22400/69092	Loss: 92.349
+25600/69092	Loss: 93.667
+28800/69092	Loss: 92.156
+32000/69092	Loss: 93.218
+35200/69092	Loss: 93.326
+38400/69092	Loss: 93.544
+41600/69092	Loss: 92.253
+44800/69092	Loss: 91.279
+48000/69092	Loss: 94.387
+51200/69092	Loss: 92.045
+54400/69092	Loss: 91.683
+57600/69092	Loss: 93.107
+60800/69092	Loss: 92.844
+64000/69092	Loss: 91.739
+67200/69092	Loss: 92.502
+Training time 0:10:29.321499
+Epoch: 183 Average loss: 92.53
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 462)
+0/69092	Loss: 103.018
+3200/69092	Loss: 92.706
+6400/69092	Loss: 92.266
+9600/69092	Loss: 92.676
+12800/69092	Loss: 93.383
+16000/69092	Loss: 92.799
+19200/69092	Loss: 92.630
+22400/69092	Loss: 93.472
+25600/69092	Loss: 93.238
+28800/69092	Loss: 92.351
+32000/69092	Loss: 92.212
+35200/69092	Loss: 91.585
+38400/69092	Loss: 92.610
+41600/69092	Loss: 91.825
+44800/69092	Loss: 92.440
+48000/69092	Loss: 91.657
+51200/69092	Loss: 92.552
+54400/69092	Loss: 93.105
+57600/69092	Loss: 94.083
+60800/69092	Loss: 92.704
+64000/69092	Loss: 93.204
+67200/69092	Loss: 92.770
+Training time 0:10:35.427171
+Epoch: 184 Average loss: 92.70
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 463)
+0/69092	Loss: 101.298
+3200/69092	Loss: 92.107
+6400/69092	Loss: 92.218
+9600/69092	Loss: 91.101
+12800/69092	Loss: 92.191
+16000/69092	Loss: 93.511
+19200/69092	Loss: 91.511
+22400/69092	Loss: 93.112
+25600/69092	Loss: 92.585
+28800/69092	Loss: 91.572
+32000/69092	Loss: 92.950
+35200/69092	Loss: 91.212
+38400/69092	Loss: 93.288
+41600/69092	Loss: 93.010
+44800/69092	Loss: 92.958
+48000/69092	Loss: 91.705
+51200/69092	Loss: 92.134
+54400/69092	Loss: 90.469
+57600/69092	Loss: 92.843
+60800/69092	Loss: 93.032
+64000/69092	Loss: 93.692
+67200/69092	Loss: 92.259
+Training time 0:11:02.285664
+Epoch: 185 Average loss: 92.39
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 464)
+0/69092	Loss: 94.230
+3200/69092	Loss: 92.898
+6400/69092	Loss: 92.181
+9600/69092	Loss: 93.121
+12800/69092	Loss: 91.863
+16000/69092	Loss: 92.530
+19200/69092	Loss: 92.870
+22400/69092	Loss: 92.006
+25600/69092	Loss: 93.110
+28800/69092	Loss: 92.332
+32000/69092	Loss: 92.339
+35200/69092	Loss: 93.616
+38400/69092	Loss: 92.527
+41600/69092	Loss: 92.748
+44800/69092	Loss: 92.354
+48000/69092	Loss: 92.645
+51200/69092	Loss: 92.903
+54400/69092	Loss: 92.011
+57600/69092	Loss: 93.055
+60800/69092	Loss: 92.064
+64000/69092	Loss: 91.617
+67200/69092	Loss: 93.046
+Training time 0:11:04.614186
+Epoch: 186 Average loss: 92.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 465)
+0/69092	Loss: 94.537
+3200/69092	Loss: 91.913
+6400/69092	Loss: 91.461
+9600/69092	Loss: 92.096
+12800/69092	Loss: 92.526
+16000/69092	Loss: 91.855
+19200/69092	Loss: 93.129
+22400/69092	Loss: 93.452
+25600/69092	Loss: 92.157
+28800/69092	Loss: 92.099
+32000/69092	Loss: 93.290
+35200/69092	Loss: 93.678
+38400/69092	Loss: 93.111
+41600/69092	Loss: 92.108
+44800/69092	Loss: 93.602
+48000/69092	Loss: 92.090
+51200/69092	Loss: 93.006
+54400/69092	Loss: 94.072
+57600/69092	Loss: 93.320
+60800/69092	Loss: 91.673
+64000/69092	Loss: 91.897
+67200/69092	Loss: 92.567
+Training time 0:10:40.193147
+Epoch: 187 Average loss: 92.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 466)
+0/69092	Loss: 90.278
+3200/69092	Loss: 91.407
+6400/69092	Loss: 93.088
+9600/69092	Loss: 93.036
+12800/69092	Loss: 92.580
+16000/69092	Loss: 91.596
+19200/69092	Loss: 92.700
+22400/69092	Loss: 93.023
+25600/69092	Loss: 93.418
+28800/69092	Loss: 92.939
+32000/69092	Loss: 92.595
+35200/69092	Loss: 91.702
+38400/69092	Loss: 92.677
+41600/69092	Loss: 92.524
+44800/69092	Loss: 92.354
+48000/69092	Loss: 92.348
+51200/69092	Loss: 93.573
+54400/69092	Loss: 93.214
+57600/69092	Loss: 92.145
+60800/69092	Loss: 92.430
+64000/69092	Loss: 92.550
+67200/69092	Loss: 92.699
+Training time 0:10:39.310802
+Epoch: 188 Average loss: 92.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 467)
+0/69092	Loss: 99.565
+3200/69092	Loss: 91.206
+6400/69092	Loss: 92.903
+9600/69092	Loss: 92.298
+12800/69092	Loss: 91.976
+16000/69092	Loss: 93.157
+19200/69092	Loss: 91.430
+22400/69092	Loss: 92.500
+25600/69092	Loss: 93.151
+28800/69092	Loss: 92.158
+32000/69092	Loss: 91.928
+35200/69092	Loss: 92.842
+38400/69092	Loss: 94.140
+41600/69092	Loss: 93.696
+44800/69092	Loss: 93.453
+48000/69092	Loss: 92.950
+51200/69092	Loss: 92.625
+54400/69092	Loss: 93.399
+57600/69092	Loss: 92.864
+60800/69092	Loss: 92.555
+64000/69092	Loss: 92.598
+67200/69092	Loss: 92.057
+Training time 0:10:26.294749
+Epoch: 189 Average loss: 92.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 468)
+0/69092	Loss: 85.838
+3200/69092	Loss: 91.951
+6400/69092	Loss: 91.191
+9600/69092	Loss: 92.056
+12800/69092	Loss: 94.117
+16000/69092	Loss: 94.127
+19200/69092	Loss: 92.044
+22400/69092	Loss: 91.650
+25600/69092	Loss: 92.858
+28800/69092	Loss: 93.462
+32000/69092	Loss: 92.354
+35200/69092	Loss: 92.319
+38400/69092	Loss: 92.187
+41600/69092	Loss: 92.585
+44800/69092	Loss: 93.096
+48000/69092	Loss: 92.838
+51200/69092	Loss: 91.398
+54400/69092	Loss: 91.908
+57600/69092	Loss: 93.913
+60800/69092	Loss: 91.988
+64000/69092	Loss: 91.901
+67200/69092	Loss: 92.324
+Training time 0:10:20.593176
+Epoch: 190 Average loss: 92.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 469)
+0/69092	Loss: 92.622
+3200/69092	Loss: 93.003
+6400/69092	Loss: 92.547
+9600/69092	Loss: 92.204
+12800/69092	Loss: 91.962
+16000/69092	Loss: 91.887
+19200/69092	Loss: 91.924
+22400/69092	Loss: 92.730
+25600/69092	Loss: 92.754
+28800/69092	Loss: 92.795
+32000/69092	Loss: 92.629
+35200/69092	Loss: 93.732
+38400/69092	Loss: 91.211
+41600/69092	Loss: 91.717
+44800/69092	Loss: 92.955
+48000/69092	Loss: 92.939
+51200/69092	Loss: 92.652
+54400/69092	Loss: 92.614
+57600/69092	Loss: 93.141
+60800/69092	Loss: 92.928
+64000/69092	Loss: 92.873
+67200/69092	Loss: 91.201
+Training time 0:10:27.798105
+Epoch: 191 Average loss: 92.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 470)
+0/69092	Loss: 96.099
+3200/69092	Loss: 92.184
+6400/69092	Loss: 92.081
+9600/69092	Loss: 92.690
+12800/69092	Loss: 91.783
+16000/69092	Loss: 93.174
+19200/69092	Loss: 92.695
+22400/69092	Loss: 91.656
+25600/69092	Loss: 93.218
+28800/69092	Loss: 94.121
+32000/69092	Loss: 92.712
+35200/69092	Loss: 93.155
+38400/69092	Loss: 91.690
+41600/69092	Loss: 92.591
+44800/69092	Loss: 92.888
+48000/69092	Loss: 91.969
+51200/69092	Loss: 92.458
+54400/69092	Loss: 93.482
+57600/69092	Loss: 92.603
+60800/69092	Loss: 93.017
+64000/69092	Loss: 91.957
+67200/69092	Loss: 91.439
+Training time 0:10:56.385201
+Epoch: 192 Average loss: 92.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 471)
+0/69092	Loss: 84.336
+3200/69092	Loss: 92.357
+6400/69092	Loss: 92.352
+9600/69092	Loss: 92.338
+12800/69092	Loss: 91.587
+16000/69092	Loss: 93.890
+19200/69092	Loss: 93.367
+22400/69092	Loss: 92.494
+25600/69092	Loss: 92.851
+28800/69092	Loss: 92.525
+32000/69092	Loss: 92.054
+35200/69092	Loss: 91.901
+38400/69092	Loss: 91.780
+41600/69092	Loss: 92.783
+44800/69092	Loss: 91.485
+48000/69092	Loss: 92.374
+51200/69092	Loss: 93.102
+54400/69092	Loss: 92.504
+57600/69092	Loss: 93.013
+60800/69092	Loss: 93.715
+64000/69092	Loss: 91.671
+67200/69092	Loss: 92.538
+Training time 0:10:26.126458
+Epoch: 193 Average loss: 92.50
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 472)
+0/69092	Loss: 89.818
+3200/69092	Loss: 94.018
+6400/69092	Loss: 90.942
+9600/69092	Loss: 93.684
+12800/69092	Loss: 91.798
+16000/69092	Loss: 91.883
+19200/69092	Loss: 92.467
+22400/69092	Loss: 92.450
+25600/69092	Loss: 94.195
+28800/69092	Loss: 93.936
+32000/69092	Loss: 93.713
+35200/69092	Loss: 92.489
+38400/69092	Loss: 92.968
+41600/69092	Loss: 92.700
+44800/69092	Loss: 91.922
+48000/69092	Loss: 92.163
+51200/69092	Loss: 91.745
+54400/69092	Loss: 92.315
+57600/69092	Loss: 92.008
+60800/69092	Loss: 92.013
+64000/69092	Loss: 93.017
+67200/69092	Loss: 91.755
+Training time 0:10:38.505884
+Epoch: 194 Average loss: 92.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 473)
+0/69092	Loss: 92.269
+3200/69092	Loss: 91.396
+6400/69092	Loss: 91.928
+9600/69092	Loss: 92.637
+12800/69092	Loss: 91.957
+16000/69092	Loss: 92.614
+19200/69092	Loss: 93.457
+22400/69092	Loss: 92.885
+25600/69092	Loss: 92.671
+28800/69092	Loss: 92.226
+32000/69092	Loss: 91.443
+35200/69092	Loss: 92.527
+38400/69092	Loss: 92.012
+41600/69092	Loss: 94.093
+44800/69092	Loss: 92.257
+48000/69092	Loss: 91.921
+51200/69092	Loss: 92.791
+54400/69092	Loss: 92.523
+57600/69092	Loss: 92.955
+60800/69092	Loss: 93.206
+64000/69092	Loss: 92.459
+67200/69092	Loss: 92.122
+Training time 0:11:05.959997
+Epoch: 195 Average loss: 92.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 474)
+0/69092	Loss: 91.724
+3200/69092	Loss: 91.884
+6400/69092	Loss: 92.152
+9600/69092	Loss: 92.388
+12800/69092	Loss: 92.620
+16000/69092	Loss: 91.821
+19200/69092	Loss: 92.299
+22400/69092	Loss: 92.259
+25600/69092	Loss: 92.619
+28800/69092	Loss: 92.508
+32000/69092	Loss: 91.919
+35200/69092	Loss: 91.998
+38400/69092	Loss: 92.711
+41600/69092	Loss: 92.019
+44800/69092	Loss: 92.816
+48000/69092	Loss: 92.754
+51200/69092	Loss: 93.547
+54400/69092	Loss: 92.742
+57600/69092	Loss: 92.858
+60800/69092	Loss: 92.868
+64000/69092	Loss: 93.404
+67200/69092	Loss: 92.245
+Training time 0:10:51.499053
+Epoch: 196 Average loss: 92.50
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 475)
+0/69092	Loss: 96.481
+3200/69092	Loss: 91.750
+6400/69092	Loss: 92.215
+9600/69092	Loss: 93.006
+12800/69092	Loss: 91.998
+16000/69092	Loss: 91.175
+19200/69092	Loss: 91.971
+22400/69092	Loss: 91.524
+25600/69092	Loss: 92.058
+28800/69092	Loss: 93.617
+32000/69092	Loss: 93.533
+35200/69092	Loss: 93.356
+38400/69092	Loss: 92.348
+41600/69092	Loss: 92.702
+44800/69092	Loss: 94.332
+48000/69092	Loss: 91.605
+51200/69092	Loss: 92.907
+54400/69092	Loss: 92.183
+57600/69092	Loss: 91.541
+60800/69092	Loss: 91.980
+64000/69092	Loss: 93.047
+67200/69092	Loss: 91.123
+Training time 0:10:29.424338
+Epoch: 197 Average loss: 92.42
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 476)
+0/69092	Loss: 87.769
+3200/69092	Loss: 92.669
+6400/69092	Loss: 91.453
+9600/69092	Loss: 92.485
+12800/69092	Loss: 93.129
+16000/69092	Loss: 91.369
+19200/69092	Loss: 92.321
+22400/69092	Loss: 93.134
+25600/69092	Loss: 92.215
+28800/69092	Loss: 93.010
+32000/69092	Loss: 92.574
+35200/69092	Loss: 92.627
+38400/69092	Loss: 92.220
+41600/69092	Loss: 94.017
+44800/69092	Loss: 91.105
+48000/69092	Loss: 92.115
+51200/69092	Loss: 90.874
+54400/69092	Loss: 92.496
+57600/69092	Loss: 93.233
+60800/69092	Loss: 92.243
+64000/69092	Loss: 93.127
+67200/69092	Loss: 93.025
+Training time 0:10:16.299810
+Epoch: 198 Average loss: 92.44
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 477)
+0/69092	Loss: 83.428
+3200/69092	Loss: 93.127
+6400/69092	Loss: 92.790
+9600/69092	Loss: 91.634
+12800/69092	Loss: 92.417
+16000/69092	Loss: 92.834
+19200/69092	Loss: 94.438
+22400/69092	Loss: 92.961
+25600/69092	Loss: 93.887
+28800/69092	Loss: 93.067
+32000/69092	Loss: 93.212
+35200/69092	Loss: 92.223
+38400/69092	Loss: 91.626
+41600/69092	Loss: 92.802
+44800/69092	Loss: 93.675
+48000/69092	Loss: 92.884
+51200/69092	Loss: 92.731
+54400/69092	Loss: 92.181
+57600/69092	Loss: 92.289
+60800/69092	Loss: 91.751
+64000/69092	Loss: 91.235
+67200/69092	Loss: 90.683
+Training time 0:10:48.505391
+Epoch: 199 Average loss: 92.53
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 478)
+0/69092	Loss: 91.822
+3200/69092	Loss: 92.707
+6400/69092	Loss: 93.541
+9600/69092	Loss: 92.129
+12800/69092	Loss: 94.054
+16000/69092	Loss: 92.689
+19200/69092	Loss: 91.195
+22400/69092	Loss: 91.319
+25600/69092	Loss: 92.728
+28800/69092	Loss: 91.862
+32000/69092	Loss: 92.363
+35200/69092	Loss: 93.152
+38400/69092	Loss: 92.711
+41600/69092	Loss: 91.474
+44800/69092	Loss: 92.733
+48000/69092	Loss: 92.265
+51200/69092	Loss: 91.150
+54400/69092	Loss: 92.162
+57600/69092	Loss: 93.075
+60800/69092	Loss: 92.043
+64000/69092	Loss: 92.671
+67200/69092	Loss: 93.117
+Training time 0:10:32.431884
+Epoch: 200 Average loss: 92.50
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 479)
+0/69092	Loss: 98.031
+3200/69092	Loss: 92.128
+6400/69092	Loss: 92.114
+9600/69092	Loss: 91.745
+12800/69092	Loss: 91.583
+16000/69092	Loss: 92.139
+19200/69092	Loss: 92.212
+22400/69092	Loss: 93.572
+25600/69092	Loss: 92.626
+28800/69092	Loss: 93.128
+32000/69092	Loss: 92.394
+35200/69092	Loss: 93.756
+38400/69092	Loss: 93.330
+41600/69092	Loss: 93.668
+44800/69092	Loss: 91.225
+48000/69092	Loss: 93.133
+51200/69092	Loss: 92.841
+54400/69092	Loss: 93.078
+57600/69092	Loss: 91.876
+60800/69092	Loss: 92.406
+64000/69092	Loss: 92.119
+67200/69092	Loss: 92.584
+Training time 0:10:32.857613
+Epoch: 201 Average loss: 92.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 480)
+0/69092	Loss: 90.992
+3200/69092	Loss: 92.732
+6400/69092	Loss: 93.011
+9600/69092	Loss: 91.974
+12800/69092	Loss: 91.857
+16000/69092	Loss: 91.501
+19200/69092	Loss: 91.941
+22400/69092	Loss: 91.566
+25600/69092	Loss: 91.031
+28800/69092	Loss: 92.270
+32000/69092	Loss: 92.784
+35200/69092	Loss: 93.741
+38400/69092	Loss: 93.047
+41600/69092	Loss: 91.970
+44800/69092	Loss: 92.652
+48000/69092	Loss: 91.572
+51200/69092	Loss: 92.155
+54400/69092	Loss: 91.571
+57600/69092	Loss: 93.037
+60800/69092	Loss: 93.415
+64000/69092	Loss: 92.755
+67200/69092	Loss: 92.004
+Training time 0:10:35.915462
+Epoch: 202 Average loss: 92.38
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last' (iter 481)
+0/69092	Loss: 89.663
+3200/69092	Loss: 91.683
+6400/69092	Loss: 91.916
+9600/69092	Loss: 92.958
+12800/69092	Loss: 92.345
+16000/69092	Loss: 92.465
diff --git a/OAR.2073644.stderr b/OAR.2073644.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..25f0bd4e7283b06c123a60e22a4d8b415a7d5146
--- /dev/null
+++ b/OAR.2073644.stderr
@@ -0,0 +1,3 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+## OAR [2020-07-07 08:29:14] Job 2073644 KILLED ##
diff --git a/OAR.2073644.stdout b/OAR.2073644.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..fd1ffa2ec0d6482438f26a7d927f02c63fd94ee4
--- /dev/null
+++ b/OAR.2073644.stdout
@@ -0,0 +1,5828 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64_ls_50', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=50, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=100, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=50, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 796135
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last (iter 274)'
+0/69092	Loss: 94.171
+3200/69092	Loss: 93.079
+6400/69092	Loss: 92.601
+9600/69092	Loss: 92.397
+12800/69092	Loss: 93.522
+16000/69092	Loss: 93.329
+19200/69092	Loss: 93.968
+22400/69092	Loss: 93.346
+25600/69092	Loss: 94.830
+28800/69092	Loss: 93.552
+32000/69092	Loss: 94.874
+35200/69092	Loss: 94.381
+38400/69092	Loss: 94.107
+41600/69092	Loss: 94.216
+44800/69092	Loss: 93.497
+48000/69092	Loss: 94.159
+51200/69092	Loss: 93.171
+54400/69092	Loss: 93.685
+57600/69092	Loss: 92.449
+60800/69092	Loss: 93.786
+64000/69092	Loss: 93.418
+67200/69092	Loss: 94.545
+Training time 0:12:24.747342
+Epoch: 1 Average loss: 93.70
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 275)
+0/69092	Loss: 89.487
+3200/69092	Loss: 94.612
+6400/69092	Loss: 92.062
+9600/69092	Loss: 92.781
+12800/69092	Loss: 93.898
+16000/69092	Loss: 92.809
+19200/69092	Loss: 94.357
+22400/69092	Loss: 94.360
+25600/69092	Loss: 94.800
+28800/69092	Loss: 93.993
+32000/69092	Loss: 93.283
+35200/69092	Loss: 94.105
+38400/69092	Loss: 94.011
+41600/69092	Loss: 93.273
+44800/69092	Loss: 95.076
+48000/69092	Loss: 92.417
+51200/69092	Loss: 92.085
+54400/69092	Loss: 94.623
+57600/69092	Loss: 92.516
+60800/69092	Loss: 93.975
+64000/69092	Loss: 93.641
+67200/69092	Loss: 93.186
+Training time 0:08:54.179311
+Epoch: 2 Average loss: 93.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 276)
+0/69092	Loss: 96.873
+3200/69092	Loss: 92.929
+6400/69092	Loss: 93.681
+9600/69092	Loss: 93.369
+12800/69092	Loss: 93.340
+16000/69092	Loss: 93.285
+19200/69092	Loss: 92.920
+22400/69092	Loss: 95.403
+25600/69092	Loss: 93.331
+28800/69092	Loss: 92.447
+32000/69092	Loss: 93.763
+35200/69092	Loss: 94.113
+38400/69092	Loss: 93.603
+41600/69092	Loss: 93.491
+44800/69092	Loss: 94.353
+48000/69092	Loss: 94.139
+51200/69092	Loss: 93.301
+54400/69092	Loss: 93.129
+57600/69092	Loss: 94.955
+60800/69092	Loss: 93.380
+64000/69092	Loss: 93.037
+67200/69092	Loss: 93.444
+Training time 0:08:56.059074
+Epoch: 3 Average loss: 93.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 277)
+0/69092	Loss: 97.778
+3200/69092	Loss: 94.069
+6400/69092	Loss: 94.302
+9600/69092	Loss: 92.691
+12800/69092	Loss: 94.155
+16000/69092	Loss: 92.070
+19200/69092	Loss: 93.580
+22400/69092	Loss: 92.614
+25600/69092	Loss: 94.540
+28800/69092	Loss: 93.328
+32000/69092	Loss: 93.538
+35200/69092	Loss: 93.719
+38400/69092	Loss: 93.445
+41600/69092	Loss: 93.099
+44800/69092	Loss: 93.675
+48000/69092	Loss: 93.535
+51200/69092	Loss: 92.904
+54400/69092	Loss: 93.583
+57600/69092	Loss: 93.261
+60800/69092	Loss: 93.472
+64000/69092	Loss: 93.284
+67200/69092	Loss: 95.204
+Training time 0:09:10.272473
+Epoch: 4 Average loss: 93.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 278)
+0/69092	Loss: 86.271
+3200/69092	Loss: 93.676
+6400/69092	Loss: 94.426
+9600/69092	Loss: 94.084
+12800/69092	Loss: 93.524
+16000/69092	Loss: 92.676
+19200/69092	Loss: 93.707
+22400/69092	Loss: 93.055
+25600/69092	Loss: 93.221
+28800/69092	Loss: 92.657
+32000/69092	Loss: 94.043
+35200/69092	Loss: 94.045
+38400/69092	Loss: 92.696
+41600/69092	Loss: 96.054
+44800/69092	Loss: 94.689
+48000/69092	Loss: 92.708
+51200/69092	Loss: 93.713
+54400/69092	Loss: 93.299
+57600/69092	Loss: 93.193
+60800/69092	Loss: 92.962
+64000/69092	Loss: 93.602
+67200/69092	Loss: 94.286
+Training time 0:09:09.392027
+Epoch: 5 Average loss: 93.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 279)
+0/69092	Loss: 93.200
+3200/69092	Loss: 92.074
+6400/69092	Loss: 94.685
+9600/69092	Loss: 94.216
+12800/69092	Loss: 93.531
+16000/69092	Loss: 93.191
+19200/69092	Loss: 93.374
+22400/69092	Loss: 92.278
+25600/69092	Loss: 94.312
+28800/69092	Loss: 94.145
+32000/69092	Loss: 92.816
+35200/69092	Loss: 93.201
+38400/69092	Loss: 92.762
+41600/69092	Loss: 92.741
+44800/69092	Loss: 93.414
+48000/69092	Loss: 93.376
+51200/69092	Loss: 94.532
+54400/69092	Loss: 93.962
+57600/69092	Loss: 93.874
+60800/69092	Loss: 94.916
+64000/69092	Loss: 94.396
+67200/69092	Loss: 93.210
+Training time 0:09:16.675170
+Epoch: 6 Average loss: 93.59
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 280)
+0/69092	Loss: 89.279
+3200/69092	Loss: 92.938
+6400/69092	Loss: 92.165
+9600/69092	Loss: 93.781
+12800/69092	Loss: 92.608
+16000/69092	Loss: 94.012
+19200/69092	Loss: 93.300
+22400/69092	Loss: 93.015
+25600/69092	Loss: 93.647
+28800/69092	Loss: 92.447
+32000/69092	Loss: 93.420
+35200/69092	Loss: 93.221
+38400/69092	Loss: 93.671
+41600/69092	Loss: 94.249
+44800/69092	Loss: 92.618
+48000/69092	Loss: 94.144
+51200/69092	Loss: 93.794
+54400/69092	Loss: 93.913
+57600/69092	Loss: 94.202
+60800/69092	Loss: 94.121
+64000/69092	Loss: 93.907
+67200/69092	Loss: 94.036
+Training time 0:09:14.131427
+Epoch: 7 Average loss: 93.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 281)
+0/69092	Loss: 85.379
+3200/69092	Loss: 92.941
+6400/69092	Loss: 93.353
+9600/69092	Loss: 92.721
+12800/69092	Loss: 93.543
+16000/69092	Loss: 92.995
+19200/69092	Loss: 94.431
+22400/69092	Loss: 94.455
+25600/69092	Loss: 93.985
+28800/69092	Loss: 93.950
+32000/69092	Loss: 92.949
+35200/69092	Loss: 92.878
+38400/69092	Loss: 93.961
+41600/69092	Loss: 93.731
+44800/69092	Loss: 94.249
+48000/69092	Loss: 94.512
+51200/69092	Loss: 94.194
+54400/69092	Loss: 93.273
+57600/69092	Loss: 92.902
+60800/69092	Loss: 94.162
+64000/69092	Loss: 93.001
+67200/69092	Loss: 93.141
+Training time 0:09:13.068327
+Epoch: 8 Average loss: 93.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 282)
+0/69092	Loss: 86.436
+3200/69092	Loss: 93.237
+6400/69092	Loss: 92.964
+9600/69092	Loss: 94.443
+12800/69092	Loss: 93.707
+16000/69092	Loss: 92.492
+19200/69092	Loss: 93.118
+22400/69092	Loss: 92.762
+25600/69092	Loss: 93.426
+28800/69092	Loss: 93.814
+32000/69092	Loss: 92.573
+35200/69092	Loss: 92.773
+38400/69092	Loss: 94.087
+41600/69092	Loss: 93.629
+44800/69092	Loss: 93.683
+48000/69092	Loss: 95.221
+51200/69092	Loss: 93.250
+54400/69092	Loss: 94.393
+57600/69092	Loss: 93.862
+60800/69092	Loss: 92.650
+64000/69092	Loss: 93.051
+67200/69092	Loss: 92.132
+Training time 0:09:08.309031
+Epoch: 9 Average loss: 93.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 283)
+0/69092	Loss: 95.725
+3200/69092	Loss: 92.831
+6400/69092	Loss: 94.043
+9600/69092	Loss: 92.847
+12800/69092	Loss: 93.584
+16000/69092	Loss: 91.817
+19200/69092	Loss: 93.803
+22400/69092	Loss: 93.590
+25600/69092	Loss: 93.885
+28800/69092	Loss: 93.658
+32000/69092	Loss: 93.663
+35200/69092	Loss: 93.371
+38400/69092	Loss: 93.228
+41600/69092	Loss: 94.679
+44800/69092	Loss: 93.913
+48000/69092	Loss: 94.224
+51200/69092	Loss: 93.134
+54400/69092	Loss: 94.145
+57600/69092	Loss: 92.890
+60800/69092	Loss: 92.728
+64000/69092	Loss: 93.624
+67200/69092	Loss: 93.444
+Training time 0:08:54.515244
+Epoch: 10 Average loss: 93.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 284)
+0/69092	Loss: 86.428
+3200/69092	Loss: 93.002
+6400/69092	Loss: 93.937
+9600/69092	Loss: 92.397
+12800/69092	Loss: 95.019
+16000/69092	Loss: 92.794
+19200/69092	Loss: 93.366
+22400/69092	Loss: 93.594
+25600/69092	Loss: 94.183
+28800/69092	Loss: 93.157
+32000/69092	Loss: 93.485
+35200/69092	Loss: 93.029
+38400/69092	Loss: 94.680
+41600/69092	Loss: 93.339
+44800/69092	Loss: 92.704
+48000/69092	Loss: 94.446
+51200/69092	Loss: 94.541
+54400/69092	Loss: 94.422
+57600/69092	Loss: 92.413
+60800/69092	Loss: 92.343
+64000/69092	Loss: 94.117
+67200/69092	Loss: 93.225
+Training time 0:09:03.489313
+Epoch: 11 Average loss: 93.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 285)
+0/69092	Loss: 98.704
+3200/69092	Loss: 93.930
+6400/69092	Loss: 92.749
+9600/69092	Loss: 93.849
+12800/69092	Loss: 93.336
+16000/69092	Loss: 93.485
+19200/69092	Loss: 93.007
+22400/69092	Loss: 95.324
+25600/69092	Loss: 93.369
+28800/69092	Loss: 92.165
+32000/69092	Loss: 92.701
+35200/69092	Loss: 93.137
+38400/69092	Loss: 94.353
+41600/69092	Loss: 91.906
+44800/69092	Loss: 92.608
+48000/69092	Loss: 93.939
+51200/69092	Loss: 93.132
+54400/69092	Loss: 93.149
+57600/69092	Loss: 93.642
+60800/69092	Loss: 93.933
+64000/69092	Loss: 94.381
+67200/69092	Loss: 92.727
+Training time 0:09:16.329956
+Epoch: 12 Average loss: 93.42
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 286)
+0/69092	Loss: 95.387
+3200/69092	Loss: 92.552
+6400/69092	Loss: 93.314
+9600/69092	Loss: 94.765
+12800/69092	Loss: 92.677
+16000/69092	Loss: 93.309
+19200/69092	Loss: 93.529
+22400/69092	Loss: 93.079
+25600/69092	Loss: 93.663
+28800/69092	Loss: 93.961
+32000/69092	Loss: 94.001
+35200/69092	Loss: 92.333
+38400/69092	Loss: 93.983
+41600/69092	Loss: 94.369
+44800/69092	Loss: 93.371
+48000/69092	Loss: 93.257
+51200/69092	Loss: 93.428
+54400/69092	Loss: 94.222
+57600/69092	Loss: 93.504
+60800/69092	Loss: 93.311
+64000/69092	Loss: 94.335
+67200/69092	Loss: 93.403
+Training time 0:09:27.830834
+Epoch: 13 Average loss: 93.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 287)
+0/69092	Loss: 85.074
+3200/69092	Loss: 93.894
+6400/69092	Loss: 93.087
+9600/69092	Loss: 94.560
+12800/69092	Loss: 94.731
+16000/69092	Loss: 93.367
+19200/69092	Loss: 92.803
+22400/69092	Loss: 93.618
+25600/69092	Loss: 93.186
+28800/69092	Loss: 93.312
+32000/69092	Loss: 92.745
+35200/69092	Loss: 94.608
+38400/69092	Loss: 92.966
+41600/69092	Loss: 92.505
+44800/69092	Loss: 92.746
+48000/69092	Loss: 93.057
+51200/69092	Loss: 94.573
+54400/69092	Loss: 94.453
+57600/69092	Loss: 93.111
+60800/69092	Loss: 93.336
+64000/69092	Loss: 93.189
+67200/69092	Loss: 94.195
+Training time 0:09:12.375810
+Epoch: 14 Average loss: 93.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 288)
+0/69092	Loss: 92.848
+3200/69092	Loss: 92.873
+6400/69092	Loss: 93.109
+9600/69092	Loss: 92.799
+12800/69092	Loss: 94.013
+16000/69092	Loss: 92.559
+19200/69092	Loss: 93.419
+22400/69092	Loss: 93.750
+25600/69092	Loss: 93.318
+28800/69092	Loss: 93.947
+32000/69092	Loss: 93.622
+35200/69092	Loss: 92.423
+38400/69092	Loss: 94.657
+41600/69092	Loss: 92.932
+44800/69092	Loss: 92.285
+48000/69092	Loss: 93.633
+51200/69092	Loss: 93.106
+54400/69092	Loss: 92.883
+57600/69092	Loss: 93.004
+60800/69092	Loss: 92.573
+64000/69092	Loss: 93.143
+67200/69092	Loss: 94.979
+Training time 0:09:20.141515
+Epoch: 15 Average loss: 93.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 289)
+0/69092	Loss: 97.313
+3200/69092	Loss: 94.001
+6400/69092	Loss: 92.579
+9600/69092	Loss: 94.481
+12800/69092	Loss: 92.436
+16000/69092	Loss: 93.777
+19200/69092	Loss: 93.558
+22400/69092	Loss: 92.738
+25600/69092	Loss: 93.722
+28800/69092	Loss: 93.448
+32000/69092	Loss: 92.296
+35200/69092	Loss: 92.675
+38400/69092	Loss: 92.853
+41600/69092	Loss: 92.430
+44800/69092	Loss: 92.978
+48000/69092	Loss: 94.814
+51200/69092	Loss: 93.994
+54400/69092	Loss: 93.750
+57600/69092	Loss: 93.661
+60800/69092	Loss: 94.722
+64000/69092	Loss: 92.031
+67200/69092	Loss: 92.779
+Training time 0:09:16.144999
+Epoch: 16 Average loss: 93.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 290)
+0/69092	Loss: 79.670
+3200/69092	Loss: 93.182
+6400/69092	Loss: 92.583
+9600/69092	Loss: 93.652
+12800/69092	Loss: 93.444
+16000/69092	Loss: 93.248
+19200/69092	Loss: 93.543
+22400/69092	Loss: 91.749
+25600/69092	Loss: 93.729
+28800/69092	Loss: 93.327
+32000/69092	Loss: 92.210
+35200/69092	Loss: 93.699
+38400/69092	Loss: 93.533
+41600/69092	Loss: 93.795
+44800/69092	Loss: 93.293
+48000/69092	Loss: 92.339
+51200/69092	Loss: 94.008
+54400/69092	Loss: 93.455
+57600/69092	Loss: 93.526
+60800/69092	Loss: 93.409
+64000/69092	Loss: 95.072
+67200/69092	Loss: 93.499
+Training time 0:09:01.453545
+Epoch: 17 Average loss: 93.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 291)
+0/69092	Loss: 86.439
+3200/69092	Loss: 94.083
+6400/69092	Loss: 94.068
+9600/69092	Loss: 92.989
+12800/69092	Loss: 93.610
+16000/69092	Loss: 92.276
+19200/69092	Loss: 92.931
+22400/69092	Loss: 94.299
+25600/69092	Loss: 91.339
+28800/69092	Loss: 93.922
+32000/69092	Loss: 91.557
+35200/69092	Loss: 94.409
+38400/69092	Loss: 93.147
+41600/69092	Loss: 92.870
+44800/69092	Loss: 93.254
+48000/69092	Loss: 93.467
+51200/69092	Loss: 94.077
+54400/69092	Loss: 93.688
+57600/69092	Loss: 92.409
+60800/69092	Loss: 93.094
+64000/69092	Loss: 93.325
+67200/69092	Loss: 93.706
+Training time 0:08:47.697694
+Epoch: 18 Average loss: 93.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 292)
+0/69092	Loss: 97.519
+3200/69092	Loss: 92.142
+6400/69092	Loss: 92.940
+9600/69092	Loss: 94.811
+12800/69092	Loss: 91.465
+16000/69092	Loss: 93.842
+19200/69092	Loss: 94.063
+22400/69092	Loss: 92.699
+25600/69092	Loss: 94.073
+28800/69092	Loss: 94.100
+32000/69092	Loss: 93.638
+35200/69092	Loss: 92.771
+38400/69092	Loss: 92.896
+41600/69092	Loss: 91.073
+44800/69092	Loss: 93.748
+48000/69092	Loss: 93.839
+51200/69092	Loss: 93.471
+54400/69092	Loss: 93.214
+57600/69092	Loss: 92.759
+60800/69092	Loss: 92.296
+64000/69092	Loss: 93.018
+67200/69092	Loss: 93.859
+Training time 0:09:02.677565
+Epoch: 19 Average loss: 93.20
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 293)
+0/69092	Loss: 94.773
+3200/69092	Loss: 93.693
+6400/69092	Loss: 92.404
+9600/69092	Loss: 92.524
+12800/69092	Loss: 92.522
+16000/69092	Loss: 92.759
+19200/69092	Loss: 94.271
+22400/69092	Loss: 93.934
+25600/69092	Loss: 93.350
+28800/69092	Loss: 94.041
+32000/69092	Loss: 92.509
+35200/69092	Loss: 93.604
+38400/69092	Loss: 92.169
+41600/69092	Loss: 93.550
+44800/69092	Loss: 93.454
+48000/69092	Loss: 92.883
+51200/69092	Loss: 93.223
+54400/69092	Loss: 93.216
+57600/69092	Loss: 93.290
+60800/69092	Loss: 94.767
+64000/69092	Loss: 94.251
+67200/69092	Loss: 92.508
+Training time 0:08:59.005856
+Epoch: 20 Average loss: 93.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 294)
+0/69092	Loss: 92.414
+3200/69092	Loss: 91.658
+6400/69092	Loss: 93.250
+9600/69092	Loss: 94.645
+12800/69092	Loss: 92.136
+16000/69092	Loss: 92.797
+19200/69092	Loss: 94.295
+22400/69092	Loss: 94.057
+25600/69092	Loss: 91.451
+28800/69092	Loss: 93.679
+32000/69092	Loss: 93.656
+35200/69092	Loss: 93.722
+38400/69092	Loss: 92.824
+41600/69092	Loss: 93.301
+44800/69092	Loss: 94.104
+48000/69092	Loss: 92.305
+51200/69092	Loss: 93.627
+54400/69092	Loss: 93.462
+57600/69092	Loss: 93.802
+60800/69092	Loss: 92.675
+64000/69092	Loss: 93.522
+67200/69092	Loss: 93.201
+Training time 0:09:20.435732
+Epoch: 21 Average loss: 93.23
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 295)
+0/69092	Loss: 89.961
+3200/69092	Loss: 94.322
+6400/69092	Loss: 93.141
+9600/69092	Loss: 94.475
+12800/69092	Loss: 93.865
+16000/69092	Loss: 93.500
+19200/69092	Loss: 94.701
+22400/69092	Loss: 92.901
+25600/69092	Loss: 92.956
+28800/69092	Loss: 92.499
+32000/69092	Loss: 91.599
+35200/69092	Loss: 94.097
+38400/69092	Loss: 93.373
+41600/69092	Loss: 92.877
+44800/69092	Loss: 93.051
+48000/69092	Loss: 92.471
+51200/69092	Loss: 95.107
+54400/69092	Loss: 93.969
+57600/69092	Loss: 92.352
+60800/69092	Loss: 92.653
+64000/69092	Loss: 92.398
+67200/69092	Loss: 93.465
+Training time 0:09:15.229790
+Epoch: 22 Average loss: 93.36
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 296)
+0/69092	Loss: 101.109
+3200/69092	Loss: 93.396
+6400/69092	Loss: 93.314
+9600/69092	Loss: 91.433
+12800/69092	Loss: 93.540
+16000/69092	Loss: 93.448
+19200/69092	Loss: 92.858
+22400/69092	Loss: 93.580
+25600/69092	Loss: 95.532
+28800/69092	Loss: 92.783
+32000/69092	Loss: 93.119
+35200/69092	Loss: 91.836
+38400/69092	Loss: 94.153
+41600/69092	Loss: 93.916
+44800/69092	Loss: 92.488
+48000/69092	Loss: 92.639
+51200/69092	Loss: 93.025
+54400/69092	Loss: 93.030
+57600/69092	Loss: 94.041
+60800/69092	Loss: 93.853
+64000/69092	Loss: 93.284
+67200/69092	Loss: 93.208
+Training time 0:09:13.766607
+Epoch: 23 Average loss: 93.32
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 297)
+0/69092	Loss: 91.590
+3200/69092	Loss: 93.942
+6400/69092	Loss: 93.564
+9600/69092	Loss: 94.264
+12800/69092	Loss: 92.455
+16000/69092	Loss: 93.498
+19200/69092	Loss: 93.120
+22400/69092	Loss: 93.019
+25600/69092	Loss: 93.677
+28800/69092	Loss: 92.789
+32000/69092	Loss: 93.649
+35200/69092	Loss: 92.487
+38400/69092	Loss: 92.863
+41600/69092	Loss: 92.913
+44800/69092	Loss: 92.006
+48000/69092	Loss: 92.975
+51200/69092	Loss: 94.016
+54400/69092	Loss: 94.105
+57600/69092	Loss: 93.806
+60800/69092	Loss: 92.699
+64000/69092	Loss: 92.434
+67200/69092	Loss: 93.459
+Training time 0:09:15.779607
+Epoch: 24 Average loss: 93.28
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 298)
+0/69092	Loss: 94.655
+3200/69092	Loss: 93.598
+6400/69092	Loss: 94.222
+9600/69092	Loss: 91.900
+12800/69092	Loss: 93.590
+16000/69092	Loss: 94.950
+19200/69092	Loss: 93.481
+22400/69092	Loss: 94.023
+25600/69092	Loss: 93.733
+28800/69092	Loss: 91.787
+32000/69092	Loss: 94.645
+35200/69092	Loss: 92.705
+38400/69092	Loss: 93.667
+41600/69092	Loss: 93.330
+44800/69092	Loss: 92.721
+48000/69092	Loss: 92.846
+51200/69092	Loss: 92.884
+54400/69092	Loss: 93.638
+57600/69092	Loss: 93.569
+60800/69092	Loss: 92.869
+64000/69092	Loss: 94.030
+67200/69092	Loss: 93.146
+Training time 0:09:10.913424
+Epoch: 25 Average loss: 93.41
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 299)
+0/69092	Loss: 93.866
+3200/69092	Loss: 92.887
+6400/69092	Loss: 93.778
+9600/69092	Loss: 93.955
+12800/69092	Loss: 94.024
+16000/69092	Loss: 92.954
+19200/69092	Loss: 93.491
+22400/69092	Loss: 92.632
+25600/69092	Loss: 95.782
+28800/69092	Loss: 93.306
+32000/69092	Loss: 91.925
+35200/69092	Loss: 92.395
+38400/69092	Loss: 94.453
+41600/69092	Loss: 93.495
+44800/69092	Loss: 92.956
+48000/69092	Loss: 92.995
+51200/69092	Loss: 92.717
+54400/69092	Loss: 93.183
+57600/69092	Loss: 93.895
+60800/69092	Loss: 94.147
+64000/69092	Loss: 93.088
+67200/69092	Loss: 92.705
+Training time 0:08:55.987150
+Epoch: 26 Average loss: 93.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 300)
+0/69092	Loss: 96.701
+3200/69092	Loss: 91.900
+6400/69092	Loss: 92.925
+9600/69092	Loss: 94.128
+12800/69092	Loss: 94.118
+16000/69092	Loss: 92.992
+19200/69092	Loss: 93.387
+22400/69092	Loss: 91.942
+25600/69092	Loss: 92.759
+28800/69092	Loss: 92.764
+32000/69092	Loss: 92.974
+35200/69092	Loss: 93.306
+38400/69092	Loss: 92.291
+41600/69092	Loss: 93.849
+44800/69092	Loss: 93.916
+48000/69092	Loss: 93.401
+51200/69092	Loss: 94.042
+54400/69092	Loss: 93.596
+57600/69092	Loss: 93.304
+60800/69092	Loss: 93.083
+64000/69092	Loss: 93.412
+67200/69092	Loss: 90.991
+Training time 0:09:11.290138
+Epoch: 27 Average loss: 93.13
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 301)
+0/69092	Loss: 93.350
+3200/69092	Loss: 93.899
+6400/69092	Loss: 93.899
+9600/69092	Loss: 93.154
+12800/69092	Loss: 93.319
+16000/69092	Loss: 92.362
+19200/69092	Loss: 92.871
+22400/69092	Loss: 93.858
+25600/69092	Loss: 92.736
+28800/69092	Loss: 92.411
+32000/69092	Loss: 94.172
+35200/69092	Loss: 93.307
+38400/69092	Loss: 92.258
+41600/69092	Loss: 93.826
+44800/69092	Loss: 92.502
+48000/69092	Loss: 93.170
+51200/69092	Loss: 93.661
+54400/69092	Loss: 93.405
+57600/69092	Loss: 92.324
+60800/69092	Loss: 92.630
+64000/69092	Loss: 93.041
+67200/69092	Loss: 93.981
+Training time 0:08:57.391692
+Epoch: 28 Average loss: 93.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 302)
+0/69092	Loss: 92.937
+3200/69092	Loss: 92.252
+6400/69092	Loss: 93.891
+9600/69092	Loss: 92.776
+12800/69092	Loss: 92.120
+16000/69092	Loss: 94.235
+19200/69092	Loss: 93.920
+22400/69092	Loss: 92.630
+25600/69092	Loss: 91.660
+28800/69092	Loss: 94.295
+32000/69092	Loss: 91.234
+35200/69092	Loss: 92.451
+38400/69092	Loss: 93.450
+41600/69092	Loss: 92.694
+44800/69092	Loss: 94.962
+48000/69092	Loss: 93.863
+51200/69092	Loss: 93.472
+54400/69092	Loss: 93.918
+57600/69092	Loss: 92.976
+60800/69092	Loss: 91.720
+64000/69092	Loss: 93.701
+67200/69092	Loss: 93.579
+Training time 0:09:10.114667
+Epoch: 29 Average loss: 93.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 303)
+0/69092	Loss: 95.726
+3200/69092	Loss: 92.662
+6400/69092	Loss: 92.068
+9600/69092	Loss: 92.231
+12800/69092	Loss: 93.608
+16000/69092	Loss: 93.085
+19200/69092	Loss: 93.584
+22400/69092	Loss: 94.159
+25600/69092	Loss: 93.367
+28800/69092	Loss: 92.545
+32000/69092	Loss: 92.723
+35200/69092	Loss: 93.889
+38400/69092	Loss: 92.020
+41600/69092	Loss: 95.421
+44800/69092	Loss: 92.356
+48000/69092	Loss: 92.870
+51200/69092	Loss: 92.684
+54400/69092	Loss: 93.095
+57600/69092	Loss: 93.094
+60800/69092	Loss: 92.761
+64000/69092	Loss: 93.711
+67200/69092	Loss: 93.186
+Training time 0:09:10.975927
+Epoch: 30 Average loss: 93.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 304)
+0/69092	Loss: 86.803
+3200/69092	Loss: 94.320
+6400/69092	Loss: 91.788
+9600/69092	Loss: 93.463
+12800/69092	Loss: 92.526
+16000/69092	Loss: 92.773
+19200/69092	Loss: 92.296
+22400/69092	Loss: 93.049
+25600/69092	Loss: 92.288
+28800/69092	Loss: 93.342
+32000/69092	Loss: 93.168
+35200/69092	Loss: 93.990
+38400/69092	Loss: 94.378
+41600/69092	Loss: 93.186
+44800/69092	Loss: 94.196
+48000/69092	Loss: 94.267
+51200/69092	Loss: 92.565
+54400/69092	Loss: 93.110
+57600/69092	Loss: 94.095
+60800/69092	Loss: 94.380
+64000/69092	Loss: 92.064
+67200/69092	Loss: 92.900
+Training time 0:09:20.948343
+Epoch: 31 Average loss: 93.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 305)
+0/69092	Loss: 87.428
+3200/69092	Loss: 92.198
+6400/69092	Loss: 93.170
+9600/69092	Loss: 92.081
+12800/69092	Loss: 92.896
+16000/69092	Loss: 92.308
+19200/69092	Loss: 93.448
+22400/69092	Loss: 92.297
+25600/69092	Loss: 93.808
+28800/69092	Loss: 92.849
+32000/69092	Loss: 92.154
+35200/69092	Loss: 93.473
+38400/69092	Loss: 92.854
+41600/69092	Loss: 93.400
+44800/69092	Loss: 94.340
+48000/69092	Loss: 92.392
+51200/69092	Loss: 93.010
+54400/69092	Loss: 94.536
+57600/69092	Loss: 93.023
+60800/69092	Loss: 93.731
+64000/69092	Loss: 92.124
+67200/69092	Loss: 93.178
+Training time 0:09:18.863995
+Epoch: 32 Average loss: 93.03
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 306)
+0/69092	Loss: 93.263
+3200/69092	Loss: 92.436
+6400/69092	Loss: 92.635
+9600/69092	Loss: 92.857
+12800/69092	Loss: 92.078
+16000/69092	Loss: 93.207
+19200/69092	Loss: 92.871
+22400/69092	Loss: 93.184
+25600/69092	Loss: 93.331
+28800/69092	Loss: 93.466
+32000/69092	Loss: 93.100
+35200/69092	Loss: 93.360
+38400/69092	Loss: 93.644
+41600/69092	Loss: 94.003
+44800/69092	Loss: 92.711
+48000/69092	Loss: 93.426
+51200/69092	Loss: 95.009
+54400/69092	Loss: 92.568
+57600/69092	Loss: 92.759
+60800/69092	Loss: 92.461
+64000/69092	Loss: 92.920
+67200/69092	Loss: 92.513
+Training time 0:09:05.001772
+Epoch: 33 Average loss: 93.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 307)
+0/69092	Loss: 90.420
+3200/69092	Loss: 93.377
+6400/69092	Loss: 92.897
+9600/69092	Loss: 91.893
+12800/69092	Loss: 93.884
+16000/69092	Loss: 93.180
+19200/69092	Loss: 94.515
+22400/69092	Loss: 92.231
+25600/69092	Loss: 93.297
+28800/69092	Loss: 93.476
+32000/69092	Loss: 94.129
+35200/69092	Loss: 93.566
+38400/69092	Loss: 91.786
+41600/69092	Loss: 93.423
+44800/69092	Loss: 93.216
+48000/69092	Loss: 92.462
+51200/69092	Loss: 93.350
+54400/69092	Loss: 93.833
+57600/69092	Loss: 93.084
+60800/69092	Loss: 94.297
+64000/69092	Loss: 92.278
+67200/69092	Loss: 94.540
+Training time 0:08:53.322226
+Epoch: 34 Average loss: 93.26
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 308)
+0/69092	Loss: 92.941
+3200/69092	Loss: 93.941
+6400/69092	Loss: 92.915
+9600/69092	Loss: 94.183
+12800/69092	Loss: 94.274
+16000/69092	Loss: 93.520
+19200/69092	Loss: 92.716
+22400/69092	Loss: 93.269
+25600/69092	Loss: 93.016
+28800/69092	Loss: 92.019
+32000/69092	Loss: 93.732
+35200/69092	Loss: 93.400
+38400/69092	Loss: 91.519
+41600/69092	Loss: 91.875
+44800/69092	Loss: 93.257
+48000/69092	Loss: 91.828
+51200/69092	Loss: 92.866
+54400/69092	Loss: 93.144
+57600/69092	Loss: 94.088
+60800/69092	Loss: 93.046
+64000/69092	Loss: 92.716
+67200/69092	Loss: 93.448
+Training time 0:08:56.456150
+Epoch: 35 Average loss: 93.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 309)
+0/69092	Loss: 85.000
+3200/69092	Loss: 93.239
+6400/69092	Loss: 94.217
+9600/69092	Loss: 91.885
+12800/69092	Loss: 93.497
+16000/69092	Loss: 92.800
+19200/69092	Loss: 93.403
+22400/69092	Loss: 92.862
+25600/69092	Loss: 91.794
+28800/69092	Loss: 92.080
+32000/69092	Loss: 91.710
+35200/69092	Loss: 92.635
+38400/69092	Loss: 93.021
+41600/69092	Loss: 93.562
+44800/69092	Loss: 92.525
+48000/69092	Loss: 92.593
+51200/69092	Loss: 93.543
+54400/69092	Loss: 93.861
+57600/69092	Loss: 93.588
+60800/69092	Loss: 94.758
+64000/69092	Loss: 93.225
+67200/69092	Loss: 93.588
+Training time 0:09:05.509716
+Epoch: 36 Average loss: 93.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 310)
+0/69092	Loss: 94.820
+3200/69092	Loss: 92.994
+6400/69092	Loss: 93.781
+9600/69092	Loss: 92.262
+12800/69092	Loss: 92.576
+16000/69092	Loss: 93.395
+19200/69092	Loss: 94.131
+22400/69092	Loss: 94.540
+25600/69092	Loss: 93.293
+28800/69092	Loss: 93.217
+32000/69092	Loss: 92.519
+35200/69092	Loss: 93.844
+38400/69092	Loss: 90.852
+41600/69092	Loss: 92.797
+44800/69092	Loss: 93.824
+48000/69092	Loss: 93.177
+51200/69092	Loss: 92.878
+54400/69092	Loss: 92.564
+57600/69092	Loss: 92.466
+60800/69092	Loss: 94.519
+64000/69092	Loss: 93.816
+67200/69092	Loss: 92.304
+Training time 0:09:25.274613
+Epoch: 37 Average loss: 93.14
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 311)
+0/69092	Loss: 85.349
+3200/69092	Loss: 91.810
+6400/69092	Loss: 93.417
+9600/69092	Loss: 92.758
+12800/69092	Loss: 93.733
+16000/69092	Loss: 92.941
+19200/69092	Loss: 92.671
+22400/69092	Loss: 93.615
+25600/69092	Loss: 93.900
+28800/69092	Loss: 92.606
+32000/69092	Loss: 92.450
+35200/69092	Loss: 93.769
+38400/69092	Loss: 92.863
+41600/69092	Loss: 93.619
+44800/69092	Loss: 92.686
+48000/69092	Loss: 91.596
+51200/69092	Loss: 93.151
+54400/69092	Loss: 93.981
+57600/69092	Loss: 93.131
+60800/69092	Loss: 93.298
+64000/69092	Loss: 94.434
+67200/69092	Loss: 93.934
+Training time 0:09:03.162613
+Epoch: 38 Average loss: 93.15
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 312)
+0/69092	Loss: 95.512
+3200/69092	Loss: 93.457
+6400/69092	Loss: 93.417
+9600/69092	Loss: 91.788
+12800/69092	Loss: 93.237
+16000/69092	Loss: 93.325
+19200/69092	Loss: 92.951
+22400/69092	Loss: 92.650
+25600/69092	Loss: 92.834
+28800/69092	Loss: 93.691
+32000/69092	Loss: 92.471
+35200/69092	Loss: 92.118
+38400/69092	Loss: 92.163
+41600/69092	Loss: 93.660
+44800/69092	Loss: 92.467
+48000/69092	Loss: 93.244
+51200/69092	Loss: 91.655
+54400/69092	Loss: 91.911
+57600/69092	Loss: 92.963
+60800/69092	Loss: 93.356
+64000/69092	Loss: 93.997
+67200/69092	Loss: 93.235
+Training time 0:09:17.860662
+Epoch: 39 Average loss: 92.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 313)
+0/69092	Loss: 92.395
+3200/69092	Loss: 93.665
+6400/69092	Loss: 91.589
+9600/69092	Loss: 92.672
+12800/69092	Loss: 93.019
+16000/69092	Loss: 95.176
+19200/69092	Loss: 91.531
+22400/69092	Loss: 92.808
+25600/69092	Loss: 94.464
+28800/69092	Loss: 92.202
+32000/69092	Loss: 92.302
+35200/69092	Loss: 92.390
+38400/69092	Loss: 92.867
+41600/69092	Loss: 94.488
+44800/69092	Loss: 94.896
+48000/69092	Loss: 92.284
+51200/69092	Loss: 91.376
+54400/69092	Loss: 93.320
+57600/69092	Loss: 93.868
+60800/69092	Loss: 92.887
+64000/69092	Loss: 94.401
+67200/69092	Loss: 93.860
+Training time 0:09:14.467706
+Epoch: 40 Average loss: 93.13
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 314)
+0/69092	Loss: 86.068
+3200/69092	Loss: 92.051
+6400/69092	Loss: 93.087
+9600/69092	Loss: 93.177
+12800/69092	Loss: 92.944
+16000/69092	Loss: 92.248
+19200/69092	Loss: 92.143
+22400/69092	Loss: 92.708
+25600/69092	Loss: 92.379
+28800/69092	Loss: 93.414
+32000/69092	Loss: 92.668
+35200/69092	Loss: 94.332
+38400/69092	Loss: 93.871
+41600/69092	Loss: 93.112
+44800/69092	Loss: 92.181
+48000/69092	Loss: 92.381
+51200/69092	Loss: 93.681
+54400/69092	Loss: 91.773
+57600/69092	Loss: 92.056
+60800/69092	Loss: 92.662
+64000/69092	Loss: 93.394
+67200/69092	Loss: 92.564
+Training time 0:09:08.767133
+Epoch: 41 Average loss: 92.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 315)
+0/69092	Loss: 84.834
+3200/69092	Loss: 91.208
+6400/69092	Loss: 92.690
+9600/69092	Loss: 93.549
+12800/69092	Loss: 94.351
+16000/69092	Loss: 93.303
+19200/69092	Loss: 92.865
+22400/69092	Loss: 92.950
+25600/69092	Loss: 93.099
+28800/69092	Loss: 93.616
+32000/69092	Loss: 92.142
+35200/69092	Loss: 92.456
+38400/69092	Loss: 92.886
+41600/69092	Loss: 92.760
+44800/69092	Loss: 93.058
+48000/69092	Loss: 93.004
+51200/69092	Loss: 93.690
+54400/69092	Loss: 92.208
+57600/69092	Loss: 92.520
+60800/69092	Loss: 93.459
+64000/69092	Loss: 93.640
+67200/69092	Loss: 93.598
+Training time 0:09:18.511430
+Epoch: 42 Average loss: 93.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 316)
+0/69092	Loss: 95.101
+3200/69092	Loss: 92.276
+6400/69092	Loss: 93.702
+9600/69092	Loss: 93.057
+12800/69092	Loss: 94.419
+16000/69092	Loss: 93.006
+19200/69092	Loss: 92.774
+22400/69092	Loss: 93.312
+25600/69092	Loss: 92.276
+28800/69092	Loss: 93.207
+32000/69092	Loss: 91.700
+35200/69092	Loss: 93.234
+38400/69092	Loss: 92.150
+41600/69092	Loss: 94.456
+44800/69092	Loss: 92.400
+48000/69092	Loss: 93.206
+51200/69092	Loss: 93.103
+54400/69092	Loss: 92.667
+57600/69092	Loss: 93.006
+60800/69092	Loss: 93.961
+64000/69092	Loss: 93.147
+67200/69092	Loss: 93.522
+Training time 0:09:04.336493
+Epoch: 43 Average loss: 93.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 317)
+0/69092	Loss: 93.529
+3200/69092	Loss: 92.401
+6400/69092	Loss: 91.202
+9600/69092	Loss: 91.839
+12800/69092	Loss: 92.349
+16000/69092	Loss: 93.097
+19200/69092	Loss: 91.168
+22400/69092	Loss: 93.340
+25600/69092	Loss: 94.741
+28800/69092	Loss: 92.208
+32000/69092	Loss: 94.123
+35200/69092	Loss: 93.215
+38400/69092	Loss: 93.843
+41600/69092	Loss: 92.704
+44800/69092	Loss: 93.324
+48000/69092	Loss: 93.691
+51200/69092	Loss: 94.091
+54400/69092	Loss: 93.019
+57600/69092	Loss: 93.252
+60800/69092	Loss: 92.973
+64000/69092	Loss: 92.577
+67200/69092	Loss: 93.234
+Training time 0:09:02.132811
+Epoch: 44 Average loss: 92.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 318)
+0/69092	Loss: 81.592
+3200/69092	Loss: 92.831
+6400/69092	Loss: 93.682
+9600/69092	Loss: 92.850
+12800/69092	Loss: 92.703
+16000/69092	Loss: 93.445
+19200/69092	Loss: 92.897
+22400/69092	Loss: 92.640
+25600/69092	Loss: 92.519
+28800/69092	Loss: 92.145
+32000/69092	Loss: 92.444
+35200/69092	Loss: 93.052
+38400/69092	Loss: 94.431
+41600/69092	Loss: 94.020
+44800/69092	Loss: 91.941
+48000/69092	Loss: 91.807
+51200/69092	Loss: 93.478
+54400/69092	Loss: 93.005
+57600/69092	Loss: 92.305
+60800/69092	Loss: 93.120
+64000/69092	Loss: 93.958
+67200/69092	Loss: 91.882
+Training time 0:09:22.164519
+Epoch: 45 Average loss: 92.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 319)
+0/69092	Loss: 92.080
+3200/69092	Loss: 92.673
+6400/69092	Loss: 93.812
+9600/69092	Loss: 93.060
+12800/69092	Loss: 93.175
+16000/69092	Loss: 93.410
+19200/69092	Loss: 92.248
+22400/69092	Loss: 92.058
+25600/69092	Loss: 92.174
+28800/69092	Loss: 92.418
+32000/69092	Loss: 94.227
+35200/69092	Loss: 93.867
+38400/69092	Loss: 92.980
+41600/69092	Loss: 93.344
+44800/69092	Loss: 92.652
+48000/69092	Loss: 92.404
+51200/69092	Loss: 93.223
+54400/69092	Loss: 92.351
+57600/69092	Loss: 93.682
+60800/69092	Loss: 92.551
+64000/69092	Loss: 93.147
+67200/69092	Loss: 92.993
+Training time 0:09:08.056991
+Epoch: 46 Average loss: 92.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 320)
+0/69092	Loss: 96.639
+3200/69092	Loss: 91.435
+6400/69092	Loss: 93.381
+9600/69092	Loss: 93.901
+12800/69092	Loss: 92.927
+16000/69092	Loss: 92.235
+19200/69092	Loss: 92.968
+22400/69092	Loss: 91.677
+25600/69092	Loss: 92.111
+28800/69092	Loss: 93.615
+32000/69092	Loss: 94.040
+35200/69092	Loss: 93.014
+38400/69092	Loss: 93.282
+41600/69092	Loss: 92.837
+44800/69092	Loss: 93.308
+48000/69092	Loss: 93.579
+51200/69092	Loss: 92.607
+54400/69092	Loss: 92.643
+57600/69092	Loss: 92.219
+60800/69092	Loss: 93.892
+64000/69092	Loss: 93.335
+67200/69092	Loss: 93.426
+Training time 0:09:16.491726
+Epoch: 47 Average loss: 92.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 321)
+0/69092	Loss: 89.210
+3200/69092	Loss: 92.131
+6400/69092	Loss: 93.575
+9600/69092	Loss: 93.251
+12800/69092	Loss: 93.450
+16000/69092	Loss: 91.159
+19200/69092	Loss: 92.438
+22400/69092	Loss: 93.100
+25600/69092	Loss: 92.302
+28800/69092	Loss: 92.370
+32000/69092	Loss: 91.996
+35200/69092	Loss: 93.309
+38400/69092	Loss: 93.970
+41600/69092	Loss: 94.355
+44800/69092	Loss: 92.368
+48000/69092	Loss: 92.421
+51200/69092	Loss: 92.885
+54400/69092	Loss: 92.810
+57600/69092	Loss: 93.795
+60800/69092	Loss: 93.335
+64000/69092	Loss: 95.613
+67200/69092	Loss: 92.874
+Training time 0:09:25.873932
+Epoch: 48 Average loss: 92.99
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 322)
+0/69092	Loss: 95.645
+3200/69092	Loss: 93.029
+6400/69092	Loss: 92.981
+9600/69092	Loss: 93.816
+12800/69092	Loss: 91.315
+16000/69092	Loss: 93.945
+19200/69092	Loss: 92.917
+22400/69092	Loss: 92.797
+25600/69092	Loss: 93.565
+28800/69092	Loss: 90.544
+32000/69092	Loss: 92.893
+35200/69092	Loss: 91.734
+38400/69092	Loss: 93.979
+41600/69092	Loss: 93.776
+44800/69092	Loss: 92.381
+48000/69092	Loss: 93.205
+51200/69092	Loss: 92.100
+54400/69092	Loss: 92.229
+57600/69092	Loss: 92.954
+60800/69092	Loss: 92.949
+64000/69092	Loss: 93.447
+67200/69092	Loss: 93.243
+Training time 0:09:18.524643
+Epoch: 49 Average loss: 92.87
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 323)
+0/69092	Loss: 95.336
+3200/69092	Loss: 92.807
+6400/69092	Loss: 91.405
+9600/69092	Loss: 93.846
+12800/69092	Loss: 93.401
+16000/69092	Loss: 94.095
+19200/69092	Loss: 93.607
+22400/69092	Loss: 93.023
+25600/69092	Loss: 92.289
+28800/69092	Loss: 91.994
+32000/69092	Loss: 90.906
+35200/69092	Loss: 91.534
+38400/69092	Loss: 92.946
+41600/69092	Loss: 93.298
+44800/69092	Loss: 93.622
+48000/69092	Loss: 94.143
+51200/69092	Loss: 91.452
+54400/69092	Loss: 92.777
+57600/69092	Loss: 93.300
+60800/69092	Loss: 93.776
+64000/69092	Loss: 92.362
+67200/69092	Loss: 93.293
+Training time 0:09:03.842659
+Epoch: 50 Average loss: 92.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 324)
+0/69092	Loss: 86.841
+3200/69092	Loss: 92.905
+6400/69092	Loss: 93.323
+9600/69092	Loss: 92.134
+12800/69092	Loss: 94.696
+16000/69092	Loss: 90.739
+19200/69092	Loss: 93.433
+22400/69092	Loss: 91.864
+25600/69092	Loss: 93.016
+28800/69092	Loss: 93.802
+32000/69092	Loss: 93.991
+35200/69092	Loss: 92.975
+38400/69092	Loss: 92.694
+41600/69092	Loss: 93.068
+44800/69092	Loss: 92.984
+48000/69092	Loss: 91.641
+51200/69092	Loss: 92.747
+54400/69092	Loss: 92.316
+57600/69092	Loss: 93.504
+60800/69092	Loss: 93.318
+64000/69092	Loss: 91.457
+67200/69092	Loss: 92.611
+Training time 0:09:19.062174
+Epoch: 51 Average loss: 92.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 325)
+0/69092	Loss: 92.469
+3200/69092	Loss: 94.819
+6400/69092	Loss: 90.666
+9600/69092	Loss: 90.973
+12800/69092	Loss: 92.130
+16000/69092	Loss: 92.325
+19200/69092	Loss: 91.847
+22400/69092	Loss: 93.715
+25600/69092	Loss: 92.911
+28800/69092	Loss: 92.366
+32000/69092	Loss: 93.465
+35200/69092	Loss: 91.471
+38400/69092	Loss: 92.781
+41600/69092	Loss: 92.166
+44800/69092	Loss: 92.867
+48000/69092	Loss: 94.009
+51200/69092	Loss: 94.476
+54400/69092	Loss: 92.444
+57600/69092	Loss: 93.165
+60800/69092	Loss: 93.614
+64000/69092	Loss: 93.459
+67200/69092	Loss: 93.418
+Training time 0:09:03.165637
+Epoch: 52 Average loss: 92.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 326)
+0/69092	Loss: 92.111
+3200/69092	Loss: 93.004
+6400/69092	Loss: 93.335
+9600/69092	Loss: 92.357
+12800/69092	Loss: 92.651
+16000/69092	Loss: 93.130
+19200/69092	Loss: 93.198
+22400/69092	Loss: 93.440
+25600/69092	Loss: 93.224
+28800/69092	Loss: 93.267
+32000/69092	Loss: 93.465
+35200/69092	Loss: 93.061
+38400/69092	Loss: 91.830
+41600/69092	Loss: 91.567
+44800/69092	Loss: 92.045
+48000/69092	Loss: 92.200
+51200/69092	Loss: 94.537
+54400/69092	Loss: 93.313
+57600/69092	Loss: 93.035
+60800/69092	Loss: 92.910
+64000/69092	Loss: 92.239
+67200/69092	Loss: 93.358
+Training time 0:09:17.381804
+Epoch: 53 Average loss: 92.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 327)
+0/69092	Loss: 84.398
+3200/69092	Loss: 93.096
+6400/69092	Loss: 92.449
+9600/69092	Loss: 93.541
+12800/69092	Loss: 93.814
+16000/69092	Loss: 91.529
+19200/69092	Loss: 94.506
+22400/69092	Loss: 93.160
+25600/69092	Loss: 93.692
+28800/69092	Loss: 91.481
+32000/69092	Loss: 93.049
+35200/69092	Loss: 93.394
+38400/69092	Loss: 93.537
+41600/69092	Loss: 93.458
+44800/69092	Loss: 92.521
+48000/69092	Loss: 91.702
+51200/69092	Loss: 92.961
+54400/69092	Loss: 93.162
+57600/69092	Loss: 92.915
+60800/69092	Loss: 92.597
+64000/69092	Loss: 91.999
+67200/69092	Loss: 92.150
+Training time 0:09:01.257973
+Epoch: 54 Average loss: 92.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 328)
+0/69092	Loss: 100.464
+3200/69092	Loss: 92.283
+6400/69092	Loss: 93.492
+9600/69092	Loss: 93.591
+12800/69092	Loss: 91.443
+16000/69092	Loss: 91.503
+19200/69092	Loss: 93.173
+22400/69092	Loss: 93.432
+25600/69092	Loss: 92.834
+28800/69092	Loss: 91.732
+32000/69092	Loss: 92.707
+35200/69092	Loss: 92.745
+38400/69092	Loss: 93.023
+41600/69092	Loss: 92.681
+44800/69092	Loss: 93.684
+48000/69092	Loss: 93.087
+51200/69092	Loss: 92.651
+54400/69092	Loss: 92.951
+57600/69092	Loss: 93.302
+60800/69092	Loss: 92.218
+64000/69092	Loss: 93.281
+67200/69092	Loss: 93.140
+Training time 0:09:23.841306
+Epoch: 55 Average loss: 92.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 329)
+0/69092	Loss: 97.575
+3200/69092	Loss: 92.268
+6400/69092	Loss: 93.325
+9600/69092	Loss: 92.218
+12800/69092	Loss: 92.721
+16000/69092	Loss: 92.995
+19200/69092	Loss: 92.820
+22400/69092	Loss: 91.817
+25600/69092	Loss: 92.479
+28800/69092	Loss: 93.091
+32000/69092	Loss: 93.483
+35200/69092	Loss: 91.549
+38400/69092	Loss: 92.100
+41600/69092	Loss: 92.307
+44800/69092	Loss: 92.972
+48000/69092	Loss: 93.736
+51200/69092	Loss: 92.991
+54400/69092	Loss: 93.274
+57600/69092	Loss: 93.542
+60800/69092	Loss: 93.596
+64000/69092	Loss: 93.094
+67200/69092	Loss: 91.901
+Training time 0:09:06.669423
+Epoch: 56 Average loss: 92.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 330)
+0/69092	Loss: 92.927
+3200/69092	Loss: 92.698
+6400/69092	Loss: 92.982
+9600/69092	Loss: 93.800
+12800/69092	Loss: 92.966
+16000/69092	Loss: 93.241
+19200/69092	Loss: 91.585
+22400/69092	Loss: 92.479
+25600/69092	Loss: 91.727
+28800/69092	Loss: 94.271
+32000/69092	Loss: 92.211
+35200/69092	Loss: 92.391
+38400/69092	Loss: 92.659
+41600/69092	Loss: 92.718
+44800/69092	Loss: 93.463
+48000/69092	Loss: 93.318
+51200/69092	Loss: 92.016
+54400/69092	Loss: 91.048
+57600/69092	Loss: 93.603
+60800/69092	Loss: 93.016
+64000/69092	Loss: 92.574
+67200/69092	Loss: 93.123
+Training time 0:09:19.401507
+Epoch: 57 Average loss: 92.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 331)
+0/69092	Loss: 80.537
+3200/69092	Loss: 92.741
+6400/69092	Loss: 91.633
+9600/69092	Loss: 91.786
+12800/69092	Loss: 92.872
+16000/69092	Loss: 92.995
+19200/69092	Loss: 92.252
+22400/69092	Loss: 93.245
+25600/69092	Loss: 93.260
+28800/69092	Loss: 93.247
+32000/69092	Loss: 92.649
+35200/69092	Loss: 93.025
+38400/69092	Loss: 91.787
+41600/69092	Loss: 91.439
+44800/69092	Loss: 92.915
+48000/69092	Loss: 91.855
+51200/69092	Loss: 93.009
+54400/69092	Loss: 94.265
+57600/69092	Loss: 92.616
+60800/69092	Loss: 93.464
+64000/69092	Loss: 93.628
+67200/69092	Loss: 93.244
+Training time 0:08:59.076508
+Epoch: 58 Average loss: 92.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 332)
+0/69092	Loss: 97.261
+3200/69092	Loss: 92.943
+6400/69092	Loss: 92.258
+9600/69092	Loss: 92.484
+12800/69092	Loss: 91.827
+16000/69092	Loss: 92.832
+19200/69092	Loss: 91.955
+22400/69092	Loss: 94.278
+25600/69092	Loss: 94.405
+28800/69092	Loss: 92.715
+32000/69092	Loss: 91.639
+35200/69092	Loss: 91.069
+38400/69092	Loss: 92.167
+41600/69092	Loss: 93.190
+44800/69092	Loss: 92.525
+48000/69092	Loss: 91.678
+51200/69092	Loss: 93.416
+54400/69092	Loss: 92.801
+57600/69092	Loss: 91.383
+60800/69092	Loss: 93.379
+64000/69092	Loss: 94.608
+67200/69092	Loss: 93.466
+Training time 0:09:19.607324
+Epoch: 59 Average loss: 92.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 333)
+0/69092	Loss: 95.697
+3200/69092	Loss: 90.910
+6400/69092	Loss: 94.230
+9600/69092	Loss: 92.091
+12800/69092	Loss: 93.166
+16000/69092	Loss: 93.982
+19200/69092	Loss: 91.477
+22400/69092	Loss: 92.561
+25600/69092	Loss: 92.917
+28800/69092	Loss: 92.715
+32000/69092	Loss: 93.933
+35200/69092	Loss: 92.997
+38400/69092	Loss: 92.920
+41600/69092	Loss: 91.964
+44800/69092	Loss: 93.404
+48000/69092	Loss: 93.127
+51200/69092	Loss: 91.331
+54400/69092	Loss: 93.219
+57600/69092	Loss: 94.402
+60800/69092	Loss: 92.442
+64000/69092	Loss: 91.941
+67200/69092	Loss: 93.307
+Training time 0:09:13.870528
+Epoch: 60 Average loss: 92.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 334)
+0/69092	Loss: 94.789
+3200/69092	Loss: 91.223
+6400/69092	Loss: 93.083
+9600/69092	Loss: 92.612
+12800/69092	Loss: 92.889
+16000/69092	Loss: 93.315
+19200/69092	Loss: 94.172
+22400/69092	Loss: 92.083
+25600/69092	Loss: 91.740
+28800/69092	Loss: 92.869
+32000/69092	Loss: 92.003
+35200/69092	Loss: 93.132
+38400/69092	Loss: 94.067
+41600/69092	Loss: 92.680
+44800/69092	Loss: 92.031
+48000/69092	Loss: 90.195
+51200/69092	Loss: 92.418
+54400/69092	Loss: 93.042
+57600/69092	Loss: 92.979
+60800/69092	Loss: 92.918
+64000/69092	Loss: 93.784
+67200/69092	Loss: 92.155
+Training time 0:09:11.371413
+Epoch: 61 Average loss: 92.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 335)
+0/69092	Loss: 93.223
+3200/69092	Loss: 93.363
+6400/69092	Loss: 92.555
+9600/69092	Loss: 92.281
+12800/69092	Loss: 92.126
+16000/69092	Loss: 91.309
+19200/69092	Loss: 92.277
+22400/69092	Loss: 92.563
+25600/69092	Loss: 93.179
+28800/69092	Loss: 92.375
+32000/69092	Loss: 93.928
+35200/69092	Loss: 92.101
+38400/69092	Loss: 91.988
+41600/69092	Loss: 93.135
+44800/69092	Loss: 94.172
+48000/69092	Loss: 93.787
+51200/69092	Loss: 93.077
+54400/69092	Loss: 92.190
+57600/69092	Loss: 91.280
+60800/69092	Loss: 93.947
+64000/69092	Loss: 94.148
+67200/69092	Loss: 92.484
+Training time 0:09:20.132109
+Epoch: 62 Average loss: 92.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 336)
+0/69092	Loss: 88.215
+3200/69092	Loss: 92.615
+6400/69092	Loss: 92.780
+9600/69092	Loss: 92.886
+12800/69092	Loss: 93.494
+16000/69092	Loss: 92.624
+19200/69092	Loss: 93.661
+22400/69092	Loss: 93.841
+25600/69092	Loss: 92.660
+28800/69092	Loss: 93.783
+32000/69092	Loss: 91.765
+35200/69092	Loss: 92.750
+38400/69092	Loss: 93.049
+41600/69092	Loss: 92.542
+44800/69092	Loss: 92.338
+48000/69092	Loss: 93.033
+51200/69092	Loss: 91.889
+54400/69092	Loss: 92.742
+57600/69092	Loss: 92.720
+60800/69092	Loss: 92.299
+64000/69092	Loss: 91.584
+67200/69092	Loss: 93.228
+Training time 0:09:04.761640
+Epoch: 63 Average loss: 92.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 337)
+0/69092	Loss: 89.847
+3200/69092	Loss: 92.129
+6400/69092	Loss: 93.793
+9600/69092	Loss: 92.179
+12800/69092	Loss: 93.794
+16000/69092	Loss: 92.462
+19200/69092	Loss: 93.471
+22400/69092	Loss: 92.942
+25600/69092	Loss: 93.235
+28800/69092	Loss: 92.808
+32000/69092	Loss: 92.041
+35200/69092	Loss: 92.615
+38400/69092	Loss: 91.374
+41600/69092	Loss: 91.330
+44800/69092	Loss: 93.226
+48000/69092	Loss: 94.729
+51200/69092	Loss: 91.781
+54400/69092	Loss: 92.486
+57600/69092	Loss: 92.895
+60800/69092	Loss: 92.269
+64000/69092	Loss: 91.702
+67200/69092	Loss: 92.197
+Training time 0:09:06.237376
+Epoch: 64 Average loss: 92.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 338)
+0/69092	Loss: 94.393
+3200/69092	Loss: 93.704
+6400/69092	Loss: 93.066
+9600/69092	Loss: 92.929
+12800/69092	Loss: 92.408
+16000/69092	Loss: 92.560
+19200/69092	Loss: 91.174
+22400/69092	Loss: 92.738
+25600/69092	Loss: 91.986
+28800/69092	Loss: 92.754
+32000/69092	Loss: 91.361
+35200/69092	Loss: 93.694
+38400/69092	Loss: 92.798
+41600/69092	Loss: 91.758
+44800/69092	Loss: 91.921
+48000/69092	Loss: 93.418
+51200/69092	Loss: 92.257
+54400/69092	Loss: 95.055
+57600/69092	Loss: 93.380
+60800/69092	Loss: 94.093
+64000/69092	Loss: 91.634
+67200/69092	Loss: 92.647
+Training time 0:09:07.762064
+Epoch: 65 Average loss: 92.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 339)
+0/69092	Loss: 86.038
+3200/69092	Loss: 93.798
+6400/69092	Loss: 93.210
+9600/69092	Loss: 91.563
+12800/69092	Loss: 93.473
+16000/69092	Loss: 91.733
+19200/69092	Loss: 91.998
+22400/69092	Loss: 93.425
+25600/69092	Loss: 93.737
+28800/69092	Loss: 91.113
+32000/69092	Loss: 93.119
+35200/69092	Loss: 92.425
+38400/69092	Loss: 93.718
+41600/69092	Loss: 91.998
+44800/69092	Loss: 93.094
+48000/69092	Loss: 92.465
+51200/69092	Loss: 92.835
+54400/69092	Loss: 92.684
+57600/69092	Loss: 91.931
+60800/69092	Loss: 92.704
+64000/69092	Loss: 92.822
+67200/69092	Loss: 91.625
+Training time 0:09:13.169273
+Epoch: 66 Average loss: 92.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 340)
+0/69092	Loss: 89.037
+3200/69092	Loss: 91.810
+6400/69092	Loss: 92.360
+9600/69092	Loss: 93.140
+12800/69092	Loss: 92.541
+16000/69092	Loss: 93.934
+19200/69092	Loss: 93.167
+22400/69092	Loss: 92.129
+25600/69092	Loss: 92.710
+28800/69092	Loss: 92.049
+32000/69092	Loss: 92.884
+35200/69092	Loss: 92.476
+38400/69092	Loss: 93.797
+41600/69092	Loss: 93.568
+44800/69092	Loss: 93.645
+48000/69092	Loss: 92.282
+51200/69092	Loss: 92.997
+54400/69092	Loss: 94.692
+57600/69092	Loss: 91.854
+60800/69092	Loss: 92.538
+64000/69092	Loss: 92.900
+67200/69092	Loss: 90.296
+Training time 0:09:04.855597
+Epoch: 67 Average loss: 92.71
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 341)
+0/69092	Loss: 94.247
+3200/69092	Loss: 93.142
+6400/69092	Loss: 92.362
+9600/69092	Loss: 93.531
+12800/69092	Loss: 93.227
+16000/69092	Loss: 93.134
+19200/69092	Loss: 92.585
+22400/69092	Loss: 92.774
+25600/69092	Loss: 92.837
+28800/69092	Loss: 92.629
+32000/69092	Loss: 92.789
+35200/69092	Loss: 92.988
+38400/69092	Loss: 91.701
+41600/69092	Loss: 92.462
+44800/69092	Loss: 92.286
+48000/69092	Loss: 92.056
+51200/69092	Loss: 92.748
+54400/69092	Loss: 93.425
+57600/69092	Loss: 92.800
+60800/69092	Loss: 92.203
+64000/69092	Loss: 93.046
+67200/69092	Loss: 91.332
+Training time 0:09:20.219479
+Epoch: 68 Average loss: 92.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 342)
+0/69092	Loss: 94.114
+3200/69092	Loss: 92.626
+6400/69092	Loss: 92.000
+9600/69092	Loss: 92.182
+12800/69092	Loss: 92.931
+16000/69092	Loss: 92.683
+19200/69092	Loss: 92.599
+22400/69092	Loss: 93.828
+25600/69092	Loss: 92.619
+28800/69092	Loss: 92.376
+32000/69092	Loss: 92.293
+35200/69092	Loss: 92.402
+38400/69092	Loss: 92.099
+41600/69092	Loss: 93.837
+44800/69092	Loss: 93.860
+48000/69092	Loss: 92.235
+51200/69092	Loss: 93.947
+54400/69092	Loss: 93.093
+57600/69092	Loss: 93.099
+60800/69092	Loss: 91.532
+64000/69092	Loss: 92.334
+67200/69092	Loss: 93.184
+Training time 0:09:17.056017
+Epoch: 69 Average loss: 92.69
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 343)
+0/69092	Loss: 94.984
+3200/69092	Loss: 93.035
+6400/69092	Loss: 92.881
+9600/69092	Loss: 94.114
+12800/69092	Loss: 92.079
+16000/69092	Loss: 92.413
+19200/69092	Loss: 92.954
+22400/69092	Loss: 92.325
+25600/69092	Loss: 93.133
+28800/69092	Loss: 92.842
+32000/69092	Loss: 92.430
+35200/69092	Loss: 93.479
+38400/69092	Loss: 92.938
+41600/69092	Loss: 91.762
+44800/69092	Loss: 92.856
+48000/69092	Loss: 92.513
+51200/69092	Loss: 91.970
+54400/69092	Loss: 91.756
+57600/69092	Loss: 93.176
+60800/69092	Loss: 92.761
+64000/69092	Loss: 92.831
+67200/69092	Loss: 91.815
+Training time 0:09:24.122106
+Epoch: 70 Average loss: 92.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 344)
+0/69092	Loss: 101.133
+3200/69092	Loss: 93.217
+6400/69092	Loss: 93.222
+9600/69092	Loss: 91.015
+12800/69092	Loss: 92.314
+16000/69092	Loss: 90.406
+19200/69092	Loss: 92.745
+22400/69092	Loss: 92.929
+25600/69092	Loss: 93.717
+28800/69092	Loss: 92.662
+32000/69092	Loss: 91.972
+35200/69092	Loss: 91.797
+38400/69092	Loss: 91.946
+41600/69092	Loss: 93.048
+44800/69092	Loss: 93.003
+48000/69092	Loss: 92.246
+51200/69092	Loss: 92.159
+54400/69092	Loss: 92.750
+57600/69092	Loss: 92.997
+60800/69092	Loss: 92.647
+64000/69092	Loss: 92.233
+67200/69092	Loss: 93.211
+Training time 0:09:00.905668
+Epoch: 71 Average loss: 92.50
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 345)
+0/69092	Loss: 101.036
+3200/69092	Loss: 91.632
+6400/69092	Loss: 92.074
+9600/69092	Loss: 93.010
+12800/69092	Loss: 92.954
+16000/69092	Loss: 92.502
+19200/69092	Loss: 92.092
+22400/69092	Loss: 91.572
+25600/69092	Loss: 92.410
+28800/69092	Loss: 92.332
+32000/69092	Loss: 93.616
+35200/69092	Loss: 92.349
+38400/69092	Loss: 92.732
+41600/69092	Loss: 92.395
+44800/69092	Loss: 92.790
+48000/69092	Loss: 92.697
+51200/69092	Loss: 93.355
+54400/69092	Loss: 91.957
+57600/69092	Loss: 92.419
+60800/69092	Loss: 93.072
+64000/69092	Loss: 93.767
+67200/69092	Loss: 92.532
+Training time 0:09:02.298593
+Epoch: 72 Average loss: 92.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 346)
+0/69092	Loss: 90.406
+3200/69092	Loss: 91.837
+6400/69092	Loss: 92.679
+9600/69092	Loss: 94.408
+12800/69092	Loss: 93.613
+16000/69092	Loss: 92.154
+19200/69092	Loss: 92.112
+22400/69092	Loss: 92.650
+25600/69092	Loss: 92.385
+28800/69092	Loss: 90.958
+32000/69092	Loss: 93.429
+35200/69092	Loss: 93.716
+38400/69092	Loss: 93.348
+41600/69092	Loss: 90.943
+44800/69092	Loss: 91.621
+48000/69092	Loss: 92.789
+51200/69092	Loss: 92.514
+54400/69092	Loss: 92.710
+57600/69092	Loss: 90.896
+60800/69092	Loss: 93.166
+64000/69092	Loss: 93.524
+67200/69092	Loss: 92.438
+Training time 0:08:52.426041
+Epoch: 73 Average loss: 92.59
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 347)
+0/69092	Loss: 94.813
+3200/69092	Loss: 91.527
+6400/69092	Loss: 93.465
+9600/69092	Loss: 91.611
+12800/69092	Loss: 93.184
+16000/69092	Loss: 93.312
+19200/69092	Loss: 92.665
+22400/69092	Loss: 91.151
+25600/69092	Loss: 92.765
+28800/69092	Loss: 91.962
+32000/69092	Loss: 93.744
+35200/69092	Loss: 93.317
+38400/69092	Loss: 92.749
+41600/69092	Loss: 93.280
+44800/69092	Loss: 92.477
+48000/69092	Loss: 93.299
+51200/69092	Loss: 92.521
+54400/69092	Loss: 92.499
+57600/69092	Loss: 92.273
+60800/69092	Loss: 93.128
+64000/69092	Loss: 93.439
+67200/69092	Loss: 91.348
+Training time 0:09:04.808072
+Epoch: 74 Average loss: 92.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 348)
+0/69092	Loss: 88.978
+3200/69092	Loss: 93.339
+6400/69092	Loss: 91.512
+9600/69092	Loss: 93.294
+12800/69092	Loss: 92.480
+16000/69092	Loss: 93.985
+19200/69092	Loss: 91.829
+22400/69092	Loss: 92.074
+25600/69092	Loss: 92.779
+28800/69092	Loss: 93.188
+32000/69092	Loss: 92.488
+35200/69092	Loss: 90.728
+38400/69092	Loss: 91.603
+41600/69092	Loss: 93.129
+44800/69092	Loss: 93.415
+48000/69092	Loss: 91.470
+51200/69092	Loss: 92.375
+54400/69092	Loss: 92.552
+57600/69092	Loss: 93.385
+60800/69092	Loss: 91.635
+64000/69092	Loss: 92.538
+67200/69092	Loss: 93.602
+Training time 0:09:14.036294
+Epoch: 75 Average loss: 92.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 349)
+0/69092	Loss: 88.200
+3200/69092	Loss: 91.713
+6400/69092	Loss: 92.429
+9600/69092	Loss: 92.610
+12800/69092	Loss: 92.892
+16000/69092	Loss: 91.790
+19200/69092	Loss: 92.742
+22400/69092	Loss: 92.233
+25600/69092	Loss: 93.628
+28800/69092	Loss: 90.922
+32000/69092	Loss: 91.466
+35200/69092	Loss: 92.868
+38400/69092	Loss: 93.775
+41600/69092	Loss: 92.962
+44800/69092	Loss: 92.343
+48000/69092	Loss: 92.501
+51200/69092	Loss: 94.172
+54400/69092	Loss: 92.765
+57600/69092	Loss: 92.924
+60800/69092	Loss: 93.382
+64000/69092	Loss: 91.429
+67200/69092	Loss: 92.952
+Training time 0:09:11.248002
+Epoch: 76 Average loss: 92.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 350)
+0/69092	Loss: 99.020
+3200/69092	Loss: 93.539
+6400/69092	Loss: 91.345
+9600/69092	Loss: 93.098
+12800/69092	Loss: 91.953
+16000/69092	Loss: 93.597
+19200/69092	Loss: 92.772
+22400/69092	Loss: 94.078
+25600/69092	Loss: 92.692
+28800/69092	Loss: 93.393
+32000/69092	Loss: 91.140
+35200/69092	Loss: 91.590
+38400/69092	Loss: 93.622
+41600/69092	Loss: 91.336
+44800/69092	Loss: 92.285
+48000/69092	Loss: 92.387
+51200/69092	Loss: 91.141
+54400/69092	Loss: 94.264
+57600/69092	Loss: 93.215
+60800/69092	Loss: 93.102
+64000/69092	Loss: 91.942
+67200/69092	Loss: 93.209
+Training time 0:09:20.061150
+Epoch: 77 Average loss: 92.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 351)
+0/69092	Loss: 92.395
+3200/69092	Loss: 92.189
+6400/69092	Loss: 92.322
+9600/69092	Loss: 91.407
+12800/69092	Loss: 91.891
+16000/69092	Loss: 93.186
+19200/69092	Loss: 93.585
+22400/69092	Loss: 93.631
+25600/69092	Loss: 93.334
+28800/69092	Loss: 93.689
+32000/69092	Loss: 91.948
+35200/69092	Loss: 91.973
+38400/69092	Loss: 92.419
+41600/69092	Loss: 92.235
+44800/69092	Loss: 92.814
+48000/69092	Loss: 93.729
+51200/69092	Loss: 92.181
+54400/69092	Loss: 92.826
+57600/69092	Loss: 91.554
+60800/69092	Loss: 91.470
+64000/69092	Loss: 92.387
+67200/69092	Loss: 92.213
+Training time 0:09:22.655556
+Epoch: 78 Average loss: 92.53
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 352)
+0/69092	Loss: 92.701
+3200/69092	Loss: 94.436
+6400/69092	Loss: 92.113
+9600/69092	Loss: 91.777
+12800/69092	Loss: 93.225
+16000/69092	Loss: 93.088
+19200/69092	Loss: 93.043
+22400/69092	Loss: 92.941
+25600/69092	Loss: 91.669
+28800/69092	Loss: 91.849
+32000/69092	Loss: 93.743
+35200/69092	Loss: 92.708
+38400/69092	Loss: 93.142
+41600/69092	Loss: 92.153
+44800/69092	Loss: 92.138
+48000/69092	Loss: 93.251
+51200/69092	Loss: 91.722
+54400/69092	Loss: 92.566
+57600/69092	Loss: 92.368
+60800/69092	Loss: 90.682
+64000/69092	Loss: 93.346
+67200/69092	Loss: 93.698
+Training time 0:09:28.585701
+Epoch: 79 Average loss: 92.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 353)
+0/69092	Loss: 92.916
+3200/69092	Loss: 92.209
+6400/69092	Loss: 92.589
+9600/69092	Loss: 91.909
+12800/69092	Loss: 92.639
+16000/69092	Loss: 92.223
+19200/69092	Loss: 93.152
+22400/69092	Loss: 92.880
+25600/69092	Loss: 92.704
+28800/69092	Loss: 92.755
+32000/69092	Loss: 93.771
+35200/69092	Loss: 92.869
+38400/69092	Loss: 92.582
+41600/69092	Loss: 92.074
+44800/69092	Loss: 92.419
+48000/69092	Loss: 92.237
+51200/69092	Loss: 92.565
+54400/69092	Loss: 93.548
+57600/69092	Loss: 92.752
+60800/69092	Loss: 92.263
+64000/69092	Loss: 91.161
+67200/69092	Loss: 92.716
+Training time 0:09:24.779396
+Epoch: 80 Average loss: 92.53
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 354)
+0/69092	Loss: 89.718
+3200/69092	Loss: 92.237
+6400/69092	Loss: 91.515
+9600/69092	Loss: 93.306
+12800/69092	Loss: 93.117
+16000/69092	Loss: 91.449
+19200/69092	Loss: 93.427
+22400/69092	Loss: 91.727
+25600/69092	Loss: 92.545
+28800/69092	Loss: 91.876
+32000/69092	Loss: 92.226
+35200/69092	Loss: 92.364
+38400/69092	Loss: 91.616
+41600/69092	Loss: 92.890
+44800/69092	Loss: 92.879
+48000/69092	Loss: 92.443
+51200/69092	Loss: 94.304
+54400/69092	Loss: 92.509
+57600/69092	Loss: 92.717
+60800/69092	Loss: 93.267
+64000/69092	Loss: 92.295
+67200/69092	Loss: 91.868
+Training time 0:09:10.255964
+Epoch: 81 Average loss: 92.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 355)
+0/69092	Loss: 95.241
+3200/69092	Loss: 92.047
+6400/69092	Loss: 92.330
+9600/69092	Loss: 92.093
+12800/69092	Loss: 91.874
+16000/69092	Loss: 92.867
+19200/69092	Loss: 93.324
+22400/69092	Loss: 93.148
+25600/69092	Loss: 92.900
+28800/69092	Loss: 92.408
+32000/69092	Loss: 91.952
+35200/69092	Loss: 92.847
+38400/69092	Loss: 90.621
+41600/69092	Loss: 92.639
+44800/69092	Loss: 92.216
+48000/69092	Loss: 92.020
+51200/69092	Loss: 92.817
+54400/69092	Loss: 91.798
+57600/69092	Loss: 92.978
+60800/69092	Loss: 92.888
+64000/69092	Loss: 93.224
+67200/69092	Loss: 93.445
+Training time 0:09:14.945449
+Epoch: 82 Average loss: 92.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 356)
+0/69092	Loss: 88.614
+3200/69092	Loss: 92.839
+6400/69092	Loss: 91.376
+9600/69092	Loss: 93.249
+12800/69092	Loss: 92.303
+16000/69092	Loss: 92.483
+19200/69092	Loss: 92.411
+22400/69092	Loss: 91.891
+25600/69092	Loss: 94.025
+28800/69092	Loss: 92.734
+32000/69092	Loss: 91.745
+35200/69092	Loss: 91.762
+38400/69092	Loss: 92.831
+41600/69092	Loss: 92.359
+44800/69092	Loss: 91.865
+48000/69092	Loss: 93.978
+51200/69092	Loss: 92.783
+54400/69092	Loss: 92.876
+57600/69092	Loss: 92.456
+60800/69092	Loss: 92.798
+64000/69092	Loss: 92.739
+67200/69092	Loss: 92.764
+Training time 0:09:00.189561
+Epoch: 83 Average loss: 92.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 357)
+0/69092	Loss: 92.353
+3200/69092	Loss: 92.025
+6400/69092	Loss: 91.983
+9600/69092	Loss: 92.258
+12800/69092	Loss: 92.672
+16000/69092	Loss: 91.614
+19200/69092	Loss: 93.940
+22400/69092	Loss: 92.666
+25600/69092	Loss: 93.206
+28800/69092	Loss: 94.376
+32000/69092	Loss: 93.161
+35200/69092	Loss: 91.801
+38400/69092	Loss: 91.450
+41600/69092	Loss: 92.336
+44800/69092	Loss: 92.474
+48000/69092	Loss: 93.434
+51200/69092	Loss: 91.323
+54400/69092	Loss: 91.694
+57600/69092	Loss: 93.193
+60800/69092	Loss: 91.834
+64000/69092	Loss: 93.180
+67200/69092	Loss: 92.002
+Training time 0:09:06.752821
+Epoch: 84 Average loss: 92.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 358)
+0/69092	Loss: 89.928
+3200/69092	Loss: 91.577
+6400/69092	Loss: 92.177
+9600/69092	Loss: 92.456
+12800/69092	Loss: 92.114
+16000/69092	Loss: 92.926
+19200/69092	Loss: 91.164
+22400/69092	Loss: 92.419
+25600/69092	Loss: 92.565
+28800/69092	Loss: 92.107
+32000/69092	Loss: 91.972
+35200/69092	Loss: 91.662
+38400/69092	Loss: 93.627
+41600/69092	Loss: 93.307
+44800/69092	Loss: 92.325
+48000/69092	Loss: 93.227
+51200/69092	Loss: 92.681
+54400/69092	Loss: 94.165
+57600/69092	Loss: 92.675
+60800/69092	Loss: 92.131
+64000/69092	Loss: 91.804
+67200/69092	Loss: 92.121
+Training time 0:08:46.237079
+Epoch: 85 Average loss: 92.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 359)
+0/69092	Loss: 96.206
+3200/69092	Loss: 92.961
+6400/69092	Loss: 91.041
+9600/69092	Loss: 92.624
+12800/69092	Loss: 91.493
+16000/69092	Loss: 91.728
+19200/69092	Loss: 90.083
+22400/69092	Loss: 92.817
+25600/69092	Loss: 92.751
+28800/69092	Loss: 92.966
+32000/69092	Loss: 92.241
+35200/69092	Loss: 93.226
+38400/69092	Loss: 92.007
+41600/69092	Loss: 94.626
+44800/69092	Loss: 92.399
+48000/69092	Loss: 92.921
+51200/69092	Loss: 92.373
+54400/69092	Loss: 93.409
+57600/69092	Loss: 93.640
+60800/69092	Loss: 92.176
+64000/69092	Loss: 92.598
+67200/69092	Loss: 92.194
+Training time 0:09:09.692338
+Epoch: 86 Average loss: 92.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 360)
+0/69092	Loss: 88.608
+3200/69092	Loss: 92.030
+6400/69092	Loss: 91.621
+9600/69092	Loss: 93.396
+12800/69092	Loss: 92.679
+16000/69092	Loss: 94.066
+19200/69092	Loss: 92.588
+22400/69092	Loss: 91.318
+25600/69092	Loss: 91.912
+28800/69092	Loss: 91.588
+32000/69092	Loss: 92.873
+35200/69092	Loss: 93.128
+38400/69092	Loss: 92.898
+41600/69092	Loss: 92.867
+44800/69092	Loss: 93.031
+48000/69092	Loss: 92.335
+51200/69092	Loss: 91.190
+54400/69092	Loss: 92.458
+57600/69092	Loss: 92.221
+60800/69092	Loss: 92.870
+64000/69092	Loss: 92.621
+67200/69092	Loss: 93.696
+Training time 0:09:14.589407
+Epoch: 87 Average loss: 92.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 361)
+0/69092	Loss: 93.102
+3200/69092	Loss: 93.604
+6400/69092	Loss: 93.492
+9600/69092	Loss: 92.752
+12800/69092	Loss: 92.960
+16000/69092	Loss: 93.057
+19200/69092	Loss: 93.448
+22400/69092	Loss: 92.796
+25600/69092	Loss: 93.914
+28800/69092	Loss: 90.658
+32000/69092	Loss: 92.540
+35200/69092	Loss: 92.774
+38400/69092	Loss: 93.041
+41600/69092	Loss: 91.714
+44800/69092	Loss: 92.051
+48000/69092	Loss: 91.279
+51200/69092	Loss: 92.665
+54400/69092	Loss: 91.531
+57600/69092	Loss: 91.586
+60800/69092	Loss: 92.973
+64000/69092	Loss: 93.911
+67200/69092	Loss: 91.511
+Training time 0:09:09.556676
+Epoch: 88 Average loss: 92.59
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 362)
+0/69092	Loss: 104.718
+3200/69092	Loss: 91.965
+6400/69092	Loss: 91.982
+9600/69092	Loss: 91.386
+12800/69092	Loss: 93.186
+16000/69092	Loss: 91.821
+19200/69092	Loss: 91.277
+22400/69092	Loss: 91.287
+25600/69092	Loss: 93.302
+28800/69092	Loss: 92.187
+32000/69092	Loss: 92.465
+35200/69092	Loss: 93.042
+38400/69092	Loss: 92.904
+41600/69092	Loss: 93.602
+44800/69092	Loss: 92.662
+48000/69092	Loss: 92.210
+51200/69092	Loss: 92.860
+54400/69092	Loss: 92.116
+57600/69092	Loss: 93.576
+60800/69092	Loss: 92.395
+64000/69092	Loss: 93.066
+67200/69092	Loss: 92.533
+Training time 0:09:17.192621
+Epoch: 89 Average loss: 92.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 363)
+0/69092	Loss: 103.000
+3200/69092	Loss: 92.302
+6400/69092	Loss: 92.547
+9600/69092	Loss: 92.996
+12800/69092	Loss: 93.129
+16000/69092	Loss: 92.819
+19200/69092	Loss: 91.761
+22400/69092	Loss: 91.859
+25600/69092	Loss: 92.097
+28800/69092	Loss: 93.936
+32000/69092	Loss: 92.431
+35200/69092	Loss: 92.406
+38400/69092	Loss: 92.025
+41600/69092	Loss: 91.283
+44800/69092	Loss: 92.613
+48000/69092	Loss: 91.666
+51200/69092	Loss: 92.467
+54400/69092	Loss: 92.308
+57600/69092	Loss: 93.005
+60800/69092	Loss: 92.721
+64000/69092	Loss: 92.137
+67200/69092	Loss: 91.879
+Training time 0:09:08.428994
+Epoch: 90 Average loss: 92.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 364)
+0/69092	Loss: 82.716
+3200/69092	Loss: 92.449
+6400/69092	Loss: 91.703
+9600/69092	Loss: 92.598
+12800/69092	Loss: 92.333
+16000/69092	Loss: 92.989
+19200/69092	Loss: 91.603
+22400/69092	Loss: 92.084
+25600/69092	Loss: 92.378
+28800/69092	Loss: 92.196
+32000/69092	Loss: 91.555
+35200/69092	Loss: 92.045
+38400/69092	Loss: 92.567
+41600/69092	Loss: 92.949
+44800/69092	Loss: 93.265
+48000/69092	Loss: 92.327
+51200/69092	Loss: 92.595
+54400/69092	Loss: 92.712
+57600/69092	Loss: 94.190
+60800/69092	Loss: 91.594
+64000/69092	Loss: 93.643
+67200/69092	Loss: 92.694
+Training time 0:09:12.135638
+Epoch: 91 Average loss: 92.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 365)
+0/69092	Loss: 104.875
+3200/69092	Loss: 92.339
+6400/69092	Loss: 92.153
+9600/69092	Loss: 92.778
+12800/69092	Loss: 91.941
+16000/69092	Loss: 91.447
+19200/69092	Loss: 92.550
+22400/69092	Loss: 92.549
+25600/69092	Loss: 93.416
+28800/69092	Loss: 93.126
+32000/69092	Loss: 92.138
+35200/69092	Loss: 93.260
+38400/69092	Loss: 91.350
+41600/69092	Loss: 91.683
+44800/69092	Loss: 91.188
+48000/69092	Loss: 91.367
+51200/69092	Loss: 92.264
+54400/69092	Loss: 92.671
+57600/69092	Loss: 92.402
+60800/69092	Loss: 93.257
+64000/69092	Loss: 93.056
+67200/69092	Loss: 93.728
+Training time 0:09:27.749909
+Epoch: 92 Average loss: 92.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 366)
+0/69092	Loss: 93.427
+3200/69092	Loss: 92.449
+6400/69092	Loss: 92.103
+9600/69092	Loss: 92.246
+12800/69092	Loss: 92.679
+16000/69092	Loss: 92.186
+19200/69092	Loss: 92.240
+22400/69092	Loss: 91.309
+25600/69092	Loss: 93.193
+28800/69092	Loss: 92.451
+32000/69092	Loss: 92.282
+35200/69092	Loss: 92.168
+38400/69092	Loss: 92.788
+41600/69092	Loss: 91.928
+44800/69092	Loss: 91.749
+48000/69092	Loss: 93.404
+51200/69092	Loss: 92.610
+54400/69092	Loss: 92.807
+57600/69092	Loss: 93.625
+60800/69092	Loss: 92.166
+64000/69092	Loss: 92.650
+67200/69092	Loss: 92.156
+Training time 0:08:46.452016
+Epoch: 93 Average loss: 92.45
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 367)
+0/69092	Loss: 96.524
+3200/69092	Loss: 92.316
+6400/69092	Loss: 93.008
+9600/69092	Loss: 90.796
+12800/69092	Loss: 92.777
+16000/69092	Loss: 93.128
+19200/69092	Loss: 91.016
+22400/69092	Loss: 92.290
+25600/69092	Loss: 92.625
+28800/69092	Loss: 94.257
+32000/69092	Loss: 91.106
+35200/69092	Loss: 92.826
+38400/69092	Loss: 91.789
+41600/69092	Loss: 91.184
+44800/69092	Loss: 91.977
+48000/69092	Loss: 92.299
+51200/69092	Loss: 94.001
+54400/69092	Loss: 93.078
+57600/69092	Loss: 92.552
+60800/69092	Loss: 91.626
+64000/69092	Loss: 91.538
+67200/69092	Loss: 92.795
+Training time 0:08:58.323246
+Epoch: 94 Average loss: 92.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 368)
+0/69092	Loss: 95.575
+3200/69092	Loss: 90.826
+6400/69092	Loss: 91.631
+9600/69092	Loss: 92.376
+12800/69092	Loss: 92.371
+16000/69092	Loss: 93.220
+19200/69092	Loss: 94.069
+22400/69092	Loss: 93.650
+25600/69092	Loss: 92.034
+28800/69092	Loss: 92.200
+32000/69092	Loss: 92.388
+35200/69092	Loss: 91.503
+38400/69092	Loss: 93.614
+41600/69092	Loss: 92.213
+44800/69092	Loss: 92.917
+48000/69092	Loss: 93.453
+51200/69092	Loss: 90.660
+54400/69092	Loss: 92.457
+57600/69092	Loss: 92.100
+60800/69092	Loss: 91.673
+64000/69092	Loss: 91.396
+67200/69092	Loss: 93.210
+Training time 0:09:07.354259
+Epoch: 95 Average loss: 92.42
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 369)
+0/69092	Loss: 81.568
+3200/69092	Loss: 91.293
+6400/69092	Loss: 93.157
+9600/69092	Loss: 93.041
+12800/69092	Loss: 91.778
+16000/69092	Loss: 92.214
+19200/69092	Loss: 90.883
+22400/69092	Loss: 90.262
+25600/69092	Loss: 92.852
+28800/69092	Loss: 91.931
+32000/69092	Loss: 92.010
+35200/69092	Loss: 92.932
+38400/69092	Loss: 92.611
+41600/69092	Loss: 93.099
+44800/69092	Loss: 92.877
+48000/69092	Loss: 92.357
+51200/69092	Loss: 92.563
+54400/69092	Loss: 92.527
+57600/69092	Loss: 92.992
+60800/69092	Loss: 92.935
+64000/69092	Loss: 92.053
+67200/69092	Loss: 92.539
+Training time 0:09:11.212684
+Epoch: 96 Average loss: 92.32
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 370)
+0/69092	Loss: 98.752
+3200/69092	Loss: 90.993
+6400/69092	Loss: 92.489
+9600/69092	Loss: 92.776
+12800/69092	Loss: 92.002
+16000/69092	Loss: 92.147
+19200/69092	Loss: 91.973
+22400/69092	Loss: 92.433
+25600/69092	Loss: 92.714
+28800/69092	Loss: 92.857
+32000/69092	Loss: 92.600
+35200/69092	Loss: 91.916
+38400/69092	Loss: 92.645
+41600/69092	Loss: 92.834
+44800/69092	Loss: 92.084
+48000/69092	Loss: 91.984
+51200/69092	Loss: 91.730
+54400/69092	Loss: 93.363
+57600/69092	Loss: 93.023
+60800/69092	Loss: 92.141
+64000/69092	Loss: 92.364
+67200/69092	Loss: 93.095
+Training time 0:09:20.304428
+Epoch: 97 Average loss: 92.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 371)
+0/69092	Loss: 84.726
+3200/69092	Loss: 91.747
+6400/69092	Loss: 90.850
+9600/69092	Loss: 92.755
+12800/69092	Loss: 92.124
+16000/69092	Loss: 92.311
+19200/69092	Loss: 93.082
+22400/69092	Loss: 92.177
+25600/69092	Loss: 91.205
+28800/69092	Loss: 93.862
+32000/69092	Loss: 93.168
+35200/69092	Loss: 92.310
+38400/69092	Loss: 92.646
+41600/69092	Loss: 90.954
+44800/69092	Loss: 93.012
+48000/69092	Loss: 92.678
+51200/69092	Loss: 92.702
+54400/69092	Loss: 92.416
+57600/69092	Loss: 91.733
+60800/69092	Loss: 93.885
+64000/69092	Loss: 92.027
+67200/69092	Loss: 91.699
+Training time 0:09:13.793960
+Epoch: 98 Average loss: 92.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 372)
+0/69092	Loss: 90.081
+3200/69092	Loss: 92.782
+6400/69092	Loss: 92.002
+9600/69092	Loss: 93.358
+12800/69092	Loss: 91.384
+16000/69092	Loss: 92.188
+19200/69092	Loss: 93.008
+22400/69092	Loss: 92.693
+25600/69092	Loss: 92.169
+28800/69092	Loss: 92.704
+32000/69092	Loss: 92.604
+35200/69092	Loss: 93.166
+38400/69092	Loss: 91.065
+41600/69092	Loss: 92.471
+44800/69092	Loss: 92.023
+48000/69092	Loss: 92.736
+51200/69092	Loss: 91.925
+54400/69092	Loss: 92.390
+57600/69092	Loss: 92.138
+60800/69092	Loss: 91.775
+64000/69092	Loss: 93.261
+67200/69092	Loss: 92.011
+Training time 0:09:04.739344
+Epoch: 99 Average loss: 92.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 373)
+0/69092	Loss: 93.962
+3200/69092	Loss: 92.368
+6400/69092	Loss: 91.617
+9600/69092	Loss: 90.768
+12800/69092	Loss: 93.207
+16000/69092	Loss: 92.035
+19200/69092	Loss: 92.287
+22400/69092	Loss: 92.210
+25600/69092	Loss: 92.650
+28800/69092	Loss: 92.435
+32000/69092	Loss: 92.510
+35200/69092	Loss: 92.643
+38400/69092	Loss: 93.035
+41600/69092	Loss: 92.735
+44800/69092	Loss: 91.862
+48000/69092	Loss: 92.361
+51200/69092	Loss: 93.824
+54400/69092	Loss: 90.932
+57600/69092	Loss: 91.344
+60800/69092	Loss: 92.436
+64000/69092	Loss: 93.419
+67200/69092	Loss: 92.690
+Training time 0:09:18.714874
+Epoch: 100 Average loss: 92.38
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 374)
+0/69092	Loss: 103.066
+3200/69092	Loss: 92.092
+6400/69092	Loss: 91.992
+9600/69092	Loss: 91.224
+12800/69092	Loss: 92.488
+16000/69092	Loss: 93.364
+19200/69092	Loss: 92.584
+22400/69092	Loss: 93.243
+25600/69092	Loss: 92.120
+28800/69092	Loss: 91.267
+32000/69092	Loss: 92.206
+35200/69092	Loss: 93.500
+38400/69092	Loss: 91.371
+41600/69092	Loss: 91.104
+44800/69092	Loss: 92.495
+48000/69092	Loss: 92.449
+51200/69092	Loss: 92.511
+54400/69092	Loss: 91.929
+57600/69092	Loss: 93.250
+60800/69092	Loss: 91.732
+64000/69092	Loss: 92.609
+67200/69092	Loss: 92.654
+Training time 0:08:51.837136
+Epoch: 101 Average loss: 92.30
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 375)
+0/69092	Loss: 92.746
+3200/69092	Loss: 91.637
+6400/69092	Loss: 92.688
+9600/69092	Loss: 90.825
+12800/69092	Loss: 91.479
+16000/69092	Loss: 92.493
+19200/69092	Loss: 91.535
+22400/69092	Loss: 92.017
+25600/69092	Loss: 92.893
+28800/69092	Loss: 92.482
+32000/69092	Loss: 92.273
+35200/69092	Loss: 91.402
+38400/69092	Loss: 92.502
+41600/69092	Loss: 92.207
+44800/69092	Loss: 93.004
+48000/69092	Loss: 92.879
+51200/69092	Loss: 93.345
+54400/69092	Loss: 93.163
+57600/69092	Loss: 91.810
+60800/69092	Loss: 93.678
+64000/69092	Loss: 92.688
+67200/69092	Loss: 93.021
+Training time 0:08:56.473340
+Epoch: 102 Average loss: 92.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 376)
+0/69092	Loss: 89.314
+3200/69092	Loss: 92.020
+6400/69092	Loss: 92.702
+9600/69092	Loss: 91.382
+12800/69092	Loss: 91.895
+16000/69092	Loss: 93.160
+19200/69092	Loss: 92.146
+22400/69092	Loss: 91.990
+25600/69092	Loss: 92.041
+28800/69092	Loss: 92.134
+32000/69092	Loss: 91.965
+35200/69092	Loss: 92.147
+38400/69092	Loss: 91.780
+41600/69092	Loss: 93.073
+44800/69092	Loss: 90.884
+48000/69092	Loss: 90.093
+51200/69092	Loss: 92.549
+54400/69092	Loss: 93.637
+57600/69092	Loss: 93.680
+60800/69092	Loss: 93.024
+64000/69092	Loss: 92.193
+67200/69092	Loss: 93.562
+Training time 0:09:00.407773
+Epoch: 103 Average loss: 92.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 377)
+0/69092	Loss: 92.262
+3200/69092	Loss: 94.452
+6400/69092	Loss: 92.233
+9600/69092	Loss: 92.509
+12800/69092	Loss: 90.670
+16000/69092	Loss: 92.692
+19200/69092	Loss: 92.287
+22400/69092	Loss: 91.804
+25600/69092	Loss: 92.455
+28800/69092	Loss: 91.249
+32000/69092	Loss: 94.175
+35200/69092	Loss: 92.779
+38400/69092	Loss: 92.605
+41600/69092	Loss: 92.501
+44800/69092	Loss: 92.958
+48000/69092	Loss: 92.356
+51200/69092	Loss: 90.282
+54400/69092	Loss: 91.727
+57600/69092	Loss: 91.624
+60800/69092	Loss: 93.527
+64000/69092	Loss: 91.460
+67200/69092	Loss: 90.648
+Training time 0:08:59.421049
+Epoch: 104 Average loss: 92.19
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 378)
+0/69092	Loss: 88.826
+3200/69092	Loss: 91.335
+6400/69092	Loss: 92.654
+9600/69092	Loss: 92.926
+12800/69092	Loss: 93.326
+16000/69092	Loss: 91.624
+19200/69092	Loss: 91.837
+22400/69092	Loss: 93.082
+25600/69092	Loss: 92.662
+28800/69092	Loss: 92.629
+32000/69092	Loss: 91.681
+35200/69092	Loss: 92.898
+38400/69092	Loss: 92.053
+41600/69092	Loss: 90.738
+44800/69092	Loss: 92.545
+48000/69092	Loss: 92.181
+51200/69092	Loss: 92.485
+54400/69092	Loss: 91.714
+57600/69092	Loss: 91.719
+60800/69092	Loss: 93.318
+64000/69092	Loss: 92.722
+67200/69092	Loss: 92.365
+Training time 0:09:19.492233
+Epoch: 105 Average loss: 92.31
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 379)
+0/69092	Loss: 91.529
+3200/69092	Loss: 92.826
+6400/69092	Loss: 93.237
+9600/69092	Loss: 91.105
+12800/69092	Loss: 92.507
+16000/69092	Loss: 92.531
+19200/69092	Loss: 92.566
+22400/69092	Loss: 90.830
+25600/69092	Loss: 91.846
+28800/69092	Loss: 92.695
+32000/69092	Loss: 91.575
+35200/69092	Loss: 93.104
+38400/69092	Loss: 91.608
+41600/69092	Loss: 91.142
+44800/69092	Loss: 91.853
+48000/69092	Loss: 93.279
+51200/69092	Loss: 94.067
+54400/69092	Loss: 91.931
+57600/69092	Loss: 92.592
+60800/69092	Loss: 92.062
+64000/69092	Loss: 91.874
+67200/69092	Loss: 92.214
+Training time 0:09:15.672185
+Epoch: 106 Average loss: 92.30
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 380)
+0/69092	Loss: 94.194
+3200/69092	Loss: 91.213
+6400/69092	Loss: 92.626
+9600/69092	Loss: 92.669
+12800/69092	Loss: 91.897
+16000/69092	Loss: 91.004
+19200/69092	Loss: 92.226
+22400/69092	Loss: 92.354
+25600/69092	Loss: 91.977
+28800/69092	Loss: 93.197
+32000/69092	Loss: 90.986
+35200/69092	Loss: 92.260
+38400/69092	Loss: 92.975
+41600/69092	Loss: 93.292
+44800/69092	Loss: 92.653
+48000/69092	Loss: 92.239
+51200/69092	Loss: 93.282
+54400/69092	Loss: 93.646
+57600/69092	Loss: 91.104
+60800/69092	Loss: 92.204
+64000/69092	Loss: 90.749
+67200/69092	Loss: 92.200
+Training time 0:09:15.754790
+Epoch: 107 Average loss: 92.22
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 381)
+0/69092	Loss: 93.731
+3200/69092	Loss: 92.872
+6400/69092	Loss: 93.003
+9600/69092	Loss: 91.341
+12800/69092	Loss: 92.704
+16000/69092	Loss: 91.940
+19200/69092	Loss: 92.758
+22400/69092	Loss: 92.465
+25600/69092	Loss: 92.835
+28800/69092	Loss: 91.770
+32000/69092	Loss: 91.545
+35200/69092	Loss: 93.779
+38400/69092	Loss: 92.024
+41600/69092	Loss: 92.991
+44800/69092	Loss: 91.749
+48000/69092	Loss: 91.697
+51200/69092	Loss: 92.615
+54400/69092	Loss: 91.461
+57600/69092	Loss: 91.839
+60800/69092	Loss: 92.887
+64000/69092	Loss: 93.056
+67200/69092	Loss: 92.558
+Training time 0:09:08.943550
+Epoch: 108 Average loss: 92.37
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 382)
+0/69092	Loss: 92.492
+3200/69092	Loss: 92.741
+6400/69092	Loss: 91.364
+9600/69092	Loss: 92.145
+12800/69092	Loss: 92.186
+16000/69092	Loss: 90.767
+19200/69092	Loss: 93.248
+22400/69092	Loss: 91.511
+25600/69092	Loss: 92.218
+28800/69092	Loss: 91.278
+32000/69092	Loss: 91.371
+35200/69092	Loss: 92.631
+38400/69092	Loss: 92.230
+41600/69092	Loss: 92.179
+44800/69092	Loss: 92.089
+48000/69092	Loss: 93.679
+51200/69092	Loss: 92.663
+54400/69092	Loss: 93.295
+57600/69092	Loss: 90.916
+60800/69092	Loss: 94.807
+64000/69092	Loss: 93.444
+67200/69092	Loss: 91.806
+Training time 0:09:31.166076
+Epoch: 109 Average loss: 92.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 383)
+0/69092	Loss: 89.371
+3200/69092	Loss: 92.759
+6400/69092	Loss: 91.894
+9600/69092	Loss: 92.290
+12800/69092	Loss: 93.371
+16000/69092	Loss: 91.988
+19200/69092	Loss: 93.333
+22400/69092	Loss: 91.791
+25600/69092	Loss: 92.648
+28800/69092	Loss: 91.478
+32000/69092	Loss: 91.414
+35200/69092	Loss: 91.253
+38400/69092	Loss: 93.281
+41600/69092	Loss: 92.110
+44800/69092	Loss: 94.109
+48000/69092	Loss: 92.248
+51200/69092	Loss: 92.400
+54400/69092	Loss: 92.745
+57600/69092	Loss: 92.195
+60800/69092	Loss: 92.535
+64000/69092	Loss: 92.632
+67200/69092	Loss: 92.644
+Training time 0:09:11.690337
+Epoch: 110 Average loss: 92.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 384)
+0/69092	Loss: 93.816
+3200/69092	Loss: 91.604
+6400/69092	Loss: 91.588
+9600/69092	Loss: 90.429
+12800/69092	Loss: 91.694
+16000/69092	Loss: 92.754
+19200/69092	Loss: 94.083
+22400/69092	Loss: 92.486
+25600/69092	Loss: 93.748
+28800/69092	Loss: 91.552
+32000/69092	Loss: 92.203
+35200/69092	Loss: 92.131
+38400/69092	Loss: 92.076
+41600/69092	Loss: 93.538
+44800/69092	Loss: 91.877
+48000/69092	Loss: 92.202
+51200/69092	Loss: 93.409
+54400/69092	Loss: 92.680
+57600/69092	Loss: 92.216
+60800/69092	Loss: 91.898
+64000/69092	Loss: 92.296
+67200/69092	Loss: 91.761
+Training time 0:09:02.647368
+Epoch: 111 Average loss: 92.32
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 385)
+0/69092	Loss: 91.325
+3200/69092	Loss: 90.225
+6400/69092	Loss: 91.722
+9600/69092	Loss: 92.634
+12800/69092	Loss: 92.710
+16000/69092	Loss: 92.705
+19200/69092	Loss: 92.802
+22400/69092	Loss: 92.700
+25600/69092	Loss: 93.177
+28800/69092	Loss: 93.241
+32000/69092	Loss: 91.321
+35200/69092	Loss: 90.026
+38400/69092	Loss: 93.153
+41600/69092	Loss: 93.158
+44800/69092	Loss: 91.482
+48000/69092	Loss: 93.233
+51200/69092	Loss: 91.125
+54400/69092	Loss: 93.355
+57600/69092	Loss: 92.627
+60800/69092	Loss: 90.121
+64000/69092	Loss: 93.660
+67200/69092	Loss: 92.791
+Training time 0:09:12.225430
+Epoch: 112 Average loss: 92.26
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 386)
+0/69092	Loss: 91.477
+3200/69092	Loss: 92.017
+6400/69092	Loss: 91.245
+9600/69092	Loss: 91.574
+12800/69092	Loss: 92.611
+16000/69092	Loss: 92.942
+19200/69092	Loss: 91.640
+22400/69092	Loss: 92.594
+25600/69092	Loss: 92.164
+28800/69092	Loss: 92.873
+32000/69092	Loss: 91.110
+35200/69092	Loss: 90.749
+38400/69092	Loss: 93.530
+41600/69092	Loss: 92.352
+44800/69092	Loss: 91.628
+48000/69092	Loss: 93.285
+51200/69092	Loss: 92.325
+54400/69092	Loss: 91.289
+57600/69092	Loss: 92.133
+60800/69092	Loss: 93.034
+64000/69092	Loss: 92.405
+67200/69092	Loss: 91.135
+Training time 0:09:00.760721
+Epoch: 113 Average loss: 92.20
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 387)
+0/69092	Loss: 106.513
+3200/69092	Loss: 92.986
+6400/69092	Loss: 91.135
+9600/69092	Loss: 91.670
+12800/69092	Loss: 91.506
+16000/69092	Loss: 91.461
+19200/69092	Loss: 92.161
+22400/69092	Loss: 92.173
+25600/69092	Loss: 93.073
+28800/69092	Loss: 91.202
+32000/69092	Loss: 94.143
+35200/69092	Loss: 93.282
+38400/69092	Loss: 91.763
+41600/69092	Loss: 91.175
+44800/69092	Loss: 93.207
+48000/69092	Loss: 92.446
+51200/69092	Loss: 93.591
+54400/69092	Loss: 92.475
+57600/69092	Loss: 92.347
+60800/69092	Loss: 93.135
+64000/69092	Loss: 92.417
+67200/69092	Loss: 91.755
+Training time 0:09:05.409547
+Epoch: 114 Average loss: 92.31
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 388)
+0/69092	Loss: 95.302
+3200/69092	Loss: 92.477
+6400/69092	Loss: 92.197
+9600/69092	Loss: 92.145
+12800/69092	Loss: 92.258
+16000/69092	Loss: 93.385
+19200/69092	Loss: 92.887
+22400/69092	Loss: 92.396
+25600/69092	Loss: 92.098
+28800/69092	Loss: 91.625
+32000/69092	Loss: 91.741
+35200/69092	Loss: 91.481
+38400/69092	Loss: 90.699
+41600/69092	Loss: 91.285
+44800/69092	Loss: 92.672
+48000/69092	Loss: 90.956
+51200/69092	Loss: 92.834
+54400/69092	Loss: 92.541
+57600/69092	Loss: 92.764
+60800/69092	Loss: 93.462
+64000/69092	Loss: 91.247
+67200/69092	Loss: 93.163
+Training time 0:09:20.420192
+Epoch: 115 Average loss: 92.24
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 389)
+0/69092	Loss: 88.873
+3200/69092	Loss: 93.439
+6400/69092	Loss: 90.976
+9600/69092	Loss: 91.998
+12800/69092	Loss: 92.274
+16000/69092	Loss: 92.200
+19200/69092	Loss: 91.082
+22400/69092	Loss: 93.744
+25600/69092	Loss: 93.241
+28800/69092	Loss: 90.897
+32000/69092	Loss: 92.269
+35200/69092	Loss: 93.289
+38400/69092	Loss: 91.202
+41600/69092	Loss: 92.805
+44800/69092	Loss: 92.574
+48000/69092	Loss: 92.290
+51200/69092	Loss: 92.296
+54400/69092	Loss: 92.143
+57600/69092	Loss: 91.274
+60800/69092	Loss: 91.962
+64000/69092	Loss: 92.522
+67200/69092	Loss: 92.236
+Training time 0:08:58.289886
+Epoch: 116 Average loss: 92.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 390)
+0/69092	Loss: 90.088
+3200/69092	Loss: 92.259
+6400/69092	Loss: 91.516
+9600/69092	Loss: 92.972
+12800/69092	Loss: 92.004
+16000/69092	Loss: 92.212
+19200/69092	Loss: 91.535
+22400/69092	Loss: 90.083
+25600/69092	Loss: 93.278
+28800/69092	Loss: 91.207
+32000/69092	Loss: 90.633
+35200/69092	Loss: 93.664
+38400/69092	Loss: 92.865
+41600/69092	Loss: 92.463
+44800/69092	Loss: 92.728
+48000/69092	Loss: 91.879
+51200/69092	Loss: 93.085
+54400/69092	Loss: 93.096
+57600/69092	Loss: 91.823
+60800/69092	Loss: 92.062
+64000/69092	Loss: 93.339
+67200/69092	Loss: 92.343
+Training time 0:09:04.326513
+Epoch: 117 Average loss: 92.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 391)
+0/69092	Loss: 94.318
+3200/69092	Loss: 91.598
+6400/69092	Loss: 93.536
+9600/69092	Loss: 91.712
+12800/69092	Loss: 93.184
+16000/69092	Loss: 92.643
+19200/69092	Loss: 92.392
+22400/69092	Loss: 91.402
+25600/69092	Loss: 92.222
+28800/69092	Loss: 92.407
+32000/69092	Loss: 92.681
+35200/69092	Loss: 91.864
+38400/69092	Loss: 92.632
+41600/69092	Loss: 92.171
+44800/69092	Loss: 92.369
+48000/69092	Loss: 91.703
+51200/69092	Loss: 93.311
+54400/69092	Loss: 93.602
+57600/69092	Loss: 91.778
+60800/69092	Loss: 91.332
+64000/69092	Loss: 92.286
+67200/69092	Loss: 91.772
+Training time 0:09:17.706127
+Epoch: 118 Average loss: 92.30
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 392)
+0/69092	Loss: 94.949
+3200/69092	Loss: 91.064
+6400/69092	Loss: 91.952
+9600/69092	Loss: 91.042
+12800/69092	Loss: 91.838
+16000/69092	Loss: 92.709
+19200/69092	Loss: 92.625
+22400/69092	Loss: 90.595
+25600/69092	Loss: 92.364
+28800/69092	Loss: 92.043
+32000/69092	Loss: 92.889
+35200/69092	Loss: 94.609
+38400/69092	Loss: 91.975
+41600/69092	Loss: 92.385
+44800/69092	Loss: 92.334
+48000/69092	Loss: 91.568
+51200/69092	Loss: 93.462
+54400/69092	Loss: 93.018
+57600/69092	Loss: 92.697
+60800/69092	Loss: 91.974
+64000/69092	Loss: 92.622
+67200/69092	Loss: 91.546
+Training time 0:09:00.811130
+Epoch: 119 Average loss: 92.28
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 393)
+0/69092	Loss: 96.708
+3200/69092	Loss: 91.631
+6400/69092	Loss: 91.755
+9600/69092	Loss: 92.328
+12800/69092	Loss: 91.551
+16000/69092	Loss: 91.468
+19200/69092	Loss: 93.741
+22400/69092	Loss: 92.504
+25600/69092	Loss: 91.219
+28800/69092	Loss: 92.333
+32000/69092	Loss: 92.606
+35200/69092	Loss: 93.082
+38400/69092	Loss: 92.986
+41600/69092	Loss: 92.457
+44800/69092	Loss: 92.689
+48000/69092	Loss: 93.570
+51200/69092	Loss: 91.720
+54400/69092	Loss: 92.240
+57600/69092	Loss: 92.101
+60800/69092	Loss: 92.084
+64000/69092	Loss: 91.728
+67200/69092	Loss: 91.929
+Training time 0:09:14.037553
+Epoch: 120 Average loss: 92.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 394)
+0/69092	Loss: 86.541
+3200/69092	Loss: 93.480
+6400/69092	Loss: 92.065
+9600/69092	Loss: 92.428
+12800/69092	Loss: 91.657
+16000/69092	Loss: 92.244
+19200/69092	Loss: 91.355
+22400/69092	Loss: 91.793
+25600/69092	Loss: 92.254
+28800/69092	Loss: 91.670
+32000/69092	Loss: 91.832
+35200/69092	Loss: 92.050
+38400/69092	Loss: 93.497
+41600/69092	Loss: 93.303
+44800/69092	Loss: 93.595
+48000/69092	Loss: 92.424
+51200/69092	Loss: 92.277
+54400/69092	Loss: 91.309
+57600/69092	Loss: 92.650
+60800/69092	Loss: 90.181
+64000/69092	Loss: 92.546
+67200/69092	Loss: 91.876
+Training time 0:09:05.779394
+Epoch: 121 Average loss: 92.23
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 395)
+0/69092	Loss: 88.550
+3200/69092	Loss: 93.514
+6400/69092	Loss: 91.738
+9600/69092	Loss: 91.828
+12800/69092	Loss: 91.703
+16000/69092	Loss: 92.316
+19200/69092	Loss: 91.899
+22400/69092	Loss: 91.801
+25600/69092	Loss: 91.043
+28800/69092	Loss: 92.077
+32000/69092	Loss: 92.416
+35200/69092	Loss: 92.462
+38400/69092	Loss: 92.953
+41600/69092	Loss: 90.666
+44800/69092	Loss: 92.955
+48000/69092	Loss: 91.962
+51200/69092	Loss: 92.126
+54400/69092	Loss: 92.340
+57600/69092	Loss: 94.594
+60800/69092	Loss: 92.728
+64000/69092	Loss: 91.579
+67200/69092	Loss: 92.637
+Training time 0:09:08.777185
+Epoch: 122 Average loss: 92.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 396)
+0/69092	Loss: 91.330
+3200/69092	Loss: 93.586
+6400/69092	Loss: 92.467
+9600/69092	Loss: 90.773
+12800/69092	Loss: 92.348
+16000/69092	Loss: 91.955
+19200/69092	Loss: 92.019
+22400/69092	Loss: 91.536
+25600/69092	Loss: 92.186
+28800/69092	Loss: 92.792
+32000/69092	Loss: 91.842
+35200/69092	Loss: 93.194
+38400/69092	Loss: 91.709
+41600/69092	Loss: 91.812
+44800/69092	Loss: 92.246
+48000/69092	Loss: 92.385
+51200/69092	Loss: 91.701
+54400/69092	Loss: 92.834
+57600/69092	Loss: 90.888
+60800/69092	Loss: 91.332
+64000/69092	Loss: 92.862
+67200/69092	Loss: 94.451
+Training time 0:09:25.072186
+Epoch: 123 Average loss: 92.26
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 397)
+0/69092	Loss: 83.727
+3200/69092	Loss: 92.323
+6400/69092	Loss: 91.273
+9600/69092	Loss: 92.397
+12800/69092	Loss: 91.398
+16000/69092	Loss: 92.398
+19200/69092	Loss: 91.375
+22400/69092	Loss: 93.676
+25600/69092	Loss: 91.985
+28800/69092	Loss: 91.409
+32000/69092	Loss: 93.498
+35200/69092	Loss: 92.955
+38400/69092	Loss: 91.515
+41600/69092	Loss: 91.239
+44800/69092	Loss: 92.136
+48000/69092	Loss: 92.433
+51200/69092	Loss: 92.161
+54400/69092	Loss: 92.319
+57600/69092	Loss: 92.389
+60800/69092	Loss: 92.386
+64000/69092	Loss: 91.474
+67200/69092	Loss: 92.845
+Training time 0:09:04.158750
+Epoch: 124 Average loss: 92.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 398)
+0/69092	Loss: 100.008
+3200/69092	Loss: 92.646
+6400/69092	Loss: 93.066
+9600/69092	Loss: 91.612
+12800/69092	Loss: 92.198
+16000/69092	Loss: 92.803
+19200/69092	Loss: 91.680
+22400/69092	Loss: 92.580
+25600/69092	Loss: 92.333
+28800/69092	Loss: 92.072
+32000/69092	Loss: 91.722
+35200/69092	Loss: 92.165
+38400/69092	Loss: 92.906
+41600/69092	Loss: 92.016
+44800/69092	Loss: 92.050
+48000/69092	Loss: 92.403
+51200/69092	Loss: 92.147
+54400/69092	Loss: 93.074
+57600/69092	Loss: 91.078
+60800/69092	Loss: 91.143
+64000/69092	Loss: 91.866
+67200/69092	Loss: 90.970
+Training time 0:09:00.199569
+Epoch: 125 Average loss: 92.15
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 399)
+0/69092	Loss: 84.643
+3200/69092	Loss: 91.363
+6400/69092	Loss: 91.885
+9600/69092	Loss: 91.944
+12800/69092	Loss: 92.691
+16000/69092	Loss: 92.874
+19200/69092	Loss: 93.412
+22400/69092	Loss: 92.265
+25600/69092	Loss: 90.137
+28800/69092	Loss: 92.528
+32000/69092	Loss: 91.899
+35200/69092	Loss: 92.221
+38400/69092	Loss: 92.439
+41600/69092	Loss: 92.578
+44800/69092	Loss: 91.654
+48000/69092	Loss: 91.931
+51200/69092	Loss: 92.146
+54400/69092	Loss: 92.570
+57600/69092	Loss: 91.268
+60800/69092	Loss: 93.372
+64000/69092	Loss: 91.359
+67200/69092	Loss: 93.631
+Training time 0:09:07.977562
+Epoch: 126 Average loss: 92.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 400)
+0/69092	Loss: 83.043
+3200/69092	Loss: 91.639
+6400/69092	Loss: 91.768
+9600/69092	Loss: 93.207
+12800/69092	Loss: 93.872
+16000/69092	Loss: 91.180
+19200/69092	Loss: 91.889
+22400/69092	Loss: 91.315
+25600/69092	Loss: 94.384
+28800/69092	Loss: 91.115
+32000/69092	Loss: 91.295
+35200/69092	Loss: 91.049
+38400/69092	Loss: 92.832
+41600/69092	Loss: 93.149
+44800/69092	Loss: 91.419
+48000/69092	Loss: 92.136
+51200/69092	Loss: 93.314
+54400/69092	Loss: 92.709
+57600/69092	Loss: 92.682
+60800/69092	Loss: 91.880
+64000/69092	Loss: 91.384
+67200/69092	Loss: 91.523
+Training time 0:09:26.145670
+Epoch: 127 Average loss: 92.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 401)
+0/69092	Loss: 89.109
+3200/69092	Loss: 90.963
+6400/69092	Loss: 92.288
+9600/69092	Loss: 91.891
+12800/69092	Loss: 91.798
+16000/69092	Loss: 93.924
+19200/69092	Loss: 92.904
+22400/69092	Loss: 92.207
+25600/69092	Loss: 90.720
+28800/69092	Loss: 91.450
+32000/69092	Loss: 91.571
+35200/69092	Loss: 91.587
+38400/69092	Loss: 92.477
+41600/69092	Loss: 92.679
+44800/69092	Loss: 92.520
+48000/69092	Loss: 92.721
+51200/69092	Loss: 93.114
+54400/69092	Loss: 91.964
+57600/69092	Loss: 92.969
+60800/69092	Loss: 91.913
+64000/69092	Loss: 92.004
+67200/69092	Loss: 90.623
+Training time 0:09:14.492296
+Epoch: 128 Average loss: 92.13
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 402)
+0/69092	Loss: 87.012
+3200/69092	Loss: 91.671
+6400/69092	Loss: 91.960
+9600/69092	Loss: 92.405
+12800/69092	Loss: 93.042
+16000/69092	Loss: 91.771
+19200/69092	Loss: 91.449
+22400/69092	Loss: 92.717
+25600/69092	Loss: 93.286
+28800/69092	Loss: 93.324
+32000/69092	Loss: 92.235
+35200/69092	Loss: 92.970
+38400/69092	Loss: 91.767
+41600/69092	Loss: 92.104
+44800/69092	Loss: 91.945
+48000/69092	Loss: 91.703
+51200/69092	Loss: 91.693
+54400/69092	Loss: 92.659
+57600/69092	Loss: 92.279
+60800/69092	Loss: 92.133
+64000/69092	Loss: 92.678
+67200/69092	Loss: 92.053
+Training time 0:09:07.251519
+Epoch: 129 Average loss: 92.26
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 403)
+0/69092	Loss: 87.376
+3200/69092	Loss: 91.925
+6400/69092	Loss: 92.901
+9600/69092	Loss: 91.405
+12800/69092	Loss: 91.570
+16000/69092	Loss: 93.809
+19200/69092	Loss: 92.422
+22400/69092	Loss: 92.515
+25600/69092	Loss: 92.818
+28800/69092	Loss: 91.918
+32000/69092	Loss: 91.335
+35200/69092	Loss: 92.251
+38400/69092	Loss: 91.761
+41600/69092	Loss: 92.677
+44800/69092	Loss: 92.043
+48000/69092	Loss: 92.765
+51200/69092	Loss: 91.619
+54400/69092	Loss: 90.414
+57600/69092	Loss: 92.127
+60800/69092	Loss: 91.804
+64000/69092	Loss: 92.577
+67200/69092	Loss: 91.053
+Training time 0:09:19.374484
+Epoch: 130 Average loss: 92.08
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 404)
+0/69092	Loss: 82.119
+3200/69092	Loss: 91.396
+6400/69092	Loss: 92.834
+9600/69092	Loss: 92.783
+12800/69092	Loss: 92.664
+16000/69092	Loss: 92.209
+19200/69092	Loss: 92.523
+22400/69092	Loss: 91.125
+25600/69092	Loss: 92.665
+28800/69092	Loss: 91.461
+32000/69092	Loss: 91.956
+35200/69092	Loss: 93.796
+38400/69092	Loss: 91.151
+41600/69092	Loss: 91.364
+44800/69092	Loss: 92.885
+48000/69092	Loss: 92.278
+51200/69092	Loss: 92.537
+54400/69092	Loss: 92.797
+57600/69092	Loss: 92.300
+60800/69092	Loss: 91.094
+64000/69092	Loss: 93.296
+67200/69092	Loss: 92.364
+Training time 0:09:21.617601
+Epoch: 131 Average loss: 92.24
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 405)
+0/69092	Loss: 90.586
+3200/69092	Loss: 91.807
+6400/69092	Loss: 92.535
+9600/69092	Loss: 94.028
+12800/69092	Loss: 90.884
+16000/69092	Loss: 93.966
+19200/69092	Loss: 91.147
+22400/69092	Loss: 91.639
+25600/69092	Loss: 92.338
+28800/69092	Loss: 92.027
+32000/69092	Loss: 92.208
+35200/69092	Loss: 92.011
+38400/69092	Loss: 91.749
+41600/69092	Loss: 91.772
+44800/69092	Loss: 92.543
+48000/69092	Loss: 93.104
+51200/69092	Loss: 92.586
+54400/69092	Loss: 91.996
+57600/69092	Loss: 90.559
+60800/69092	Loss: 91.474
+64000/69092	Loss: 91.504
+67200/69092	Loss: 92.398
+Training time 0:09:19.551918
+Epoch: 132 Average loss: 92.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 406)
+0/69092	Loss: 95.776
+3200/69092	Loss: 91.024
+6400/69092	Loss: 90.952
+9600/69092	Loss: 91.850
+12800/69092	Loss: 91.891
+16000/69092	Loss: 92.509
+19200/69092	Loss: 92.154
+22400/69092	Loss: 93.121
+25600/69092	Loss: 92.245
+28800/69092	Loss: 91.237
+32000/69092	Loss: 92.365
+35200/69092	Loss: 92.513
+38400/69092	Loss: 90.698
+41600/69092	Loss: 92.358
+44800/69092	Loss: 94.475
+48000/69092	Loss: 91.907
+51200/69092	Loss: 91.035
+54400/69092	Loss: 92.961
+57600/69092	Loss: 93.340
+60800/69092	Loss: 92.449
+64000/69092	Loss: 90.522
+67200/69092	Loss: 92.188
+Training time 0:08:56.215793
+Epoch: 133 Average loss: 92.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 407)
+0/69092	Loss: 96.443
+3200/69092	Loss: 92.253
+6400/69092	Loss: 93.106
+9600/69092	Loss: 90.904
+12800/69092	Loss: 91.891
+16000/69092	Loss: 92.583
+19200/69092	Loss: 91.328
+22400/69092	Loss: 92.431
+25600/69092	Loss: 92.384
+28800/69092	Loss: 90.784
+32000/69092	Loss: 91.219
+35200/69092	Loss: 91.672
+38400/69092	Loss: 91.621
+41600/69092	Loss: 92.225
+44800/69092	Loss: 91.398
+48000/69092	Loss: 91.670
+51200/69092	Loss: 91.664
+54400/69092	Loss: 91.837
+57600/69092	Loss: 93.080
+60800/69092	Loss: 92.781
+64000/69092	Loss: 92.439
+67200/69092	Loss: 92.898
+Training time 0:09:06.798722
+Epoch: 134 Average loss: 92.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 408)
+0/69092	Loss: 93.209
+3200/69092	Loss: 91.517
+6400/69092	Loss: 91.649
+9600/69092	Loss: 91.688
+12800/69092	Loss: 90.766
+16000/69092	Loss: 91.784
+19200/69092	Loss: 92.636
+22400/69092	Loss: 92.001
+25600/69092	Loss: 91.213
+28800/69092	Loss: 92.284
+32000/69092	Loss: 92.465
+35200/69092	Loss: 92.156
+38400/69092	Loss: 92.335
+41600/69092	Loss: 91.043
+44800/69092	Loss: 91.395
+48000/69092	Loss: 92.365
+51200/69092	Loss: 93.463
+54400/69092	Loss: 92.153
+57600/69092	Loss: 91.810
+60800/69092	Loss: 90.732
+64000/69092	Loss: 92.684
+67200/69092	Loss: 92.826
+Training time 0:08:52.208051
+Epoch: 135 Average loss: 91.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 409)
+0/69092	Loss: 84.643
+3200/69092	Loss: 91.970
+6400/69092	Loss: 91.153
+9600/69092	Loss: 91.851
+12800/69092	Loss: 90.788
+16000/69092	Loss: 92.018
+19200/69092	Loss: 92.835
+22400/69092	Loss: 91.239
+25600/69092	Loss: 91.001
+28800/69092	Loss: 91.265
+32000/69092	Loss: 91.277
+35200/69092	Loss: 93.150
+38400/69092	Loss: 92.244
+41600/69092	Loss: 92.757
+44800/69092	Loss: 92.247
+48000/69092	Loss: 91.675
+51200/69092	Loss: 91.988
+54400/69092	Loss: 91.622
+57600/69092	Loss: 92.529
+60800/69092	Loss: 92.589
+64000/69092	Loss: 92.547
+67200/69092	Loss: 92.397
+Training time 0:09:20.491583
+Epoch: 136 Average loss: 91.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 410)
+0/69092	Loss: 90.657
+3200/69092	Loss: 93.395
+6400/69092	Loss: 91.712
+9600/69092	Loss: 92.762
+12800/69092	Loss: 92.146
+16000/69092	Loss: 91.592
+19200/69092	Loss: 91.913
+22400/69092	Loss: 91.197
+25600/69092	Loss: 92.207
+28800/69092	Loss: 92.175
+32000/69092	Loss: 90.639
+35200/69092	Loss: 93.225
+38400/69092	Loss: 92.183
+41600/69092	Loss: 92.805
+44800/69092	Loss: 93.115
+48000/69092	Loss: 91.750
+51200/69092	Loss: 92.780
+54400/69092	Loss: 91.844
+57600/69092	Loss: 92.839
+60800/69092	Loss: 92.164
+64000/69092	Loss: 91.050
+67200/69092	Loss: 91.254
+Training time 0:09:32.273765
+Epoch: 137 Average loss: 92.15
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 411)
+0/69092	Loss: 96.427
+3200/69092	Loss: 91.007
+6400/69092	Loss: 91.983
+9600/69092	Loss: 91.835
+12800/69092	Loss: 91.049
+16000/69092	Loss: 91.340
+19200/69092	Loss: 92.444
+22400/69092	Loss: 92.486
+25600/69092	Loss: 93.009
+28800/69092	Loss: 92.403
+32000/69092	Loss: 92.993
+35200/69092	Loss: 91.424
+38400/69092	Loss: 93.535
+41600/69092	Loss: 91.450
+44800/69092	Loss: 92.310
+48000/69092	Loss: 91.469
+51200/69092	Loss: 91.299
+54400/69092	Loss: 92.681
+57600/69092	Loss: 92.148
+60800/69092	Loss: 91.447
+64000/69092	Loss: 91.688
+67200/69092	Loss: 91.070
+Training time 0:09:24.914193
+Epoch: 138 Average loss: 91.99
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 412)
+0/69092	Loss: 93.081
+3200/69092	Loss: 91.895
+6400/69092	Loss: 91.587
+9600/69092	Loss: 93.229
+12800/69092	Loss: 91.042
+16000/69092	Loss: 92.410
+19200/69092	Loss: 92.185
+22400/69092	Loss: 92.732
+25600/69092	Loss: 92.631
+28800/69092	Loss: 92.081
+32000/69092	Loss: 90.789
+35200/69092	Loss: 92.325
+38400/69092	Loss: 92.411
+41600/69092	Loss: 92.100
+44800/69092	Loss: 93.229
+48000/69092	Loss: 92.378
+51200/69092	Loss: 91.726
+54400/69092	Loss: 90.949
+57600/69092	Loss: 92.487
+60800/69092	Loss: 91.802
+64000/69092	Loss: 92.132
+67200/69092	Loss: 90.835
+Training time 0:09:13.285170
+Epoch: 139 Average loss: 92.03
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 413)
+0/69092	Loss: 95.461
+3200/69092	Loss: 92.109
+6400/69092	Loss: 91.748
+9600/69092	Loss: 92.418
+12800/69092	Loss: 92.609
+16000/69092	Loss: 92.160
+19200/69092	Loss: 92.325
+22400/69092	Loss: 91.534
+25600/69092	Loss: 92.438
+28800/69092	Loss: 91.502
+32000/69092	Loss: 92.192
+35200/69092	Loss: 90.582
+38400/69092	Loss: 91.600
+41600/69092	Loss: 91.933
+44800/69092	Loss: 90.583
+48000/69092	Loss: 91.809
+51200/69092	Loss: 91.625
+54400/69092	Loss: 91.565
+57600/69092	Loss: 92.129
+60800/69092	Loss: 92.085
+64000/69092	Loss: 92.768
+67200/69092	Loss: 92.154
+Training time 0:09:29.904519
+Epoch: 140 Average loss: 91.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 414)
+0/69092	Loss: 95.504
+3200/69092	Loss: 92.589
+6400/69092	Loss: 91.692
+9600/69092	Loss: 91.525
+12800/69092	Loss: 92.060
+16000/69092	Loss: 91.612
+19200/69092	Loss: 93.510
+22400/69092	Loss: 92.056
+25600/69092	Loss: 91.996
+28800/69092	Loss: 92.132
+32000/69092	Loss: 91.751
+35200/69092	Loss: 91.047
+38400/69092	Loss: 91.366
+41600/69092	Loss: 92.720
+44800/69092	Loss: 92.109
+48000/69092	Loss: 93.151
+51200/69092	Loss: 92.653
+54400/69092	Loss: 91.985
+57600/69092	Loss: 92.938
+60800/69092	Loss: 92.094
+64000/69092	Loss: 90.968
+67200/69092	Loss: 91.573
+Training time 0:09:09.413433
+Epoch: 141 Average loss: 92.04
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 415)
+0/69092	Loss: 81.082
+3200/69092	Loss: 92.105
+6400/69092	Loss: 93.118
+9600/69092	Loss: 91.644
+12800/69092	Loss: 91.527
+16000/69092	Loss: 90.760
+19200/69092	Loss: 92.783
+22400/69092	Loss: 90.977
+25600/69092	Loss: 90.821
+28800/69092	Loss: 92.008
+32000/69092	Loss: 91.398
+35200/69092	Loss: 92.125
+38400/69092	Loss: 92.672
+41600/69092	Loss: 91.161
+44800/69092	Loss: 91.718
+48000/69092	Loss: 91.701
+51200/69092	Loss: 91.764
+54400/69092	Loss: 91.028
+57600/69092	Loss: 92.776
+60800/69092	Loss: 94.048
+64000/69092	Loss: 91.044
+67200/69092	Loss: 92.388
+Training time 0:08:58.090750
+Epoch: 142 Average loss: 91.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 416)
+0/69092	Loss: 89.243
+3200/69092	Loss: 91.684
+6400/69092	Loss: 93.159
+9600/69092	Loss: 91.663
+12800/69092	Loss: 91.474
+16000/69092	Loss: 91.078
+19200/69092	Loss: 92.375
+22400/69092	Loss: 91.978
+25600/69092	Loss: 92.557
+28800/69092	Loss: 92.784
+32000/69092	Loss: 92.195
+35200/69092	Loss: 92.066
+38400/69092	Loss: 92.731
+41600/69092	Loss: 91.959
+44800/69092	Loss: 92.472
+48000/69092	Loss: 91.268
+51200/69092	Loss: 92.488
+54400/69092	Loss: 92.305
+57600/69092	Loss: 91.417
+60800/69092	Loss: 92.057
+64000/69092	Loss: 90.280
+67200/69092	Loss: 90.723
+Training time 0:09:03.935169
+Epoch: 143 Average loss: 91.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 417)
+0/69092	Loss: 88.340
+3200/69092	Loss: 91.891
+6400/69092	Loss: 91.574
+9600/69092	Loss: 92.456
+12800/69092	Loss: 90.660
+16000/69092	Loss: 92.496
+19200/69092	Loss: 91.106
+22400/69092	Loss: 91.626
+25600/69092	Loss: 91.525
+28800/69092	Loss: 92.384
+32000/69092	Loss: 91.438
+35200/69092	Loss: 92.786
+38400/69092	Loss: 92.752
+41600/69092	Loss: 91.987
+44800/69092	Loss: 92.181
+48000/69092	Loss: 90.806
+51200/69092	Loss: 91.076
+54400/69092	Loss: 92.485
+57600/69092	Loss: 91.163
+60800/69092	Loss: 93.816
+64000/69092	Loss: 92.153
+67200/69092	Loss: 91.900
+Training time 0:09:05.801074
+Epoch: 144 Average loss: 91.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 418)
+0/69092	Loss: 92.790
+3200/69092	Loss: 92.358
+6400/69092	Loss: 92.373
+9600/69092	Loss: 91.877
+12800/69092	Loss: 90.258
+16000/69092	Loss: 92.545
+19200/69092	Loss: 92.394
+22400/69092	Loss: 93.182
+25600/69092	Loss: 91.071
+28800/69092	Loss: 89.542
+32000/69092	Loss: 93.394
+35200/69092	Loss: 91.280
+38400/69092	Loss: 92.491
+41600/69092	Loss: 92.250
+44800/69092	Loss: 92.035
+48000/69092	Loss: 90.767
+51200/69092	Loss: 92.683
+54400/69092	Loss: 93.363
+57600/69092	Loss: 92.379
+60800/69092	Loss: 91.534
+64000/69092	Loss: 91.797
+67200/69092	Loss: 91.573
+Training time 0:09:37.577532
+Epoch: 145 Average loss: 91.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 419)
+0/69092	Loss: 97.883
+3200/69092	Loss: 91.900
+6400/69092	Loss: 91.811
+9600/69092	Loss: 90.275
+12800/69092	Loss: 91.939
+16000/69092	Loss: 91.186
+19200/69092	Loss: 93.104
+22400/69092	Loss: 91.598
+25600/69092	Loss: 90.858
+28800/69092	Loss: 93.596
+32000/69092	Loss: 92.274
+35200/69092	Loss: 91.530
+38400/69092	Loss: 92.206
+41600/69092	Loss: 92.682
+44800/69092	Loss: 91.545
+48000/69092	Loss: 91.640
+51200/69092	Loss: 92.157
+54400/69092	Loss: 92.538
+57600/69092	Loss: 92.324
+60800/69092	Loss: 90.733
+64000/69092	Loss: 91.797
+67200/69092	Loss: 93.266
+Training time 0:09:18.120688
+Epoch: 146 Average loss: 91.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 420)
+0/69092	Loss: 91.639
+3200/69092	Loss: 93.180
+6400/69092	Loss: 92.272
+9600/69092	Loss: 92.385
+12800/69092	Loss: 91.132
+16000/69092	Loss: 92.219
+19200/69092	Loss: 93.381
+22400/69092	Loss: 91.944
+25600/69092	Loss: 91.329
+28800/69092	Loss: 91.822
+32000/69092	Loss: 91.813
+35200/69092	Loss: 91.763
+38400/69092	Loss: 92.133
+41600/69092	Loss: 91.600
+44800/69092	Loss: 92.026
+48000/69092	Loss: 92.787
+51200/69092	Loss: 93.262
+54400/69092	Loss: 92.367
+57600/69092	Loss: 90.323
+60800/69092	Loss: 89.872
+64000/69092	Loss: 91.262
+67200/69092	Loss: 90.591
+Training time 0:09:07.749334
+Epoch: 147 Average loss: 91.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 421)
+0/69092	Loss: 88.543
+3200/69092	Loss: 93.043
+6400/69092	Loss: 91.033
+9600/69092	Loss: 92.557
+12800/69092	Loss: 91.374
+16000/69092	Loss: 91.621
+19200/69092	Loss: 91.353
+22400/69092	Loss: 91.149
+25600/69092	Loss: 92.072
+28800/69092	Loss: 92.517
+32000/69092	Loss: 92.389
+35200/69092	Loss: 92.783
+38400/69092	Loss: 92.784
+41600/69092	Loss: 93.411
+44800/69092	Loss: 91.714
+48000/69092	Loss: 91.790
+51200/69092	Loss: 92.152
+54400/69092	Loss: 91.367
+57600/69092	Loss: 93.516
+60800/69092	Loss: 90.557
+64000/69092	Loss: 90.918
+67200/69092	Loss: 92.455
+Training time 0:09:01.288443
+Epoch: 148 Average loss: 92.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 422)
+0/69092	Loss: 89.943
+3200/69092	Loss: 93.111
+6400/69092	Loss: 92.314
+9600/69092	Loss: 92.072
+12800/69092	Loss: 90.164
+16000/69092	Loss: 91.631
+19200/69092	Loss: 92.145
+22400/69092	Loss: 90.386
+25600/69092	Loss: 91.931
+28800/69092	Loss: 92.050
+32000/69092	Loss: 92.364
+35200/69092	Loss: 92.730
+38400/69092	Loss: 91.133
+41600/69092	Loss: 92.610
+44800/69092	Loss: 91.955
+48000/69092	Loss: 91.750
+51200/69092	Loss: 91.959
+54400/69092	Loss: 92.519
+57600/69092	Loss: 92.149
+60800/69092	Loss: 91.678
+64000/69092	Loss: 91.990
+67200/69092	Loss: 90.230
+Training time 0:09:20.311216
+Epoch: 149 Average loss: 91.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 423)
+0/69092	Loss: 92.492
+3200/69092	Loss: 91.581
+6400/69092	Loss: 91.678
+9600/69092	Loss: 91.262
+12800/69092	Loss: 91.903
+16000/69092	Loss: 91.913
+19200/69092	Loss: 91.392
+22400/69092	Loss: 91.102
+25600/69092	Loss: 91.342
+28800/69092	Loss: 92.159
+32000/69092	Loss: 92.236
+35200/69092	Loss: 91.951
+38400/69092	Loss: 92.421
+41600/69092	Loss: 92.697
+44800/69092	Loss: 91.083
+48000/69092	Loss: 93.362
+51200/69092	Loss: 93.409
+54400/69092	Loss: 92.621
+57600/69092	Loss: 89.747
+60800/69092	Loss: 92.156
+64000/69092	Loss: 93.163
+67200/69092	Loss: 91.170
+Training time 0:09:13.848839
+Epoch: 150 Average loss: 91.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 424)
+0/69092	Loss: 94.543
+3200/69092	Loss: 92.248
+6400/69092	Loss: 92.062
+9600/69092	Loss: 91.151
+12800/69092	Loss: 90.570
+16000/69092	Loss: 92.841
+19200/69092	Loss: 90.666
+22400/69092	Loss: 91.464
+25600/69092	Loss: 92.524
+28800/69092	Loss: 92.911
+32000/69092	Loss: 91.105
+35200/69092	Loss: 89.963
+38400/69092	Loss: 91.110
+41600/69092	Loss: 91.666
+44800/69092	Loss: 92.966
+48000/69092	Loss: 91.451
+51200/69092	Loss: 91.222
+54400/69092	Loss: 93.134
+57600/69092	Loss: 90.936
+60800/69092	Loss: 92.781
+64000/69092	Loss: 93.864
+67200/69092	Loss: 92.620
+Training time 0:09:15.479361
+Epoch: 151 Average loss: 91.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 425)
+0/69092	Loss: 96.764
+3200/69092	Loss: 92.419
+6400/69092	Loss: 93.363
+9600/69092	Loss: 91.241
+12800/69092	Loss: 92.509
+16000/69092	Loss: 91.952
+19200/69092	Loss: 91.725
+22400/69092	Loss: 92.405
+25600/69092	Loss: 92.974
+28800/69092	Loss: 91.684
+32000/69092	Loss: 92.642
+35200/69092	Loss: 92.634
+38400/69092	Loss: 92.644
+41600/69092	Loss: 90.291
+44800/69092	Loss: 91.599
+48000/69092	Loss: 92.321
+51200/69092	Loss: 91.403
+54400/69092	Loss: 91.857
+57600/69092	Loss: 91.674
+60800/69092	Loss: 91.592
+64000/69092	Loss: 90.822
+67200/69092	Loss: 91.827
+Training time 0:09:15.708044
+Epoch: 152 Average loss: 91.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 426)
+0/69092	Loss: 94.601
+3200/69092	Loss: 91.506
+6400/69092	Loss: 90.643
+9600/69092	Loss: 91.191
+12800/69092	Loss: 92.072
+16000/69092	Loss: 92.680
+19200/69092	Loss: 92.120
+22400/69092	Loss: 92.606
+25600/69092	Loss: 92.032
+28800/69092	Loss: 92.899
+32000/69092	Loss: 91.660
+35200/69092	Loss: 91.510
+38400/69092	Loss: 91.417
+41600/69092	Loss: 91.145
+44800/69092	Loss: 90.927
+48000/69092	Loss: 92.462
+51200/69092	Loss: 92.723
+54400/69092	Loss: 91.720
+57600/69092	Loss: 93.010
+60800/69092	Loss: 89.922
+64000/69092	Loss: 91.724
+67200/69092	Loss: 94.043
+Training time 0:09:18.938997
+Epoch: 153 Average loss: 91.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 427)
+0/69092	Loss: 89.691
+3200/69092	Loss: 92.673
+6400/69092	Loss: 92.301
+9600/69092	Loss: 92.408
+12800/69092	Loss: 92.118
+16000/69092	Loss: 92.145
+19200/69092	Loss: 90.207
+22400/69092	Loss: 92.873
+25600/69092	Loss: 92.958
+28800/69092	Loss: 91.627
+32000/69092	Loss: 92.223
+35200/69092	Loss: 91.044
+38400/69092	Loss: 92.608
+41600/69092	Loss: 91.498
+44800/69092	Loss: 91.784
+48000/69092	Loss: 91.375
+51200/69092	Loss: 93.525
+54400/69092	Loss: 91.571
+57600/69092	Loss: 91.459
+60800/69092	Loss: 91.974
+64000/69092	Loss: 90.593
+67200/69092	Loss: 92.447
+Training time 0:09:29.670206
+Epoch: 154 Average loss: 91.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 428)
+0/69092	Loss: 89.314
+3200/69092	Loss: 93.143
+6400/69092	Loss: 90.607
+9600/69092	Loss: 92.733
+12800/69092	Loss: 91.938
+16000/69092	Loss: 91.166
+19200/69092	Loss: 92.572
+22400/69092	Loss: 90.644
+25600/69092	Loss: 92.476
+28800/69092	Loss: 90.634
+32000/69092	Loss: 92.255
+35200/69092	Loss: 92.141
+38400/69092	Loss: 90.818
+41600/69092	Loss: 91.034
+44800/69092	Loss: 92.699
+48000/69092	Loss: 91.935
+51200/69092	Loss: 91.307
+54400/69092	Loss: 92.660
+57600/69092	Loss: 92.205
+60800/69092	Loss: 93.390
+64000/69092	Loss: 91.593
+67200/69092	Loss: 92.591
+Training time 0:09:05.594088
+Epoch: 155 Average loss: 91.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 429)
+0/69092	Loss: 91.487
+3200/69092	Loss: 92.353
+6400/69092	Loss: 91.678
+9600/69092	Loss: 90.897
+12800/69092	Loss: 90.662
+16000/69092	Loss: 91.044
+19200/69092	Loss: 89.622
+22400/69092	Loss: 91.656
+25600/69092	Loss: 92.274
+28800/69092	Loss: 91.995
+32000/69092	Loss: 93.435
+35200/69092	Loss: 93.628
+38400/69092	Loss: 93.267
+41600/69092	Loss: 92.528
+44800/69092	Loss: 92.000
+48000/69092	Loss: 92.430
+51200/69092	Loss: 91.319
+54400/69092	Loss: 91.601
+57600/69092	Loss: 91.823
+60800/69092	Loss: 91.966
+64000/69092	Loss: 91.414
+67200/69092	Loss: 91.830
+Training time 0:08:58.181731
+Epoch: 156 Average loss: 91.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 430)
+0/69092	Loss: 96.361
+3200/69092	Loss: 91.647
+6400/69092	Loss: 91.788
+9600/69092	Loss: 92.381
+12800/69092	Loss: 91.669
+16000/69092	Loss: 91.384
+19200/69092	Loss: 91.880
+22400/69092	Loss: 92.831
+25600/69092	Loss: 92.682
+28800/69092	Loss: 91.870
+32000/69092	Loss: 91.848
+35200/69092	Loss: 91.838
+38400/69092	Loss: 91.670
+41600/69092	Loss: 90.990
+44800/69092	Loss: 92.064
+48000/69092	Loss: 91.539
+51200/69092	Loss: 92.761
+54400/69092	Loss: 91.867
+57600/69092	Loss: 92.019
+60800/69092	Loss: 91.618
+64000/69092	Loss: 91.437
+67200/69092	Loss: 91.545
+Training time 0:09:08.343688
+Epoch: 157 Average loss: 91.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 431)
+0/69092	Loss: 99.896
+3200/69092	Loss: 92.485
+6400/69092	Loss: 92.375
+9600/69092	Loss: 91.831
+12800/69092	Loss: 92.214
+16000/69092	Loss: 92.564
+19200/69092	Loss: 91.289
+22400/69092	Loss: 92.427
+25600/69092	Loss: 90.088
+28800/69092	Loss: 92.852
+32000/69092	Loss: 91.822
+35200/69092	Loss: 91.957
+38400/69092	Loss: 93.161
+41600/69092	Loss: 92.558
+44800/69092	Loss: 91.904
+48000/69092	Loss: 92.761
+51200/69092	Loss: 91.247
+54400/69092	Loss: 91.004
+57600/69092	Loss: 92.523
+60800/69092	Loss: 92.166
+64000/69092	Loss: 90.841
+67200/69092	Loss: 91.122
+Training time 0:09:26.582489
+Epoch: 158 Average loss: 91.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 432)
+0/69092	Loss: 92.624
+3200/69092	Loss: 92.245
+6400/69092	Loss: 92.827
+9600/69092	Loss: 93.325
+12800/69092	Loss: 91.907
+16000/69092	Loss: 91.640
+19200/69092	Loss: 91.528
+22400/69092	Loss: 91.894
+25600/69092	Loss: 92.436
+28800/69092	Loss: 91.410
+32000/69092	Loss: 91.042
+35200/69092	Loss: 91.476
+38400/69092	Loss: 90.761
+41600/69092	Loss: 91.502
+44800/69092	Loss: 92.094
+48000/69092	Loss: 92.243
+51200/69092	Loss: 90.975
+54400/69092	Loss: 91.310
+57600/69092	Loss: 91.008
+60800/69092	Loss: 91.027
+64000/69092	Loss: 92.788
+67200/69092	Loss: 92.353
+Training time 0:08:49.510622
+Epoch: 159 Average loss: 91.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 433)
+0/69092	Loss: 89.864
+3200/69092	Loss: 91.134
+6400/69092	Loss: 93.499
+9600/69092	Loss: 92.372
+12800/69092	Loss: 91.157
+16000/69092	Loss: 92.344
+19200/69092	Loss: 90.973
+22400/69092	Loss: 92.031
+25600/69092	Loss: 91.280
+28800/69092	Loss: 90.753
+32000/69092	Loss: 90.838
+35200/69092	Loss: 90.666
+38400/69092	Loss: 91.878
+41600/69092	Loss: 92.154
+44800/69092	Loss: 93.469
+48000/69092	Loss: 92.247
+51200/69092	Loss: 92.311
+54400/69092	Loss: 92.195
+57600/69092	Loss: 91.593
+60800/69092	Loss: 90.559
+64000/69092	Loss: 90.635
+67200/69092	Loss: 93.316
+Training time 0:08:59.944768
+Epoch: 160 Average loss: 91.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 434)
+0/69092	Loss: 90.190
+3200/69092	Loss: 91.361
+6400/69092	Loss: 92.635
+9600/69092	Loss: 92.279
+12800/69092	Loss: 92.198
+16000/69092	Loss: 91.146
+19200/69092	Loss: 93.696
+22400/69092	Loss: 91.185
+25600/69092	Loss: 90.985
+28800/69092	Loss: 91.240
+32000/69092	Loss: 92.493
+35200/69092	Loss: 92.108
+38400/69092	Loss: 92.665
+41600/69092	Loss: 92.089
+44800/69092	Loss: 91.375
+48000/69092	Loss: 91.549
+51200/69092	Loss: 90.948
+54400/69092	Loss: 90.172
+57600/69092	Loss: 92.630
+60800/69092	Loss: 93.305
+64000/69092	Loss: 91.477
+67200/69092	Loss: 92.110
+Training time 0:09:13.735779
+Epoch: 161 Average loss: 91.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 435)
+0/69092	Loss: 86.516
+3200/69092	Loss: 92.952
+6400/69092	Loss: 91.350
+9600/69092	Loss: 91.201
+12800/69092	Loss: 91.818
+16000/69092	Loss: 92.395
+19200/69092	Loss: 91.143
+22400/69092	Loss: 91.159
+25600/69092	Loss: 91.175
+28800/69092	Loss: 91.230
+32000/69092	Loss: 91.962
+35200/69092	Loss: 92.215
+38400/69092	Loss: 93.155
+41600/69092	Loss: 92.329
+44800/69092	Loss: 90.965
+48000/69092	Loss: 92.067
+51200/69092	Loss: 92.496
+54400/69092	Loss: 92.338
+57600/69092	Loss: 91.556
+60800/69092	Loss: 90.312
+64000/69092	Loss: 91.713
+67200/69092	Loss: 92.577
+Training time 0:09:04.908932
+Epoch: 162 Average loss: 91.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 436)
+0/69092	Loss: 84.524
+3200/69092	Loss: 90.767
+6400/69092	Loss: 90.377
+9600/69092	Loss: 91.579
+12800/69092	Loss: 92.959
+16000/69092	Loss: 91.280
+19200/69092	Loss: 92.682
+22400/69092	Loss: 92.747
+25600/69092	Loss: 91.847
+28800/69092	Loss: 93.304
+32000/69092	Loss: 91.480
+35200/69092	Loss: 91.805
+38400/69092	Loss: 92.221
+41600/69092	Loss: 92.247
+44800/69092	Loss: 92.214
+48000/69092	Loss: 90.888
+51200/69092	Loss: 91.454
+54400/69092	Loss: 91.290
+57600/69092	Loss: 91.981
+60800/69092	Loss: 90.664
+64000/69092	Loss: 92.822
+67200/69092	Loss: 90.980
+Training time 0:09:24.313635
+Epoch: 163 Average loss: 91.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 437)
+0/69092	Loss: 90.152
+3200/69092	Loss: 91.822
+6400/69092	Loss: 91.403
+9600/69092	Loss: 91.338
+12800/69092	Loss: 91.744
+16000/69092	Loss: 91.207
+19200/69092	Loss: 91.558
+22400/69092	Loss: 91.500
+25600/69092	Loss: 92.289
+28800/69092	Loss: 92.393
+32000/69092	Loss: 91.084
+35200/69092	Loss: 92.961
+38400/69092	Loss: 92.017
+41600/69092	Loss: 91.545
+44800/69092	Loss: 92.963
+48000/69092	Loss: 91.542
+51200/69092	Loss: 91.571
+54400/69092	Loss: 91.306
+57600/69092	Loss: 94.102
+60800/69092	Loss: 92.204
+64000/69092	Loss: 91.182
+67200/69092	Loss: 90.887
+Training time 0:09:22.947507
+Epoch: 164 Average loss: 91.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 438)
+0/69092	Loss: 98.447
+3200/69092	Loss: 91.358
+6400/69092	Loss: 92.214
+9600/69092	Loss: 92.528
+12800/69092	Loss: 91.887
+16000/69092	Loss: 91.895
+19200/69092	Loss: 91.081
+22400/69092	Loss: 90.581
+25600/69092	Loss: 91.746
+28800/69092	Loss: 91.165
+32000/69092	Loss: 91.634
+35200/69092	Loss: 91.140
+38400/69092	Loss: 92.708
+41600/69092	Loss: 93.343
+44800/69092	Loss: 91.092
+48000/69092	Loss: 91.630
+51200/69092	Loss: 90.971
+54400/69092	Loss: 91.955
+57600/69092	Loss: 91.865
+60800/69092	Loss: 93.230
+64000/69092	Loss: 92.588
+67200/69092	Loss: 92.681
+Training time 0:09:15.726676
+Epoch: 165 Average loss: 91.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 439)
+0/69092	Loss: 90.650
+3200/69092	Loss: 90.522
+6400/69092	Loss: 92.173
+9600/69092	Loss: 91.827
+12800/69092	Loss: 92.291
+16000/69092	Loss: 92.532
+19200/69092	Loss: 92.692
+22400/69092	Loss: 90.684
+25600/69092	Loss: 91.755
+28800/69092	Loss: 91.724
+32000/69092	Loss: 91.894
+35200/69092	Loss: 93.405
+38400/69092	Loss: 92.250
+41600/69092	Loss: 93.758
+44800/69092	Loss: 91.522
+48000/69092	Loss: 92.384
+51200/69092	Loss: 90.878
+54400/69092	Loss: 90.904
+57600/69092	Loss: 91.748
+60800/69092	Loss: 91.047
+64000/69092	Loss: 92.421
+67200/69092	Loss: 90.242
+Training time 0:09:09.442750
+Epoch: 166 Average loss: 91.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 440)
+0/69092	Loss: 97.741
+3200/69092	Loss: 91.428
+6400/69092	Loss: 91.373
+9600/69092	Loss: 91.282
+12800/69092	Loss: 91.818
+16000/69092	Loss: 92.355
+19200/69092	Loss: 91.813
+22400/69092	Loss: 91.377
+25600/69092	Loss: 89.945
+28800/69092	Loss: 92.778
+32000/69092	Loss: 91.164
+35200/69092	Loss: 92.578
+38400/69092	Loss: 91.562
+41600/69092	Loss: 92.660
+44800/69092	Loss: 92.416
+48000/69092	Loss: 92.265
+51200/69092	Loss: 92.370
+54400/69092	Loss: 93.890
+57600/69092	Loss: 91.277
+60800/69092	Loss: 91.758
+64000/69092	Loss: 91.558
+67200/69092	Loss: 90.921
+Training time 0:09:31.640009
+Epoch: 167 Average loss: 91.87
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 441)
+0/69092	Loss: 91.409
+3200/69092	Loss: 92.777
+6400/69092	Loss: 91.107
+9600/69092	Loss: 91.246
+12800/69092	Loss: 91.945
+16000/69092	Loss: 92.590
+19200/69092	Loss: 91.660
+22400/69092	Loss: 91.578
+25600/69092	Loss: 91.893
+28800/69092	Loss: 92.470
+32000/69092	Loss: 92.178
+35200/69092	Loss: 91.622
+38400/69092	Loss: 92.650
+41600/69092	Loss: 91.304
+44800/69092	Loss: 91.879
+48000/69092	Loss: 90.472
+51200/69092	Loss: 92.684
+54400/69092	Loss: 92.375
+57600/69092	Loss: 91.308
+60800/69092	Loss: 91.203
+64000/69092	Loss: 92.507
+67200/69092	Loss: 92.946
+Training time 0:08:59.187869
+Epoch: 168 Average loss: 91.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 442)
+0/69092	Loss: 89.336
+3200/69092	Loss: 91.378
+6400/69092	Loss: 91.673
+9600/69092	Loss: 92.039
+12800/69092	Loss: 93.234
+16000/69092	Loss: 92.424
+19200/69092	Loss: 91.539
+22400/69092	Loss: 90.152
+25600/69092	Loss: 91.199
+28800/69092	Loss: 91.356
+32000/69092	Loss: 91.843
+35200/69092	Loss: 92.231
+38400/69092	Loss: 91.968
+41600/69092	Loss: 91.428
+44800/69092	Loss: 90.820
+48000/69092	Loss: 91.748
+51200/69092	Loss: 92.291
+54400/69092	Loss: 92.437
+57600/69092	Loss: 91.829
+60800/69092	Loss: 92.164
+64000/69092	Loss: 92.103
+67200/69092	Loss: 92.449
+Training time 0:09:22.967632
+Epoch: 169 Average loss: 91.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 443)
+0/69092	Loss: 93.775
+3200/69092	Loss: 92.694
+6400/69092	Loss: 91.256
+9600/69092	Loss: 92.471
+12800/69092	Loss: 91.624
+16000/69092	Loss: 91.881
+19200/69092	Loss: 92.353
+22400/69092	Loss: 92.406
+25600/69092	Loss: 91.526
+28800/69092	Loss: 93.356
+32000/69092	Loss: 90.846
+35200/69092	Loss: 91.820
+38400/69092	Loss: 91.454
+41600/69092	Loss: 92.195
+44800/69092	Loss: 92.123
+48000/69092	Loss: 92.899
+51200/69092	Loss: 91.788
+54400/69092	Loss: 91.439
+57600/69092	Loss: 91.066
+60800/69092	Loss: 92.002
+64000/69092	Loss: 90.087
+67200/69092	Loss: 90.685
+Training time 0:08:50.075514
+Epoch: 170 Average loss: 91.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 444)
+0/69092	Loss: 81.602
+3200/69092	Loss: 92.934
+6400/69092	Loss: 92.069
+9600/69092	Loss: 90.232
+12800/69092	Loss: 91.002
+16000/69092	Loss: 91.504
+19200/69092	Loss: 92.093
+22400/69092	Loss: 91.098
+25600/69092	Loss: 91.227
+28800/69092	Loss: 91.037
+32000/69092	Loss: 91.163
+35200/69092	Loss: 91.024
+38400/69092	Loss: 92.176
+41600/69092	Loss: 92.087
+44800/69092	Loss: 92.202
+48000/69092	Loss: 91.532
+51200/69092	Loss: 92.734
+54400/69092	Loss: 92.289
+57600/69092	Loss: 91.990
+60800/69092	Loss: 91.315
+64000/69092	Loss: 93.516
+67200/69092	Loss: 92.237
+Training time 0:09:02.109141
+Epoch: 171 Average loss: 91.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 445)
+0/69092	Loss: 84.844
+3200/69092	Loss: 92.028
+6400/69092	Loss: 91.517
+9600/69092	Loss: 92.498
+12800/69092	Loss: 92.784
+16000/69092	Loss: 92.034
+19200/69092	Loss: 91.006
+22400/69092	Loss: 93.901
+25600/69092	Loss: 91.241
+28800/69092	Loss: 91.173
+32000/69092	Loss: 91.885
+35200/69092	Loss: 92.421
+38400/69092	Loss: 91.936
+41600/69092	Loss: 91.537
+44800/69092	Loss: 92.433
+48000/69092	Loss: 92.513
+51200/69092	Loss: 91.291
+54400/69092	Loss: 89.847
+57600/69092	Loss: 91.786
+60800/69092	Loss: 92.028
+64000/69092	Loss: 92.531
+67200/69092	Loss: 90.933
+Training time 0:08:58.896339
+Epoch: 172 Average loss: 91.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 446)
+0/69092	Loss: 94.568
+3200/69092	Loss: 92.393
+6400/69092	Loss: 90.037
+9600/69092	Loss: 91.358
+12800/69092	Loss: 91.837
+16000/69092	Loss: 91.871
+19200/69092	Loss: 93.222
+22400/69092	Loss: 92.132
+25600/69092	Loss: 91.676
+28800/69092	Loss: 91.789
+32000/69092	Loss: 92.364
+35200/69092	Loss: 91.985
+38400/69092	Loss: 92.698
+41600/69092	Loss: 91.804
+44800/69092	Loss: 91.294
+48000/69092	Loss: 93.502
+51200/69092	Loss: 89.991
+54400/69092	Loss: 92.177
+57600/69092	Loss: 90.834
+60800/69092	Loss: 92.515
+64000/69092	Loss: 92.191
+67200/69092	Loss: 91.381
+Training time 0:09:00.754946
+Epoch: 173 Average loss: 91.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 447)
+0/69092	Loss: 100.044
+3200/69092	Loss: 91.859
+6400/69092	Loss: 91.349
+9600/69092	Loss: 91.472
+12800/69092	Loss: 89.989
+16000/69092	Loss: 91.070
+19200/69092	Loss: 91.906
+22400/69092	Loss: 89.921
+25600/69092	Loss: 91.405
+28800/69092	Loss: 91.710
+32000/69092	Loss: 91.621
+35200/69092	Loss: 91.327
+38400/69092	Loss: 93.174
+41600/69092	Loss: 91.958
+44800/69092	Loss: 92.252
+48000/69092	Loss: 92.608
+51200/69092	Loss: 93.162
+54400/69092	Loss: 90.326
+57600/69092	Loss: 90.613
+60800/69092	Loss: 93.389
+64000/69092	Loss: 92.382
+67200/69092	Loss: 92.523
+Training time 0:09:10.544357
+Epoch: 174 Average loss: 91.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 448)
+0/69092	Loss: 93.416
+3200/69092	Loss: 91.120
+6400/69092	Loss: 92.129
+9600/69092	Loss: 91.573
+12800/69092	Loss: 91.099
+16000/69092	Loss: 91.033
+19200/69092	Loss: 92.283
+22400/69092	Loss: 90.043
+25600/69092	Loss: 90.900
+28800/69092	Loss: 91.581
+32000/69092	Loss: 91.037
+35200/69092	Loss: 92.822
+38400/69092	Loss: 92.874
+41600/69092	Loss: 92.387
+44800/69092	Loss: 92.890
+48000/69092	Loss: 92.056
+51200/69092	Loss: 92.874
+54400/69092	Loss: 90.125
+57600/69092	Loss: 91.422
+60800/69092	Loss: 92.047
+64000/69092	Loss: 92.317
+67200/69092	Loss: 91.987
+Training time 0:09:17.327961
+Epoch: 175 Average loss: 91.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 449)
+0/69092	Loss: 98.819
+3200/69092	Loss: 91.749
+6400/69092	Loss: 90.821
+9600/69092	Loss: 91.248
+12800/69092	Loss: 92.095
+16000/69092	Loss: 91.560
+19200/69092	Loss: 91.401
+22400/69092	Loss: 90.632
+25600/69092	Loss: 93.116
+28800/69092	Loss: 90.629
+32000/69092	Loss: 90.011
+35200/69092	Loss: 91.184
+38400/69092	Loss: 92.474
+41600/69092	Loss: 92.149
+44800/69092	Loss: 92.230
+48000/69092	Loss: 90.949
+51200/69092	Loss: 92.886
+54400/69092	Loss: 91.655
+57600/69092	Loss: 91.410
+60800/69092	Loss: 92.876
+64000/69092	Loss: 92.639
+67200/69092	Loss: 91.653
+Training time 0:09:09.515024
+Epoch: 176 Average loss: 91.70
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 450)
+0/69092	Loss: 90.693
+3200/69092	Loss: 90.501
+6400/69092	Loss: 90.469
+9600/69092	Loss: 90.508
+12800/69092	Loss: 91.830
+16000/69092	Loss: 92.630
+19200/69092	Loss: 92.514
+22400/69092	Loss: 91.701
+25600/69092	Loss: 92.163
+28800/69092	Loss: 91.209
+32000/69092	Loss: 91.816
+35200/69092	Loss: 92.451
+38400/69092	Loss: 90.851
+41600/69092	Loss: 92.181
+44800/69092	Loss: 92.330
+48000/69092	Loss: 92.783
+51200/69092	Loss: 91.644
+54400/69092	Loss: 91.231
+57600/69092	Loss: 92.562
+60800/69092	Loss: 92.537
+64000/69092	Loss: 91.384
+67200/69092	Loss: 92.631
+Training time 0:09:29.266967
+Epoch: 177 Average loss: 91.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 451)
+0/69092	Loss: 90.781
+3200/69092	Loss: 91.826
+6400/69092	Loss: 92.675
+9600/69092	Loss: 91.407
+12800/69092	Loss: 91.850
+16000/69092	Loss: 91.849
+19200/69092	Loss: 90.995
+22400/69092	Loss: 91.104
+25600/69092	Loss: 93.555
+28800/69092	Loss: 90.598
+32000/69092	Loss: 91.653
+35200/69092	Loss: 92.138
+38400/69092	Loss: 94.147
+41600/69092	Loss: 92.391
+44800/69092	Loss: 91.517
+48000/69092	Loss: 89.849
+51200/69092	Loss: 90.936
+54400/69092	Loss: 90.106
+57600/69092	Loss: 91.651
+60800/69092	Loss: 91.083
+64000/69092	Loss: 92.676
+67200/69092	Loss: 91.086
+Training time 0:09:12.378687
+Epoch: 178 Average loss: 91.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 452)
+0/69092	Loss: 98.726
+3200/69092	Loss: 91.072
+6400/69092	Loss: 93.083
+9600/69092	Loss: 92.259
+12800/69092	Loss: 92.251
+16000/69092	Loss: 91.763
+19200/69092	Loss: 90.831
+22400/69092	Loss: 93.074
+25600/69092	Loss: 91.892
+28800/69092	Loss: 92.073
+32000/69092	Loss: 91.117
+35200/69092	Loss: 90.273
+38400/69092	Loss: 91.604
+41600/69092	Loss: 90.439
+44800/69092	Loss: 92.370
+48000/69092	Loss: 91.896
+51200/69092	Loss: 91.670
+54400/69092	Loss: 92.627
+57600/69092	Loss: 91.415
+60800/69092	Loss: 90.224
+64000/69092	Loss: 91.772
+67200/69092	Loss: 93.028
+Training time 0:09:36.366639
+Epoch: 179 Average loss: 91.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 453)
+0/69092	Loss: 89.203
+3200/69092	Loss: 92.047
+6400/69092	Loss: 90.991
+9600/69092	Loss: 91.363
+12800/69092	Loss: 91.896
+16000/69092	Loss: 90.785
+19200/69092	Loss: 92.240
+22400/69092	Loss: 91.270
+25600/69092	Loss: 91.735
+28800/69092	Loss: 93.242
+32000/69092	Loss: 92.068
+35200/69092	Loss: 92.400
+38400/69092	Loss: 90.716
+41600/69092	Loss: 91.059
+44800/69092	Loss: 91.896
+48000/69092	Loss: 91.600
+51200/69092	Loss: 91.380
+54400/69092	Loss: 90.623
+57600/69092	Loss: 90.711
+60800/69092	Loss: 92.317
+64000/69092	Loss: 92.609
+67200/69092	Loss: 91.545
+Training time 0:08:59.004187
+Epoch: 180 Average loss: 91.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 454)
+0/69092	Loss: 83.991
+3200/69092	Loss: 93.609
+6400/69092	Loss: 91.455
+9600/69092	Loss: 92.076
+12800/69092	Loss: 92.204
+16000/69092	Loss: 92.018
+19200/69092	Loss: 91.327
+22400/69092	Loss: 91.308
+25600/69092	Loss: 92.144
+28800/69092	Loss: 92.155
+32000/69092	Loss: 90.352
+35200/69092	Loss: 91.324
+38400/69092	Loss: 91.553
+41600/69092	Loss: 91.787
+44800/69092	Loss: 92.048
+48000/69092	Loss: 91.230
+51200/69092	Loss: 91.914
+54400/69092	Loss: 91.360
+57600/69092	Loss: 92.023
+60800/69092	Loss: 91.325
+64000/69092	Loss: 91.326
+67200/69092	Loss: 91.440
+Training time 0:10:03.312567
+Epoch: 181 Average loss: 91.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 455)
+0/69092	Loss: 88.782
+3200/69092	Loss: 91.873
+6400/69092	Loss: 91.373
+9600/69092	Loss: 91.447
+12800/69092	Loss: 91.848
+16000/69092	Loss: 90.694
+19200/69092	Loss: 92.265
+22400/69092	Loss: 91.969
+25600/69092	Loss: 91.948
+28800/69092	Loss: 93.139
+32000/69092	Loss: 92.529
+35200/69092	Loss: 90.908
+38400/69092	Loss: 91.751
+41600/69092	Loss: 90.522
+44800/69092	Loss: 90.246
+48000/69092	Loss: 92.367
+51200/69092	Loss: 91.342
+54400/69092	Loss: 91.874
+57600/69092	Loss: 92.841
+60800/69092	Loss: 90.962
+64000/69092	Loss: 92.092
+67200/69092	Loss: 92.193
+Training time 0:10:09.506059
+Epoch: 182 Average loss: 91.73
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 456)
+0/69092	Loss: 88.207
+3200/69092	Loss: 91.771
+6400/69092	Loss: 92.292
+9600/69092	Loss: 91.255
+12800/69092	Loss: 90.549
+16000/69092	Loss: 91.699
+19200/69092	Loss: 91.294
+22400/69092	Loss: 90.931
+25600/69092	Loss: 91.445
+28800/69092	Loss: 93.210
+32000/69092	Loss: 91.764
+35200/69092	Loss: 90.597
+38400/69092	Loss: 92.382
+41600/69092	Loss: 90.849
+44800/69092	Loss: 92.949
+48000/69092	Loss: 93.269
+51200/69092	Loss: 91.900
+54400/69092	Loss: 90.744
+57600/69092	Loss: 90.673
+60800/69092	Loss: 91.716
+64000/69092	Loss: 91.432
+67200/69092	Loss: 91.098
+Training time 0:09:34.606604
+Epoch: 183 Average loss: 91.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 457)
+0/69092	Loss: 92.495
+3200/69092	Loss: 91.981
+6400/69092	Loss: 91.809
+9600/69092	Loss: 91.381
+12800/69092	Loss: 92.153
+16000/69092	Loss: 91.703
+19200/69092	Loss: 91.903
+22400/69092	Loss: 92.772
+25600/69092	Loss: 93.223
+28800/69092	Loss: 91.319
+32000/69092	Loss: 91.020
+35200/69092	Loss: 92.605
+38400/69092	Loss: 91.373
+41600/69092	Loss: 92.144
+44800/69092	Loss: 91.837
+48000/69092	Loss: 91.208
+51200/69092	Loss: 91.332
+54400/69092	Loss: 90.824
+57600/69092	Loss: 92.335
+60800/69092	Loss: 91.835
+64000/69092	Loss: 91.587
+67200/69092	Loss: 91.433
+Training time 0:09:26.976478
+Epoch: 184 Average loss: 91.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 458)
+0/69092	Loss: 91.757
+3200/69092	Loss: 91.004
+6400/69092	Loss: 90.986
+9600/69092	Loss: 91.437
+12800/69092	Loss: 92.783
+16000/69092	Loss: 91.126
+19200/69092	Loss: 92.294
+22400/69092	Loss: 91.914
+25600/69092	Loss: 92.063
+28800/69092	Loss: 91.555
+32000/69092	Loss: 90.565
+35200/69092	Loss: 91.741
+38400/69092	Loss: 91.401
+41600/69092	Loss: 92.477
+44800/69092	Loss: 91.405
+48000/69092	Loss: 91.884
+51200/69092	Loss: 92.537
+54400/69092	Loss: 89.975
+57600/69092	Loss: 90.544
+60800/69092	Loss: 93.293
+64000/69092	Loss: 91.254
+67200/69092	Loss: 91.357
+Training time 0:10:25.513529
+Epoch: 185 Average loss: 91.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 459)
+0/69092	Loss: 83.694
+3200/69092	Loss: 91.531
+6400/69092	Loss: 90.794
+9600/69092	Loss: 91.129
+12800/69092	Loss: 91.605
+16000/69092	Loss: 92.120
+19200/69092	Loss: 90.303
+22400/69092	Loss: 91.690
+25600/69092	Loss: 91.863
+28800/69092	Loss: 92.357
+32000/69092	Loss: 91.197
+35200/69092	Loss: 92.009
+38400/69092	Loss: 91.103
+41600/69092	Loss: 91.392
+44800/69092	Loss: 93.181
+48000/69092	Loss: 92.062
+51200/69092	Loss: 91.375
+54400/69092	Loss: 92.252
+57600/69092	Loss: 91.727
+60800/69092	Loss: 91.365
+64000/69092	Loss: 91.595
+67200/69092	Loss: 92.010
+Training time 0:12:30.042349
+Epoch: 186 Average loss: 91.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 460)
+0/69092	Loss: 96.268
+3200/69092	Loss: 91.410
+6400/69092	Loss: 91.754
+9600/69092	Loss: 90.444
+12800/69092	Loss: 92.474
+16000/69092	Loss: 91.239
+19200/69092	Loss: 91.643
+22400/69092	Loss: 90.980
+25600/69092	Loss: 91.908
+28800/69092	Loss: 92.625
+32000/69092	Loss: 91.359
+35200/69092	Loss: 91.546
+38400/69092	Loss: 91.605
+41600/69092	Loss: 91.670
+44800/69092	Loss: 90.528
+48000/69092	Loss: 92.515
+51200/69092	Loss: 91.964
+54400/69092	Loss: 90.902
+57600/69092	Loss: 91.447
+60800/69092	Loss: 92.375
+64000/69092	Loss: 91.659
+67200/69092	Loss: 92.271
+Training time 0:12:18.991371
+Epoch: 187 Average loss: 91.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 461)
+0/69092	Loss: 88.961
+3200/69092	Loss: 91.695
+6400/69092	Loss: 90.395
+9600/69092	Loss: 90.898
+12800/69092	Loss: 90.639
+16000/69092	Loss: 92.316
+19200/69092	Loss: 91.790
+22400/69092	Loss: 90.799
+25600/69092	Loss: 91.855
+28800/69092	Loss: 91.979
+32000/69092	Loss: 91.185
+35200/69092	Loss: 91.431
+38400/69092	Loss: 91.946
+41600/69092	Loss: 92.278
+44800/69092	Loss: 91.822
+48000/69092	Loss: 92.549
+51200/69092	Loss: 92.060
+54400/69092	Loss: 92.006
+57600/69092	Loss: 90.796
+60800/69092	Loss: 91.388
+64000/69092	Loss: 92.066
+67200/69092	Loss: 91.156
+Training time 0:09:12.808779
+Epoch: 188 Average loss: 91.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 462)
+0/69092	Loss: 93.178
+3200/69092	Loss: 93.087
+6400/69092	Loss: 92.024
+9600/69092	Loss: 93.261
+12800/69092	Loss: 90.820
+16000/69092	Loss: 91.301
+19200/69092	Loss: 90.181
+22400/69092	Loss: 90.112
+25600/69092	Loss: 91.096
+28800/69092	Loss: 91.560
+32000/69092	Loss: 92.218
+35200/69092	Loss: 90.702
+38400/69092	Loss: 91.090
+41600/69092	Loss: 93.038
+44800/69092	Loss: 91.909
+48000/69092	Loss: 91.183
+51200/69092	Loss: 92.272
+54400/69092	Loss: 91.147
+57600/69092	Loss: 91.311
+60800/69092	Loss: 91.273
+64000/69092	Loss: 90.928
+67200/69092	Loss: 91.762
+Training time 0:08:57.042188
+Epoch: 189 Average loss: 91.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 463)
+0/69092	Loss: 93.221
+3200/69092	Loss: 91.421
+6400/69092	Loss: 91.188
+9600/69092	Loss: 91.617
+12800/69092	Loss: 91.484
+16000/69092	Loss: 91.671
+19200/69092	Loss: 90.307
+22400/69092	Loss: 92.640
+25600/69092	Loss: 92.106
+28800/69092	Loss: 92.910
+32000/69092	Loss: 92.764
+35200/69092	Loss: 90.614
+38400/69092	Loss: 90.834
+41600/69092	Loss: 92.050
+44800/69092	Loss: 91.245
+48000/69092	Loss: 90.336
+51200/69092	Loss: 92.334
+54400/69092	Loss: 91.068
+57600/69092	Loss: 92.019
+60800/69092	Loss: 91.188
+64000/69092	Loss: 92.173
+67200/69092	Loss: 92.519
+Training time 0:09:12.835653
+Epoch: 190 Average loss: 91.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 464)
+0/69092	Loss: 88.732
+3200/69092	Loss: 92.387
+6400/69092	Loss: 91.347
+9600/69092	Loss: 92.028
+12800/69092	Loss: 91.810
+16000/69092	Loss: 91.178
+19200/69092	Loss: 90.543
+22400/69092	Loss: 90.820
+25600/69092	Loss: 91.033
+28800/69092	Loss: 91.481
+32000/69092	Loss: 91.733
+35200/69092	Loss: 92.369
+38400/69092	Loss: 91.325
+41600/69092	Loss: 91.638
+44800/69092	Loss: 92.088
+48000/69092	Loss: 90.575
+51200/69092	Loss: 91.883
+54400/69092	Loss: 91.051
+57600/69092	Loss: 91.777
+60800/69092	Loss: 90.907
+64000/69092	Loss: 91.780
+67200/69092	Loss: 92.448
+Training time 0:09:07.374636
+Epoch: 191 Average loss: 91.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 465)
+0/69092	Loss: 92.439
+3200/69092	Loss: 91.334
+6400/69092	Loss: 92.625
+9600/69092	Loss: 91.749
+12800/69092	Loss: 91.084
+16000/69092	Loss: 92.094
+19200/69092	Loss: 93.100
+22400/69092	Loss: 91.623
+25600/69092	Loss: 92.272
+28800/69092	Loss: 91.040
+32000/69092	Loss: 90.631
+35200/69092	Loss: 92.136
+38400/69092	Loss: 90.950
+41600/69092	Loss: 92.829
+44800/69092	Loss: 91.511
+48000/69092	Loss: 92.627
+51200/69092	Loss: 90.338
+54400/69092	Loss: 92.538
+57600/69092	Loss: 91.398
+60800/69092	Loss: 91.970
+64000/69092	Loss: 91.432
+67200/69092	Loss: 91.022
+Training time 0:09:14.327296
+Epoch: 192 Average loss: 91.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 466)
+0/69092	Loss: 91.983
+3200/69092	Loss: 91.116
+6400/69092	Loss: 92.378
+9600/69092	Loss: 90.838
+12800/69092	Loss: 92.496
+16000/69092	Loss: 91.071
+19200/69092	Loss: 91.687
+22400/69092	Loss: 91.931
+25600/69092	Loss: 91.802
+28800/69092	Loss: 91.077
+32000/69092	Loss: 91.557
+35200/69092	Loss: 91.991
+38400/69092	Loss: 91.032
+41600/69092	Loss: 92.928
+44800/69092	Loss: 92.509
+48000/69092	Loss: 91.002
+51200/69092	Loss: 90.788
+54400/69092	Loss: 91.908
+57600/69092	Loss: 91.492
+60800/69092	Loss: 92.735
+64000/69092	Loss: 92.212
+67200/69092	Loss: 90.923
+Training time 0:09:08.964932
+Epoch: 193 Average loss: 91.69
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 467)
+0/69092	Loss: 99.497
+3200/69092	Loss: 90.870
+6400/69092	Loss: 90.090
+9600/69092	Loss: 90.786
+12800/69092	Loss: 91.568
+16000/69092	Loss: 91.131
+19200/69092	Loss: 93.189
+22400/69092	Loss: 92.022
+25600/69092	Loss: 91.893
+28800/69092	Loss: 91.072
+32000/69092	Loss: 92.211
+35200/69092	Loss: 91.330
+38400/69092	Loss: 92.226
+41600/69092	Loss: 92.685
+44800/69092	Loss: 90.488
+48000/69092	Loss: 91.999
+51200/69092	Loss: 91.439
+54400/69092	Loss: 91.164
+57600/69092	Loss: 90.495
+60800/69092	Loss: 92.162
+64000/69092	Loss: 92.239
+67200/69092	Loss: 90.326
+Training time 0:09:15.572436
+Epoch: 194 Average loss: 91.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 468)
+0/69092	Loss: 96.908
+3200/69092	Loss: 91.746
+6400/69092	Loss: 90.765
+9600/69092	Loss: 92.329
+12800/69092	Loss: 91.663
+16000/69092	Loss: 92.256
+19200/69092	Loss: 91.099
+22400/69092	Loss: 92.186
+25600/69092	Loss: 90.801
+28800/69092	Loss: 89.694
+32000/69092	Loss: 90.998
+35200/69092	Loss: 93.487
+38400/69092	Loss: 91.097
+41600/69092	Loss: 90.159
+44800/69092	Loss: 91.116
+48000/69092	Loss: 91.449
+51200/69092	Loss: 91.246
+54400/69092	Loss: 94.168
+57600/69092	Loss: 90.752
+60800/69092	Loss: 91.528
+64000/69092	Loss: 93.140
+67200/69092	Loss: 91.218
+Training time 0:09:25.758512
+Epoch: 195 Average loss: 91.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 469)
+0/69092	Loss: 79.500
+3200/69092	Loss: 91.367
+6400/69092	Loss: 90.851
+9600/69092	Loss: 92.389
+12800/69092	Loss: 91.697
+16000/69092	Loss: 91.831
+19200/69092	Loss: 91.671
+22400/69092	Loss: 90.995
+25600/69092	Loss: 92.067
+28800/69092	Loss: 92.329
+32000/69092	Loss: 92.280
+35200/69092	Loss: 91.215
+38400/69092	Loss: 91.755
+41600/69092	Loss: 90.177
+44800/69092	Loss: 91.322
+48000/69092	Loss: 92.094
+51200/69092	Loss: 93.036
+54400/69092	Loss: 92.035
+57600/69092	Loss: 92.133
+60800/69092	Loss: 91.636
+64000/69092	Loss: 91.200
+67200/69092	Loss: 92.404
+Training time 0:09:13.104178
+Epoch: 196 Average loss: 91.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 470)
+0/69092	Loss: 85.968
+3200/69092	Loss: 92.276
+6400/69092	Loss: 91.106
+9600/69092	Loss: 90.865
+12800/69092	Loss: 91.741
+16000/69092	Loss: 92.611
+19200/69092	Loss: 92.188
+22400/69092	Loss: 90.565
+25600/69092	Loss: 91.004
+28800/69092	Loss: 91.303
+32000/69092	Loss: 92.477
+35200/69092	Loss: 91.044
+38400/69092	Loss: 90.608
+41600/69092	Loss: 92.426
+44800/69092	Loss: 92.520
+48000/69092	Loss: 91.778
+51200/69092	Loss: 90.289
+54400/69092	Loss: 91.373
+57600/69092	Loss: 92.193
+60800/69092	Loss: 92.792
+64000/69092	Loss: 91.452
+67200/69092	Loss: 92.881
+Training time 0:09:20.320731
+Epoch: 197 Average loss: 91.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 471)
+0/69092	Loss: 91.516
+3200/69092	Loss: 90.725
+6400/69092	Loss: 90.803
+9600/69092	Loss: 92.089
+12800/69092	Loss: 92.492
+16000/69092	Loss: 92.983
+19200/69092	Loss: 90.578
+22400/69092	Loss: 90.874
+25600/69092	Loss: 89.864
+28800/69092	Loss: 92.386
+32000/69092	Loss: 91.860
+35200/69092	Loss: 92.691
+38400/69092	Loss: 91.121
+41600/69092	Loss: 91.445
+44800/69092	Loss: 91.971
+48000/69092	Loss: 92.604
+51200/69092	Loss: 92.029
+54400/69092	Loss: 91.812
+57600/69092	Loss: 92.076
+60800/69092	Loss: 92.732
+64000/69092	Loss: 90.182
+67200/69092	Loss: 92.071
+Training time 0:09:03.455825
+Epoch: 198 Average loss: 91.69
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 472)
+0/69092	Loss: 92.601
+3200/69092	Loss: 92.523
+6400/69092	Loss: 91.811
+9600/69092	Loss: 92.786
+12800/69092	Loss: 92.378
+16000/69092	Loss: 90.828
+19200/69092	Loss: 91.295
+22400/69092	Loss: 91.170
+25600/69092	Loss: 90.942
+28800/69092	Loss: 90.897
+32000/69092	Loss: 90.957
+35200/69092	Loss: 91.855
+38400/69092	Loss: 92.091
+41600/69092	Loss: 91.807
+44800/69092	Loss: 91.590
+48000/69092	Loss: 92.009
+51200/69092	Loss: 89.820
+54400/69092	Loss: 91.851
+57600/69092	Loss: 93.456
+60800/69092	Loss: 91.052
+64000/69092	Loss: 91.228
+67200/69092	Loss: 91.647
+Training time 0:09:18.905715
+Epoch: 199 Average loss: 91.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 473)
+0/69092	Loss: 91.826
+3200/69092	Loss: 90.827
+6400/69092	Loss: 90.540
+9600/69092	Loss: 91.062
+12800/69092	Loss: 91.202
+16000/69092	Loss: 92.162
+19200/69092	Loss: 91.683
+22400/69092	Loss: 91.639
+25600/69092	Loss: 92.209
+28800/69092	Loss: 92.721
+32000/69092	Loss: 91.379
+35200/69092	Loss: 92.341
+38400/69092	Loss: 91.677
+41600/69092	Loss: 92.160
+44800/69092	Loss: 90.510
+48000/69092	Loss: 90.753
+51200/69092	Loss: 90.465
+54400/69092	Loss: 92.816
+57600/69092	Loss: 91.572
+60800/69092	Loss: 92.127
+64000/69092	Loss: 92.406
+67200/69092	Loss: 92.154
+Training time 0:09:16.899494
+Epoch: 200 Average loss: 91.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 474)
+0/69092	Loss: 90.308
+3200/69092	Loss: 92.036
+6400/69092	Loss: 91.401
+9600/69092	Loss: 91.493
+12800/69092	Loss: 90.525
+16000/69092	Loss: 91.276
+19200/69092	Loss: 92.181
+22400/69092	Loss: 92.536
+25600/69092	Loss: 91.577
+28800/69092	Loss: 91.189
+32000/69092	Loss: 93.311
+35200/69092	Loss: 91.838
+38400/69092	Loss: 92.170
+41600/69092	Loss: 91.492
+44800/69092	Loss: 91.990
+48000/69092	Loss: 91.767
+51200/69092	Loss: 91.123
+54400/69092	Loss: 91.407
+57600/69092	Loss: 91.919
+60800/69092	Loss: 91.818
+64000/69092	Loss: 90.941
+67200/69092	Loss: 91.026
+Training time 0:09:09.534051
+Epoch: 201 Average loss: 91.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 475)
+0/69092	Loss: 83.192
+3200/69092	Loss: 90.671
+6400/69092	Loss: 91.714
+9600/69092	Loss: 91.149
+12800/69092	Loss: 91.642
+16000/69092	Loss: 91.795
+19200/69092	Loss: 92.004
+22400/69092	Loss: 92.022
+25600/69092	Loss: 91.033
+28800/69092	Loss: 90.057
+32000/69092	Loss: 91.457
+35200/69092	Loss: 91.091
+38400/69092	Loss: 92.147
+41600/69092	Loss: 92.131
+44800/69092	Loss: 91.589
+48000/69092	Loss: 93.013
+51200/69092	Loss: 91.901
+54400/69092	Loss: 91.198
+57600/69092	Loss: 91.179
+60800/69092	Loss: 91.746
+64000/69092	Loss: 91.792
+67200/69092	Loss: 91.031
+Training time 0:09:17.341926
+Epoch: 202 Average loss: 91.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 476)
+0/69092	Loss: 106.665
+3200/69092	Loss: 92.247
+6400/69092	Loss: 92.297
+9600/69092	Loss: 92.054
+12800/69092	Loss: 92.337
+16000/69092	Loss: 92.159
+19200/69092	Loss: 90.383
+22400/69092	Loss: 91.833
+25600/69092	Loss: 91.857
+28800/69092	Loss: 91.190
+32000/69092	Loss: 90.715
+35200/69092	Loss: 92.041
+38400/69092	Loss: 91.930
+41600/69092	Loss: 91.957
+44800/69092	Loss: 92.099
+48000/69092	Loss: 91.563
+51200/69092	Loss: 91.762
+54400/69092	Loss: 91.049
+57600/69092	Loss: 90.407
+60800/69092	Loss: 92.133
+64000/69092	Loss: 91.316
+67200/69092	Loss: 90.968
+Training time 0:08:52.498032
+Epoch: 203 Average loss: 91.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 477)
+0/69092	Loss: 88.260
+3200/69092	Loss: 89.999
+6400/69092	Loss: 91.828
+9600/69092	Loss: 91.987
+12800/69092	Loss: 92.744
+16000/69092	Loss: 90.678
+19200/69092	Loss: 91.542
+22400/69092	Loss: 91.632
+25600/69092	Loss: 91.608
+28800/69092	Loss: 91.265
+32000/69092	Loss: 92.682
+35200/69092	Loss: 91.484
+38400/69092	Loss: 92.124
+41600/69092	Loss: 91.703
+44800/69092	Loss: 90.467
+48000/69092	Loss: 91.379
+51200/69092	Loss: 91.012
+54400/69092	Loss: 91.756
+57600/69092	Loss: 91.115
+60800/69092	Loss: 91.991
+64000/69092	Loss: 92.679
+67200/69092	Loss: 90.919
+Training time 0:08:47.392015
+Epoch: 204 Average loss: 91.59
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 478)
+0/69092	Loss: 99.760
+3200/69092	Loss: 90.563
+6400/69092	Loss: 90.993
+9600/69092	Loss: 90.338
+12800/69092	Loss: 91.112
+16000/69092	Loss: 92.846
+19200/69092	Loss: 91.754
+22400/69092	Loss: 91.798
+25600/69092	Loss: 90.936
+28800/69092	Loss: 91.713
+32000/69092	Loss: 91.267
+35200/69092	Loss: 91.586
+38400/69092	Loss: 91.011
+41600/69092	Loss: 90.421
+44800/69092	Loss: 91.459
+48000/69092	Loss: 90.299
+51200/69092	Loss: 93.219
+54400/69092	Loss: 90.953
+57600/69092	Loss: 90.416
+60800/69092	Loss: 93.810
+64000/69092	Loss: 92.520
+67200/69092	Loss: 91.793
+Training time 0:09:21.041407
+Epoch: 205 Average loss: 91.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 479)
+0/69092	Loss: 87.775
+3200/69092	Loss: 91.696
+6400/69092	Loss: 89.644
+9600/69092	Loss: 89.711
+12800/69092	Loss: 92.757
+16000/69092	Loss: 92.531
+19200/69092	Loss: 92.506
+22400/69092	Loss: 91.429
+25600/69092	Loss: 89.811
+28800/69092	Loss: 91.141
+32000/69092	Loss: 91.976
+35200/69092	Loss: 92.275
+38400/69092	Loss: 92.947
+41600/69092	Loss: 90.709
+44800/69092	Loss: 91.624
+48000/69092	Loss: 92.914
+51200/69092	Loss: 91.979
+54400/69092	Loss: 90.829
+57600/69092	Loss: 92.758
+60800/69092	Loss: 91.317
+64000/69092	Loss: 90.494
+67200/69092	Loss: 91.251
+Training time 0:08:52.697592
+Epoch: 206 Average loss: 91.57
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 480)
+0/69092	Loss: 97.792
+3200/69092	Loss: 91.187
+6400/69092	Loss: 89.968
+9600/69092	Loss: 91.875
+12800/69092	Loss: 92.778
+16000/69092	Loss: 91.456
+19200/69092	Loss: 93.176
+22400/69092	Loss: 91.277
+25600/69092	Loss: 91.504
+28800/69092	Loss: 91.197
+32000/69092	Loss: 90.127
+35200/69092	Loss: 90.962
+38400/69092	Loss: 90.393
+41600/69092	Loss: 90.520
+44800/69092	Loss: 91.587
+48000/69092	Loss: 91.792
+51200/69092	Loss: 91.772
+54400/69092	Loss: 92.937
+57600/69092	Loss: 91.873
+60800/69092	Loss: 92.609
+64000/69092	Loss: 92.312
+67200/69092	Loss: 92.201
+Training time 0:09:15.241987
+Epoch: 207 Average loss: 91.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 481)
+0/69092	Loss: 90.590
+3200/69092	Loss: 91.629
+6400/69092	Loss: 93.082
+9600/69092	Loss: 91.510
+12800/69092	Loss: 90.775
+16000/69092	Loss: 90.925
+19200/69092	Loss: 91.343
+22400/69092	Loss: 91.588
+25600/69092	Loss: 92.711
+28800/69092	Loss: 91.215
+32000/69092	Loss: 91.919
+35200/69092	Loss: 92.863
+38400/69092	Loss: 91.875
+41600/69092	Loss: 90.464
+44800/69092	Loss: 91.958
+48000/69092	Loss: 91.656
+51200/69092	Loss: 91.971
+54400/69092	Loss: 90.733
+57600/69092	Loss: 91.118
+60800/69092	Loss: 90.745
+64000/69092	Loss: 90.727
+67200/69092	Loss: 91.163
+Training time 0:09:24.140712
+Epoch: 208 Average loss: 91.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 482)
+0/69092	Loss: 89.602
+3200/69092	Loss: 91.499
+6400/69092	Loss: 92.348
+9600/69092	Loss: 90.159
+12800/69092	Loss: 90.509
+16000/69092	Loss: 90.774
+19200/69092	Loss: 92.990
+22400/69092	Loss: 91.155
+25600/69092	Loss: 91.896
+28800/69092	Loss: 91.219
+32000/69092	Loss: 92.131
+35200/69092	Loss: 92.111
+38400/69092	Loss: 92.349
+41600/69092	Loss: 89.981
+44800/69092	Loss: 91.968
+48000/69092	Loss: 91.060
+51200/69092	Loss: 91.757
+54400/69092	Loss: 91.203
+57600/69092	Loss: 90.723
+60800/69092	Loss: 91.250
+64000/69092	Loss: 91.773
+67200/69092	Loss: 92.112
+Training time 0:09:04.877000
+Epoch: 209 Average loss: 91.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 483)
+0/69092	Loss: 91.984
+3200/69092	Loss: 91.854
+6400/69092	Loss: 92.329
+9600/69092	Loss: 91.337
+12800/69092	Loss: 92.547
+16000/69092	Loss: 90.957
+19200/69092	Loss: 91.673
+22400/69092	Loss: 91.630
+25600/69092	Loss: 90.557
+28800/69092	Loss: 90.722
+32000/69092	Loss: 91.880
+35200/69092	Loss: 91.527
+38400/69092	Loss: 91.958
+41600/69092	Loss: 91.326
+44800/69092	Loss: 92.134
+48000/69092	Loss: 90.518
+51200/69092	Loss: 90.685
+54400/69092	Loss: 91.670
+57600/69092	Loss: 90.780
+60800/69092	Loss: 90.762
+64000/69092	Loss: 90.769
+67200/69092	Loss: 92.253
+Training time 0:09:07.705281
+Epoch: 210 Average loss: 91.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 484)
+0/69092	Loss: 91.881
+3200/69092	Loss: 90.612
+6400/69092	Loss: 90.786
+9600/69092	Loss: 90.490
+12800/69092	Loss: 91.644
+16000/69092	Loss: 92.392
+19200/69092	Loss: 92.432
+22400/69092	Loss: 91.932
+25600/69092	Loss: 92.309
+28800/69092	Loss: 91.375
+32000/69092	Loss: 92.026
+35200/69092	Loss: 91.892
+38400/69092	Loss: 90.820
+41600/69092	Loss: 91.423
+44800/69092	Loss: 91.307
+48000/69092	Loss: 91.737
+51200/69092	Loss: 91.880
+54400/69092	Loss: 91.247
+57600/69092	Loss: 92.057
+60800/69092	Loss: 90.043
+64000/69092	Loss: 91.656
+67200/69092	Loss: 92.037
+Training time 0:09:08.531300
+Epoch: 211 Average loss: 91.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 485)
+0/69092	Loss: 85.857
+3200/69092	Loss: 90.742
+6400/69092	Loss: 91.722
+9600/69092	Loss: 92.336
+12800/69092	Loss: 92.299
+16000/69092	Loss: 91.076
+19200/69092	Loss: 91.467
+22400/69092	Loss: 91.578
+25600/69092	Loss: 90.805
+28800/69092	Loss: 91.768
+32000/69092	Loss: 91.014
+35200/69092	Loss: 89.680
+38400/69092	Loss: 91.202
+41600/69092	Loss: 91.631
+44800/69092	Loss: 91.583
+48000/69092	Loss: 91.460
+51200/69092	Loss: 92.024
+54400/69092	Loss: 90.914
+57600/69092	Loss: 92.518
+60800/69092	Loss: 91.812
+64000/69092	Loss: 91.631
+67200/69092	Loss: 92.560
+Training time 0:09:26.058235
+Epoch: 212 Average loss: 91.57
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 486)
+0/69092	Loss: 93.344
+3200/69092	Loss: 91.268
+6400/69092	Loss: 91.952
+9600/69092	Loss: 90.728
+12800/69092	Loss: 90.793
+16000/69092	Loss: 90.978
+19200/69092	Loss: 92.151
+22400/69092	Loss: 91.901
+25600/69092	Loss: 90.961
+28800/69092	Loss: 90.796
+32000/69092	Loss: 90.302
+35200/69092	Loss: 92.061
+38400/69092	Loss: 92.254
+41600/69092	Loss: 91.867
+44800/69092	Loss: 92.227
+48000/69092	Loss: 91.060
+51200/69092	Loss: 91.018
+54400/69092	Loss: 92.325
+57600/69092	Loss: 92.060
+60800/69092	Loss: 91.679
+64000/69092	Loss: 92.001
+67200/69092	Loss: 91.493
+Training time 0:09:03.952879
+Epoch: 213 Average loss: 91.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 487)
+0/69092	Loss: 88.031
+3200/69092	Loss: 91.149
+6400/69092	Loss: 91.437
+9600/69092	Loss: 89.715
+12800/69092	Loss: 91.769
+16000/69092	Loss: 92.271
+19200/69092	Loss: 90.687
+22400/69092	Loss: 89.984
+25600/69092	Loss: 92.056
+28800/69092	Loss: 91.661
+32000/69092	Loss: 92.071
+35200/69092	Loss: 91.821
+38400/69092	Loss: 91.258
+41600/69092	Loss: 90.714
+44800/69092	Loss: 92.087
+48000/69092	Loss: 91.446
+51200/69092	Loss: 91.021
+54400/69092	Loss: 91.508
+57600/69092	Loss: 91.004
+60800/69092	Loss: 93.188
+64000/69092	Loss: 92.469
+67200/69092	Loss: 91.949
+Training time 0:08:55.908873
+Epoch: 214 Average loss: 91.47
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 488)
+0/69092	Loss: 91.599
+3200/69092	Loss: 91.367
+6400/69092	Loss: 91.809
+9600/69092	Loss: 92.465
+12800/69092	Loss: 92.420
+16000/69092	Loss: 91.711
+19200/69092	Loss: 92.323
+22400/69092	Loss: 90.466
+25600/69092	Loss: 91.660
+28800/69092	Loss: 91.886
+32000/69092	Loss: 92.149
+35200/69092	Loss: 90.678
+38400/69092	Loss: 92.076
+41600/69092	Loss: 91.075
+44800/69092	Loss: 92.862
+48000/69092	Loss: 90.071
+51200/69092	Loss: 92.559
+54400/69092	Loss: 91.078
+57600/69092	Loss: 91.822
+60800/69092	Loss: 92.045
+64000/69092	Loss: 91.109
+67200/69092	Loss: 91.409
+Training time 0:09:14.219483
+Epoch: 215 Average loss: 91.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 489)
+0/69092	Loss: 92.964
+3200/69092	Loss: 91.060
+6400/69092	Loss: 91.848
+9600/69092	Loss: 93.152
+12800/69092	Loss: 90.070
+16000/69092	Loss: 91.104
+19200/69092	Loss: 91.235
+22400/69092	Loss: 92.064
+25600/69092	Loss: 92.003
+28800/69092	Loss: 90.685
+32000/69092	Loss: 91.561
+35200/69092	Loss: 91.848
+38400/69092	Loss: 92.279
+41600/69092	Loss: 91.566
+44800/69092	Loss: 91.479
+48000/69092	Loss: 91.301
+51200/69092	Loss: 91.533
+54400/69092	Loss: 90.562
+57600/69092	Loss: 91.511
+60800/69092	Loss: 92.648
+64000/69092	Loss: 92.069
+67200/69092	Loss: 92.032
+Training time 0:09:28.980372
+Epoch: 216 Average loss: 91.57
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 490)
+0/69092	Loss: 102.241
+3200/69092	Loss: 91.065
+6400/69092	Loss: 90.175
+9600/69092	Loss: 90.486
+12800/69092	Loss: 91.130
+16000/69092	Loss: 89.589
+19200/69092	Loss: 90.505
+22400/69092	Loss: 91.521
+25600/69092	Loss: 93.202
+28800/69092	Loss: 92.229
+32000/69092	Loss: 91.167
+35200/69092	Loss: 92.020
+38400/69092	Loss: 90.941
+41600/69092	Loss: 91.863
+44800/69092	Loss: 91.561
+48000/69092	Loss: 91.797
+51200/69092	Loss: 91.513
+54400/69092	Loss: 92.564
+57600/69092	Loss: 92.595
+60800/69092	Loss: 90.930
+64000/69092	Loss: 92.695
+67200/69092	Loss: 92.692
+Training time 0:08:55.337526
+Epoch: 217 Average loss: 91.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 491)
+0/69092	Loss: 96.405
+3200/69092	Loss: 92.009
+6400/69092	Loss: 90.605
+9600/69092	Loss: 91.626
+12800/69092	Loss: 91.359
+16000/69092	Loss: 92.120
+19200/69092	Loss: 90.475
+22400/69092	Loss: 93.177
+25600/69092	Loss: 92.101
+28800/69092	Loss: 90.976
+32000/69092	Loss: 90.938
+35200/69092	Loss: 91.934
+38400/69092	Loss: 91.385
+41600/69092	Loss: 91.017
+44800/69092	Loss: 91.009
+48000/69092	Loss: 92.317
+51200/69092	Loss: 92.172
+54400/69092	Loss: 91.313
+57600/69092	Loss: 92.144
+60800/69092	Loss: 89.707
+64000/69092	Loss: 90.897
+67200/69092	Loss: 93.352
+Training time 0:09:28.894598
+Epoch: 218 Average loss: 91.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 492)
+0/69092	Loss: 94.742
+3200/69092	Loss: 92.601
+6400/69092	Loss: 91.037
+9600/69092	Loss: 90.292
+12800/69092	Loss: 91.088
+16000/69092	Loss: 93.489
+19200/69092	Loss: 92.605
+22400/69092	Loss: 90.891
+25600/69092	Loss: 90.250
+28800/69092	Loss: 91.333
+32000/69092	Loss: 92.696
+35200/69092	Loss: 90.957
+38400/69092	Loss: 92.158
+41600/69092	Loss: 91.606
+44800/69092	Loss: 91.978
+48000/69092	Loss: 91.174
+51200/69092	Loss: 90.943
+54400/69092	Loss: 91.311
+57600/69092	Loss: 91.200
+60800/69092	Loss: 91.156
+64000/69092	Loss: 92.155
+67200/69092	Loss: 91.356
+Training time 0:09:22.922135
+Epoch: 219 Average loss: 91.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 493)
+0/69092	Loss: 83.161
+3200/69092	Loss: 91.061
+6400/69092	Loss: 91.244
+9600/69092	Loss: 90.590
+12800/69092	Loss: 91.123
+16000/69092	Loss: 92.694
+19200/69092	Loss: 91.686
+22400/69092	Loss: 91.914
+25600/69092	Loss: 91.151
+28800/69092	Loss: 90.826
+32000/69092	Loss: 91.369
+35200/69092	Loss: 91.703
+38400/69092	Loss: 91.720
+41600/69092	Loss: 92.262
+44800/69092	Loss: 90.355
+48000/69092	Loss: 91.018
+51200/69092	Loss: 90.991
+54400/69092	Loss: 91.628
+57600/69092	Loss: 91.681
+60800/69092	Loss: 91.762
+64000/69092	Loss: 91.671
+67200/69092	Loss: 91.123
+Training time 0:09:26.713460
+Epoch: 220 Average loss: 91.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 494)
+0/69092	Loss: 85.072
+3200/69092	Loss: 90.496
+6400/69092	Loss: 91.069
+9600/69092	Loss: 92.433
+12800/69092	Loss: 91.338
+16000/69092	Loss: 92.060
+19200/69092	Loss: 92.391
+22400/69092	Loss: 91.740
+25600/69092	Loss: 92.502
+28800/69092	Loss: 91.013
+32000/69092	Loss: 91.335
+35200/69092	Loss: 90.481
+38400/69092	Loss: 92.236
+41600/69092	Loss: 91.094
+44800/69092	Loss: 92.170
+48000/69092	Loss: 91.390
+51200/69092	Loss: 91.162
+54400/69092	Loss: 91.180
+57600/69092	Loss: 90.616
+60800/69092	Loss: 92.372
+64000/69092	Loss: 90.649
+67200/69092	Loss: 90.470
+Training time 0:09:13.642592
+Epoch: 221 Average loss: 91.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 495)
+0/69092	Loss: 94.170
+3200/69092	Loss: 90.876
+6400/69092	Loss: 91.545
+9600/69092	Loss: 92.283
+12800/69092	Loss: 90.910
+16000/69092	Loss: 91.307
+19200/69092	Loss: 89.587
+22400/69092	Loss: 91.929
+25600/69092	Loss: 91.142
+28800/69092	Loss: 92.661
+32000/69092	Loss: 92.211
+35200/69092	Loss: 91.127
+38400/69092	Loss: 90.971
+41600/69092	Loss: 91.651
+44800/69092	Loss: 91.189
+48000/69092	Loss: 92.072
+51200/69092	Loss: 91.302
+54400/69092	Loss: 92.091
+57600/69092	Loss: 91.916
+60800/69092	Loss: 90.704
+64000/69092	Loss: 90.850
+67200/69092	Loss: 91.265
+Training time 0:09:26.807780
+Epoch: 222 Average loss: 91.42
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 496)
+0/69092	Loss: 89.271
+3200/69092	Loss: 92.420
+6400/69092	Loss: 90.450
+9600/69092	Loss: 92.155
+12800/69092	Loss: 90.594
+16000/69092	Loss: 89.982
+19200/69092	Loss: 91.262
+22400/69092	Loss: 91.691
+25600/69092	Loss: 93.615
+28800/69092	Loss: 92.190
+32000/69092	Loss: 91.231
+35200/69092	Loss: 90.893
+38400/69092	Loss: 90.571
+41600/69092	Loss: 92.117
+44800/69092	Loss: 90.486
+48000/69092	Loss: 92.205
+51200/69092	Loss: 91.111
+54400/69092	Loss: 91.993
+57600/69092	Loss: 90.869
+60800/69092	Loss: 91.939
+64000/69092	Loss: 91.235
+67200/69092	Loss: 91.504
+Training time 0:09:05.484379
+Epoch: 223 Average loss: 91.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 497)
+0/69092	Loss: 89.181
+3200/69092	Loss: 90.413
+6400/69092	Loss: 90.718
+9600/69092	Loss: 91.599
+12800/69092	Loss: 91.833
+16000/69092	Loss: 90.470
+19200/69092	Loss: 92.388
+22400/69092	Loss: 92.364
+25600/69092	Loss: 93.409
+28800/69092	Loss: 91.568
+32000/69092	Loss: 91.481
+35200/69092	Loss: 91.362
+38400/69092	Loss: 89.977
+41600/69092	Loss: 91.041
+44800/69092	Loss: 90.258
+48000/69092	Loss: 91.862
+51200/69092	Loss: 90.980
+54400/69092	Loss: 89.762
+57600/69092	Loss: 92.184
+60800/69092	Loss: 91.036
+64000/69092	Loss: 91.268
+67200/69092	Loss: 92.936
+Training time 0:09:04.440334
+Epoch: 224 Average loss: 91.36
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 498)
+0/69092	Loss: 91.026
+3200/69092	Loss: 91.255
+6400/69092	Loss: 91.719
+9600/69092	Loss: 91.157
+12800/69092	Loss: 92.406
+16000/69092	Loss: 91.583
+19200/69092	Loss: 91.929
+22400/69092	Loss: 90.688
+25600/69092	Loss: 92.398
+28800/69092	Loss: 91.607
+32000/69092	Loss: 91.711
+35200/69092	Loss: 90.678
+38400/69092	Loss: 91.806
+41600/69092	Loss: 91.460
+44800/69092	Loss: 90.860
+48000/69092	Loss: 93.146
+51200/69092	Loss: 90.785
+54400/69092	Loss: 91.771
+57600/69092	Loss: 91.671
+60800/69092	Loss: 90.313
+64000/69092	Loss: 90.619
+67200/69092	Loss: 91.646
+Training time 0:09:06.338469
+Epoch: 225 Average loss: 91.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 499)
+0/69092	Loss: 89.670
+3200/69092	Loss: 90.785
+6400/69092	Loss: 92.256
+9600/69092	Loss: 90.962
+12800/69092	Loss: 91.310
+16000/69092	Loss: 90.989
+19200/69092	Loss: 90.828
+22400/69092	Loss: 91.930
+25600/69092	Loss: 91.360
+28800/69092	Loss: 90.975
+32000/69092	Loss: 93.853
+35200/69092	Loss: 91.287
+38400/69092	Loss: 90.064
+41600/69092	Loss: 90.798
+44800/69092	Loss: 91.702
+48000/69092	Loss: 92.073
+51200/69092	Loss: 92.525
+54400/69092	Loss: 91.912
+57600/69092	Loss: 91.698
+60800/69092	Loss: 91.356
+64000/69092	Loss: 92.227
+67200/69092	Loss: 91.197
+Training time 0:09:20.758062
+Epoch: 226 Average loss: 91.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 500)
+0/69092	Loss: 94.209
+3200/69092	Loss: 90.273
+6400/69092	Loss: 91.390
+9600/69092	Loss: 90.108
+12800/69092	Loss: 92.401
+16000/69092	Loss: 91.664
+19200/69092	Loss: 90.982
+22400/69092	Loss: 92.526
+25600/69092	Loss: 92.870
+28800/69092	Loss: 90.755
+32000/69092	Loss: 91.740
+35200/69092	Loss: 90.622
+38400/69092	Loss: 90.655
+41600/69092	Loss: 92.257
+44800/69092	Loss: 91.149
+48000/69092	Loss: 91.351
+51200/69092	Loss: 91.690
+54400/69092	Loss: 91.563
+57600/69092	Loss: 91.349
+60800/69092	Loss: 90.898
+64000/69092	Loss: 93.412
+67200/69092	Loss: 91.794
+Training time 0:09:18.575249
+Epoch: 227 Average loss: 91.50
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 501)
+0/69092	Loss: 89.815
+3200/69092	Loss: 90.205
+6400/69092	Loss: 92.771
+9600/69092	Loss: 91.412
+12800/69092	Loss: 91.882
+16000/69092	Loss: 92.039
+19200/69092	Loss: 90.997
+22400/69092	Loss: 91.267
+25600/69092	Loss: 90.162
+28800/69092	Loss: 90.757
+32000/69092	Loss: 91.968
+35200/69092	Loss: 91.184
+38400/69092	Loss: 91.391
+41600/69092	Loss: 92.231
+44800/69092	Loss: 92.805
+48000/69092	Loss: 91.353
+51200/69092	Loss: 91.103
+54400/69092	Loss: 91.689
+57600/69092	Loss: 91.242
+60800/69092	Loss: 91.488
+64000/69092	Loss: 89.920
+67200/69092	Loss: 91.587
+Training time 0:09:11.332201
+Epoch: 228 Average loss: 91.42
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 502)
+0/69092	Loss: 97.890
+3200/69092	Loss: 90.488
+6400/69092	Loss: 90.414
+9600/69092	Loss: 91.751
+12800/69092	Loss: 90.765
+16000/69092	Loss: 91.700
+19200/69092	Loss: 90.633
+22400/69092	Loss: 91.844
+25600/69092	Loss: 91.076
+28800/69092	Loss: 91.281
+32000/69092	Loss: 92.061
+35200/69092	Loss: 90.002
+38400/69092	Loss: 92.285
+41600/69092	Loss: 91.231
+44800/69092	Loss: 91.473
+48000/69092	Loss: 92.521
+51200/69092	Loss: 91.218
+54400/69092	Loss: 92.007
+57600/69092	Loss: 91.683
+60800/69092	Loss: 91.943
+64000/69092	Loss: 90.460
+67200/69092	Loss: 92.123
+Training time 0:08:57.582498
+Epoch: 229 Average loss: 91.39
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 503)
+0/69092	Loss: 82.349
+3200/69092	Loss: 91.664
+6400/69092	Loss: 90.908
+9600/69092	Loss: 91.213
+12800/69092	Loss: 89.733
+16000/69092	Loss: 92.262
+19200/69092	Loss: 93.181
+22400/69092	Loss: 90.687
+25600/69092	Loss: 90.776
+28800/69092	Loss: 92.175
+32000/69092	Loss: 91.615
+35200/69092	Loss: 90.498
+38400/69092	Loss: 90.153
+41600/69092	Loss: 91.187
+44800/69092	Loss: 91.861
+48000/69092	Loss: 90.863
+51200/69092	Loss: 91.644
+54400/69092	Loss: 93.041
+57600/69092	Loss: 90.276
+60800/69092	Loss: 91.210
+64000/69092	Loss: 92.169
+67200/69092	Loss: 90.042
+Training time 0:09:17.600384
+Epoch: 230 Average loss: 91.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 504)
+0/69092	Loss: 91.827
+3200/69092	Loss: 90.411
+6400/69092	Loss: 90.648
+9600/69092	Loss: 91.059
+12800/69092	Loss: 91.310
+16000/69092	Loss: 91.963
+19200/69092	Loss: 92.521
+22400/69092	Loss: 89.598
+25600/69092	Loss: 90.726
+28800/69092	Loss: 92.736
+32000/69092	Loss: 91.885
+35200/69092	Loss: 91.264
+38400/69092	Loss: 90.551
+41600/69092	Loss: 91.847
+44800/69092	Loss: 90.194
+48000/69092	Loss: 91.781
+51200/69092	Loss: 93.145
+54400/69092	Loss: 91.810
+57600/69092	Loss: 91.763
+60800/69092	Loss: 91.025
+64000/69092	Loss: 91.372
+67200/69092	Loss: 91.085
+Training time 0:09:17.945246
+Epoch: 231 Average loss: 91.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last' (iter 505)
+0/69092	Loss: 86.150
+3200/69092	Loss: 91.619
+6400/69092	Loss: 91.922
+9600/69092	Loss: 91.481
+12800/69092	Loss: 91.698
+16000/69092	Loss: 91.638
diff --git a/OAR.2073645.stderr b/OAR.2073645.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..b800dbc96d0955b2893e858442aeea11bcc338e5
--- /dev/null
+++ b/OAR.2073645.stderr
@@ -0,0 +1,10 @@
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 417, in load_checkpoint
+    self.mean_epoch_loss = checkpoint['loss']
+KeyError: 'loss'
diff --git a/OAR.2073645.stdout b/OAR.2073645.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..e943950ae7124cf77d6991cee93fa200316bb8fb
--- /dev/null
+++ b/OAR.2073645.stdout
@@ -0,0 +1,46 @@
+Namespace(batch_size=256, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='beta_VAE_bs_256', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 765335
+don't use continuous capacity
diff --git a/OAR.2073646.stderr b/OAR.2073646.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..428f51beba791a9e4402d9e7e7cb048737a3ccb0
--- /dev/null
+++ b/OAR.2073646.stderr
@@ -0,0 +1,9 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py:26: UserWarning: 
+    There is an imbalance between your GPUs. You may want to exclude GPU 1 which
+    has less than 75% of the memory or cores of GPU 0. You can do so by setting
+    the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES
+    environment variable.
+  warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+## OAR [2020-07-06 14:09:39] Job 2073646 KILLED ##
diff --git a/OAR.2073646.stdout b/OAR.2073646.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..1f8a48422fb8bb6424673dc55a7a824ab234430e
--- /dev/null
+++ b/OAR.2073646.stdout
@@ -0,0 +1,3603 @@
+Namespace(batch_size=64, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='beta_VAE_bs_64', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+Tesla K40c
+Tesla K20m
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 765335
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last (iter 797)'
+0/69092	Loss: 142.832
+3200/69092	Loss: 151.428
+6400/69092	Loss: 154.939
+9600/69092	Loss: 150.255
+12800/69092	Loss: 152.961
+16000/69092	Loss: 151.128
+19200/69092	Loss: 150.601
+22400/69092	Loss: 151.621
+25600/69092	Loss: 151.453
+28800/69092	Loss: 151.952
+32000/69092	Loss: 150.342
+35200/69092	Loss: 152.334
+38400/69092	Loss: 152.996
+41600/69092	Loss: 154.452
+44800/69092	Loss: 149.559
+48000/69092	Loss: 152.127
+51200/69092	Loss: 150.600
+54400/69092	Loss: 152.427
+57600/69092	Loss: 152.343
+60800/69092	Loss: 151.399
+64000/69092	Loss: 151.713
+67200/69092	Loss: 151.581
+Training time 0:10:46.693358
+Epoch: 1 Average loss: 151.76
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 798)
+0/69092	Loss: 131.466
+3200/69092	Loss: 153.140
+6400/69092	Loss: 152.061
+9600/69092	Loss: 151.407
+12800/69092	Loss: 148.320
+16000/69092	Loss: 152.133
+19200/69092	Loss: 153.223
+22400/69092	Loss: 152.522
+25600/69092	Loss: 149.832
+28800/69092	Loss: 154.702
+32000/69092	Loss: 152.283
+35200/69092	Loss: 147.379
+38400/69092	Loss: 150.764
+41600/69092	Loss: 150.538
+44800/69092	Loss: 150.184
+48000/69092	Loss: 150.135
+51200/69092	Loss: 152.698
+54400/69092	Loss: 152.481
+57600/69092	Loss: 152.071
+60800/69092	Loss: 155.076
+64000/69092	Loss: 151.858
+67200/69092	Loss: 150.355
+Training time 0:07:52.566749
+Epoch: 2 Average loss: 151.58
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 799)
+0/69092	Loss: 153.552
+3200/69092	Loss: 151.396
+6400/69092	Loss: 154.249
+9600/69092	Loss: 152.852
+12800/69092	Loss: 151.672
+16000/69092	Loss: 153.207
+19200/69092	Loss: 151.788
+22400/69092	Loss: 150.910
+25600/69092	Loss: 150.622
+28800/69092	Loss: 149.125
+32000/69092	Loss: 150.276
+35200/69092	Loss: 152.476
+38400/69092	Loss: 151.409
+41600/69092	Loss: 152.512
+44800/69092	Loss: 151.830
+48000/69092	Loss: 153.252
+51200/69092	Loss: 148.425
+54400/69092	Loss: 153.022
+57600/69092	Loss: 151.896
+60800/69092	Loss: 151.356
+64000/69092	Loss: 150.920
+67200/69092	Loss: 150.466
+Training time 0:07:40.210971
+Epoch: 3 Average loss: 151.61
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 800)
+0/69092	Loss: 149.220
+3200/69092	Loss: 153.549
+6400/69092	Loss: 152.571
+9600/69092	Loss: 151.262
+12800/69092	Loss: 151.059
+16000/69092	Loss: 150.423
+19200/69092	Loss: 154.031
+22400/69092	Loss: 152.053
+25600/69092	Loss: 153.655
+28800/69092	Loss: 149.575
+32000/69092	Loss: 149.359
+35200/69092	Loss: 150.729
+38400/69092	Loss: 152.202
+41600/69092	Loss: 151.922
+44800/69092	Loss: 151.350
+48000/69092	Loss: 153.064
+51200/69092	Loss: 152.192
+54400/69092	Loss: 148.975
+57600/69092	Loss: 149.852
+60800/69092	Loss: 152.121
+64000/69092	Loss: 153.938
+67200/69092	Loss: 152.545
+Training time 0:07:35.708027
+Epoch: 4 Average loss: 151.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 801)
+0/69092	Loss: 147.088
+3200/69092	Loss: 154.065
+6400/69092	Loss: 149.628
+9600/69092	Loss: 149.559
+12800/69092	Loss: 151.099
+16000/69092	Loss: 154.106
+19200/69092	Loss: 149.777
+22400/69092	Loss: 150.702
+25600/69092	Loss: 154.616
+28800/69092	Loss: 149.317
+32000/69092	Loss: 152.851
+35200/69092	Loss: 153.567
+38400/69092	Loss: 151.744
+41600/69092	Loss: 149.520
+44800/69092	Loss: 148.214
+48000/69092	Loss: 151.462
+51200/69092	Loss: 151.701
+54400/69092	Loss: 150.467
+57600/69092	Loss: 149.840
+60800/69092	Loss: 151.528
+64000/69092	Loss: 151.747
+67200/69092	Loss: 152.380
+Training time 0:07:57.809355
+Epoch: 5 Average loss: 151.43
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 802)
+0/69092	Loss: 151.311
+3200/69092	Loss: 150.602
+6400/69092	Loss: 150.899
+9600/69092	Loss: 152.649
+12800/69092	Loss: 152.877
+16000/69092	Loss: 152.631
+19200/69092	Loss: 152.606
+22400/69092	Loss: 151.643
+25600/69092	Loss: 150.756
+28800/69092	Loss: 149.740
+32000/69092	Loss: 151.477
+35200/69092	Loss: 152.934
+38400/69092	Loss: 151.614
+41600/69092	Loss: 149.164
+44800/69092	Loss: 152.253
+48000/69092	Loss: 152.297
+51200/69092	Loss: 149.771
+54400/69092	Loss: 153.283
+57600/69092	Loss: 153.180
+60800/69092	Loss: 150.826
+64000/69092	Loss: 150.909
+67200/69092	Loss: 153.284
+Training time 0:07:30.752925
+Epoch: 6 Average loss: 151.62
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 803)
+0/69092	Loss: 155.523
+3200/69092	Loss: 152.202
+6400/69092	Loss: 151.890
+9600/69092	Loss: 154.005
+12800/69092	Loss: 152.243
+16000/69092	Loss: 150.647
+19200/69092	Loss: 149.749
+22400/69092	Loss: 149.702
+25600/69092	Loss: 150.467
+28800/69092	Loss: 151.769
+32000/69092	Loss: 149.260
+35200/69092	Loss: 152.489
+38400/69092	Loss: 153.783
+41600/69092	Loss: 154.698
+44800/69092	Loss: 150.038
+48000/69092	Loss: 150.720
+51200/69092	Loss: 152.133
+54400/69092	Loss: 151.531
+57600/69092	Loss: 150.957
+60800/69092	Loss: 151.272
+64000/69092	Loss: 150.041
+67200/69092	Loss: 152.465
+Training time 0:07:32.685306
+Epoch: 7 Average loss: 151.53
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 804)
+0/69092	Loss: 146.798
+3200/69092	Loss: 149.984
+6400/69092	Loss: 150.086
+9600/69092	Loss: 151.987
+12800/69092	Loss: 150.882
+16000/69092	Loss: 150.604
+19200/69092	Loss: 150.730
+22400/69092	Loss: 152.218
+25600/69092	Loss: 151.894
+28800/69092	Loss: 152.447
+32000/69092	Loss: 153.182
+35200/69092	Loss: 150.758
+38400/69092	Loss: 151.858
+41600/69092	Loss: 153.620
+44800/69092	Loss: 154.218
+48000/69092	Loss: 149.610
+51200/69092	Loss: 151.251
+54400/69092	Loss: 149.222
+57600/69092	Loss: 153.495
+60800/69092	Loss: 152.255
+64000/69092	Loss: 152.853
+67200/69092	Loss: 152.295
+Training time 0:07:35.505770
+Epoch: 8 Average loss: 151.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 805)
+0/69092	Loss: 160.319
+3200/69092	Loss: 152.974
+6400/69092	Loss: 150.695
+9600/69092	Loss: 150.355
+12800/69092	Loss: 150.285
+16000/69092	Loss: 150.416
+19200/69092	Loss: 151.078
+22400/69092	Loss: 154.285
+25600/69092	Loss: 151.172
+28800/69092	Loss: 151.029
+32000/69092	Loss: 151.973
+35200/69092	Loss: 154.305
+38400/69092	Loss: 151.517
+41600/69092	Loss: 150.787
+44800/69092	Loss: 150.841
+48000/69092	Loss: 153.113
+51200/69092	Loss: 149.988
+54400/69092	Loss: 151.136
+57600/69092	Loss: 151.874
+60800/69092	Loss: 151.309
+64000/69092	Loss: 152.939
+67200/69092	Loss: 152.066
+Training time 0:07:40.346530
+Epoch: 9 Average loss: 151.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 806)
+0/69092	Loss: 140.940
+3200/69092	Loss: 149.976
+6400/69092	Loss: 153.539
+9600/69092	Loss: 154.428
+12800/69092	Loss: 153.127
+16000/69092	Loss: 152.540
+19200/69092	Loss: 152.555
+22400/69092	Loss: 151.403
+25600/69092	Loss: 151.441
+28800/69092	Loss: 150.558
+32000/69092	Loss: 151.403
+35200/69092	Loss: 149.511
+38400/69092	Loss: 149.908
+41600/69092	Loss: 151.184
+44800/69092	Loss: 149.961
+48000/69092	Loss: 151.066
+51200/69092	Loss: 151.044
+54400/69092	Loss: 152.363
+57600/69092	Loss: 151.708
+60800/69092	Loss: 153.671
+64000/69092	Loss: 151.170
+67200/69092	Loss: 152.389
+Training time 0:07:37.483801
+Epoch: 10 Average loss: 151.58
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 807)
+0/69092	Loss: 159.772
+3200/69092	Loss: 151.655
+6400/69092	Loss: 152.404
+9600/69092	Loss: 152.278
+12800/69092	Loss: 153.847
+16000/69092	Loss: 151.843
+19200/69092	Loss: 151.602
+22400/69092	Loss: 153.643
+25600/69092	Loss: 148.815
+28800/69092	Loss: 151.932
+32000/69092	Loss: 150.882
+35200/69092	Loss: 148.644
+38400/69092	Loss: 150.872
+41600/69092	Loss: 151.482
+44800/69092	Loss: 150.188
+48000/69092	Loss: 151.897
+51200/69092	Loss: 148.668
+54400/69092	Loss: 152.283
+57600/69092	Loss: 151.700
+60800/69092	Loss: 153.371
+64000/69092	Loss: 152.254
+67200/69092	Loss: 152.654
+Training time 0:07:35.844384
+Epoch: 11 Average loss: 151.63
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 808)
+0/69092	Loss: 149.332
+3200/69092	Loss: 150.202
+6400/69092	Loss: 147.318
+9600/69092	Loss: 151.879
+12800/69092	Loss: 155.115
+16000/69092	Loss: 152.035
+19200/69092	Loss: 151.063
+22400/69092	Loss: 149.873
+25600/69092	Loss: 151.657
+28800/69092	Loss: 150.022
+32000/69092	Loss: 151.053
+35200/69092	Loss: 152.898
+38400/69092	Loss: 154.348
+41600/69092	Loss: 151.439
+44800/69092	Loss: 151.348
+48000/69092	Loss: 150.846
+51200/69092	Loss: 151.212
+54400/69092	Loss: 151.078
+57600/69092	Loss: 151.025
+60800/69092	Loss: 154.230
+64000/69092	Loss: 154.987
+67200/69092	Loss: 151.852
+Training time 0:07:37.224474
+Epoch: 12 Average loss: 151.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 809)
+0/69092	Loss: 138.583
+3200/69092	Loss: 153.194
+6400/69092	Loss: 152.075
+9600/69092	Loss: 150.860
+12800/69092	Loss: 148.227
+16000/69092	Loss: 150.734
+19200/69092	Loss: 149.018
+22400/69092	Loss: 153.552
+25600/69092	Loss: 152.421
+28800/69092	Loss: 151.671
+32000/69092	Loss: 152.167
+35200/69092	Loss: 151.276
+38400/69092	Loss: 152.898
+41600/69092	Loss: 152.320
+44800/69092	Loss: 152.869
+48000/69092	Loss: 151.612
+51200/69092	Loss: 148.819
+54400/69092	Loss: 150.429
+57600/69092	Loss: 153.729
+60800/69092	Loss: 151.637
+64000/69092	Loss: 151.642
+67200/69092	Loss: 149.629
+Training time 0:07:40.787807
+Epoch: 13 Average loss: 151.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 810)
+0/69092	Loss: 147.644
+3200/69092	Loss: 153.846
+6400/69092	Loss: 151.848
+9600/69092	Loss: 149.836
+12800/69092	Loss: 152.001
+16000/69092	Loss: 151.389
+19200/69092	Loss: 150.485
+22400/69092	Loss: 150.750
+25600/69092	Loss: 149.420
+28800/69092	Loss: 152.185
+32000/69092	Loss: 149.508
+35200/69092	Loss: 152.795
+38400/69092	Loss: 148.575
+41600/69092	Loss: 152.989
+44800/69092	Loss: 154.810
+48000/69092	Loss: 151.022
+51200/69092	Loss: 152.563
+54400/69092	Loss: 152.374
+57600/69092	Loss: 148.134
+60800/69092	Loss: 151.173
+64000/69092	Loss: 152.669
+67200/69092	Loss: 153.190
+Training time 0:07:45.114223
+Epoch: 14 Average loss: 151.52
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 811)
+0/69092	Loss: 141.849
+3200/69092	Loss: 152.143
+6400/69092	Loss: 153.037
+9600/69092	Loss: 152.729
+12800/69092	Loss: 150.901
+16000/69092	Loss: 153.110
+19200/69092	Loss: 151.586
+22400/69092	Loss: 152.629
+25600/69092	Loss: 150.923
+28800/69092	Loss: 151.909
+32000/69092	Loss: 152.531
+35200/69092	Loss: 153.017
+38400/69092	Loss: 149.319
+41600/69092	Loss: 151.842
+44800/69092	Loss: 150.922
+48000/69092	Loss: 149.904
+51200/69092	Loss: 149.914
+54400/69092	Loss: 154.381
+57600/69092	Loss: 150.180
+60800/69092	Loss: 149.407
+64000/69092	Loss: 152.661
+67200/69092	Loss: 151.762
+Training time 0:07:35.326505
+Epoch: 15 Average loss: 151.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 812)
+0/69092	Loss: 148.428
+3200/69092	Loss: 150.966
+6400/69092	Loss: 151.189
+9600/69092	Loss: 152.722
+12800/69092	Loss: 148.759
+16000/69092	Loss: 151.323
+19200/69092	Loss: 153.601
+22400/69092	Loss: 150.202
+25600/69092	Loss: 153.207
+28800/69092	Loss: 153.975
+32000/69092	Loss: 151.357
+35200/69092	Loss: 151.863
+38400/69092	Loss: 150.525
+41600/69092	Loss: 150.028
+44800/69092	Loss: 151.842
+48000/69092	Loss: 151.937
+51200/69092	Loss: 150.990
+54400/69092	Loss: 152.793
+57600/69092	Loss: 152.481
+60800/69092	Loss: 153.697
+64000/69092	Loss: 150.563
+67200/69092	Loss: 150.937
+Training time 0:07:52.454446
+Epoch: 16 Average loss: 151.56
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 813)
+0/69092	Loss: 165.051
+3200/69092	Loss: 152.356
+6400/69092	Loss: 151.707
+9600/69092	Loss: 152.731
+12800/69092	Loss: 148.486
+16000/69092	Loss: 151.790
+19200/69092	Loss: 152.862
+22400/69092	Loss: 151.890
+25600/69092	Loss: 152.049
+28800/69092	Loss: 149.456
+32000/69092	Loss: 151.685
+35200/69092	Loss: 154.041
+38400/69092	Loss: 148.235
+41600/69092	Loss: 154.044
+44800/69092	Loss: 149.114
+48000/69092	Loss: 152.398
+51200/69092	Loss: 148.419
+54400/69092	Loss: 149.442
+57600/69092	Loss: 152.814
+60800/69092	Loss: 152.266
+64000/69092	Loss: 149.424
+67200/69092	Loss: 151.552
+Training time 0:07:43.384686
+Epoch: 17 Average loss: 151.36
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 814)
+0/69092	Loss: 126.141
+3200/69092	Loss: 151.218
+6400/69092	Loss: 151.762
+9600/69092	Loss: 153.108
+12800/69092	Loss: 150.925
+16000/69092	Loss: 152.302
+19200/69092	Loss: 152.114
+22400/69092	Loss: 154.952
+25600/69092	Loss: 149.640
+28800/69092	Loss: 153.500
+32000/69092	Loss: 152.145
+35200/69092	Loss: 150.850
+38400/69092	Loss: 150.811
+41600/69092	Loss: 151.004
+44800/69092	Loss: 150.151
+48000/69092	Loss: 150.852
+51200/69092	Loss: 150.746
+54400/69092	Loss: 153.982
+57600/69092	Loss: 150.529
+60800/69092	Loss: 152.979
+64000/69092	Loss: 151.288
+67200/69092	Loss: 151.380
+Training time 0:07:34.996320
+Epoch: 18 Average loss: 151.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 815)
+0/69092	Loss: 172.651
+3200/69092	Loss: 153.101
+6400/69092	Loss: 153.456
+9600/69092	Loss: 150.571
+12800/69092	Loss: 149.409
+16000/69092	Loss: 151.089
+19200/69092	Loss: 154.176
+22400/69092	Loss: 148.249
+25600/69092	Loss: 150.918
+28800/69092	Loss: 151.937
+32000/69092	Loss: 151.031
+35200/69092	Loss: 150.894
+38400/69092	Loss: 151.705
+41600/69092	Loss: 153.474
+44800/69092	Loss: 151.484
+48000/69092	Loss: 148.892
+51200/69092	Loss: 151.000
+54400/69092	Loss: 153.309
+57600/69092	Loss: 150.007
+60800/69092	Loss: 152.490
+64000/69092	Loss: 151.719
+67200/69092	Loss: 152.703
+Training time 0:07:38.211483
+Epoch: 19 Average loss: 151.52
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 816)
+0/69092	Loss: 136.414
+3200/69092	Loss: 150.012
+6400/69092	Loss: 150.873
+9600/69092	Loss: 151.578
+12800/69092	Loss: 151.445
+16000/69092	Loss: 153.938
+19200/69092	Loss: 152.728
+22400/69092	Loss: 152.766
+25600/69092	Loss: 149.509
+28800/69092	Loss: 151.017
+32000/69092	Loss: 149.687
+35200/69092	Loss: 152.461
+38400/69092	Loss: 151.911
+41600/69092	Loss: 152.539
+44800/69092	Loss: 148.983
+48000/69092	Loss: 153.657
+51200/69092	Loss: 151.178
+54400/69092	Loss: 152.763
+57600/69092	Loss: 150.197
+60800/69092	Loss: 151.684
+64000/69092	Loss: 151.547
+67200/69092	Loss: 150.111
+Training time 0:07:31.339478
+Epoch: 20 Average loss: 151.44
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 817)
+0/69092	Loss: 143.900
+3200/69092	Loss: 151.848
+6400/69092	Loss: 152.165
+9600/69092	Loss: 150.452
+12800/69092	Loss: 152.078
+16000/69092	Loss: 152.112
+19200/69092	Loss: 151.913
+22400/69092	Loss: 149.455
+25600/69092	Loss: 150.123
+28800/69092	Loss: 152.930
+32000/69092	Loss: 151.828
+35200/69092	Loss: 152.006
+38400/69092	Loss: 150.040
+41600/69092	Loss: 151.655
+44800/69092	Loss: 151.215
+48000/69092	Loss: 152.819
+51200/69092	Loss: 150.766
+54400/69092	Loss: 152.408
+57600/69092	Loss: 149.854
+60800/69092	Loss: 151.033
+64000/69092	Loss: 151.729
+67200/69092	Loss: 152.009
+Training time 0:07:35.017780
+Epoch: 21 Average loss: 151.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 818)
+0/69092	Loss: 157.734
+3200/69092	Loss: 150.653
+6400/69092	Loss: 149.956
+9600/69092	Loss: 151.723
+12800/69092	Loss: 152.990
+16000/69092	Loss: 152.325
+19200/69092	Loss: 149.504
+22400/69092	Loss: 150.876
+25600/69092	Loss: 150.986
+28800/69092	Loss: 151.457
+32000/69092	Loss: 150.582
+35200/69092	Loss: 155.020
+38400/69092	Loss: 152.673
+41600/69092	Loss: 151.270
+44800/69092	Loss: 151.241
+48000/69092	Loss: 152.973
+51200/69092	Loss: 151.529
+54400/69092	Loss: 150.431
+57600/69092	Loss: 151.148
+60800/69092	Loss: 147.814
+64000/69092	Loss: 151.480
+67200/69092	Loss: 155.033
+Training time 0:07:40.380809
+Epoch: 22 Average loss: 151.54
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 819)
+0/69092	Loss: 155.389
+3200/69092	Loss: 150.793
+6400/69092	Loss: 152.988
+9600/69092	Loss: 148.746
+12800/69092	Loss: 152.022
+16000/69092	Loss: 153.037
+19200/69092	Loss: 152.275
+22400/69092	Loss: 151.229
+25600/69092	Loss: 151.761
+28800/69092	Loss: 150.749
+32000/69092	Loss: 152.514
+35200/69092	Loss: 152.362
+38400/69092	Loss: 149.450
+41600/69092	Loss: 151.644
+44800/69092	Loss: 150.395
+48000/69092	Loss: 151.387
+51200/69092	Loss: 149.469
+54400/69092	Loss: 153.230
+57600/69092	Loss: 152.747
+60800/69092	Loss: 149.452
+64000/69092	Loss: 152.556
+67200/69092	Loss: 154.979
+Training time 0:07:37.195908
+Epoch: 23 Average loss: 151.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 820)
+0/69092	Loss: 147.278
+3200/69092	Loss: 150.818
+6400/69092	Loss: 150.412
+9600/69092	Loss: 155.031
+12800/69092	Loss: 150.162
+16000/69092	Loss: 152.846
+19200/69092	Loss: 151.563
+22400/69092	Loss: 150.620
+25600/69092	Loss: 153.353
+28800/69092	Loss: 150.121
+32000/69092	Loss: 152.388
+35200/69092	Loss: 150.256
+38400/69092	Loss: 150.500
+41600/69092	Loss: 149.279
+44800/69092	Loss: 153.392
+48000/69092	Loss: 151.072
+51200/69092	Loss: 152.543
+54400/69092	Loss: 153.213
+57600/69092	Loss: 152.648
+60800/69092	Loss: 149.935
+64000/69092	Loss: 148.767
+67200/69092	Loss: 152.621
+Training time 0:07:34.708826
+Epoch: 24 Average loss: 151.46
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 821)
+0/69092	Loss: 142.904
+3200/69092	Loss: 150.181
+6400/69092	Loss: 150.047
+9600/69092	Loss: 151.204
+12800/69092	Loss: 153.292
+16000/69092	Loss: 152.787
+19200/69092	Loss: 150.105
+22400/69092	Loss: 150.024
+25600/69092	Loss: 150.287
+28800/69092	Loss: 150.240
+32000/69092	Loss: 151.663
+35200/69092	Loss: 152.149
+38400/69092	Loss: 152.479
+41600/69092	Loss: 155.239
+44800/69092	Loss: 150.795
+48000/69092	Loss: 148.347
+51200/69092	Loss: 152.913
+54400/69092	Loss: 152.134
+57600/69092	Loss: 152.681
+60800/69092	Loss: 151.110
+64000/69092	Loss: 152.178
+67200/69092	Loss: 152.020
+Training time 0:07:33.964920
+Epoch: 25 Average loss: 151.54
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 822)
+0/69092	Loss: 159.863
+3200/69092	Loss: 153.939
+6400/69092	Loss: 148.890
+9600/69092	Loss: 151.681
+12800/69092	Loss: 150.213
+16000/69092	Loss: 151.870
+19200/69092	Loss: 150.416
+22400/69092	Loss: 150.563
+25600/69092	Loss: 151.130
+28800/69092	Loss: 152.032
+32000/69092	Loss: 152.799
+35200/69092	Loss: 151.744
+38400/69092	Loss: 153.140
+41600/69092	Loss: 152.244
+44800/69092	Loss: 150.946
+48000/69092	Loss: 148.664
+51200/69092	Loss: 151.003
+54400/69092	Loss: 150.275
+57600/69092	Loss: 151.283
+60800/69092	Loss: 152.473
+64000/69092	Loss: 153.192
+67200/69092	Loss: 149.443
+Training time 0:07:45.012621
+Epoch: 26 Average loss: 151.36
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 823)
+0/69092	Loss: 141.299
+3200/69092	Loss: 151.075
+6400/69092	Loss: 152.108
+9600/69092	Loss: 149.469
+12800/69092	Loss: 152.957
+16000/69092	Loss: 153.685
+19200/69092	Loss: 150.958
+22400/69092	Loss: 151.207
+25600/69092	Loss: 154.237
+28800/69092	Loss: 151.630
+32000/69092	Loss: 152.125
+35200/69092	Loss: 150.062
+38400/69092	Loss: 150.619
+41600/69092	Loss: 151.156
+44800/69092	Loss: 151.004
+48000/69092	Loss: 150.362
+51200/69092	Loss: 149.012
+54400/69092	Loss: 153.539
+57600/69092	Loss: 151.311
+60800/69092	Loss: 151.837
+64000/69092	Loss: 154.029
+67200/69092	Loss: 153.095
+Training time 0:07:34.528430
+Epoch: 27 Average loss: 151.66
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 824)
+0/69092	Loss: 145.865
+3200/69092	Loss: 150.555
+6400/69092	Loss: 150.805
+9600/69092	Loss: 149.113
+12800/69092	Loss: 152.178
+16000/69092	Loss: 152.462
+19200/69092	Loss: 150.257
+22400/69092	Loss: 153.100
+25600/69092	Loss: 151.356
+28800/69092	Loss: 153.961
+32000/69092	Loss: 148.219
+35200/69092	Loss: 148.384
+38400/69092	Loss: 154.166
+41600/69092	Loss: 154.838
+44800/69092	Loss: 150.812
+48000/69092	Loss: 151.954
+51200/69092	Loss: 152.448
+54400/69092	Loss: 150.004
+57600/69092	Loss: 151.900
+60800/69092	Loss: 151.151
+64000/69092	Loss: 151.995
+67200/69092	Loss: 152.103
+Training time 0:07:39.083113
+Epoch: 28 Average loss: 151.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 825)
+0/69092	Loss: 150.216
+3200/69092	Loss: 151.561
+6400/69092	Loss: 155.378
+9600/69092	Loss: 153.434
+12800/69092	Loss: 152.985
+16000/69092	Loss: 150.476
+19200/69092	Loss: 152.858
+22400/69092	Loss: 151.955
+25600/69092	Loss: 151.650
+28800/69092	Loss: 149.985
+32000/69092	Loss: 150.730
+35200/69092	Loss: 152.483
+38400/69092	Loss: 148.704
+41600/69092	Loss: 150.577
+44800/69092	Loss: 153.234
+48000/69092	Loss: 151.425
+51200/69092	Loss: 151.968
+54400/69092	Loss: 151.549
+57600/69092	Loss: 151.721
+60800/69092	Loss: 152.422
+64000/69092	Loss: 151.836
+67200/69092	Loss: 148.307
+Training time 0:07:36.019182
+Epoch: 29 Average loss: 151.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 826)
+0/69092	Loss: 156.343
+3200/69092	Loss: 150.589
+6400/69092	Loss: 150.726
+9600/69092	Loss: 152.634
+12800/69092	Loss: 150.066
+16000/69092	Loss: 151.919
+19200/69092	Loss: 151.432
+22400/69092	Loss: 152.506
+25600/69092	Loss: 151.867
+28800/69092	Loss: 152.442
+32000/69092	Loss: 151.872
+35200/69092	Loss: 150.297
+38400/69092	Loss: 149.650
+41600/69092	Loss: 150.866
+44800/69092	Loss: 151.734
+48000/69092	Loss: 152.931
+51200/69092	Loss: 149.614
+54400/69092	Loss: 151.499
+57600/69092	Loss: 150.234
+60800/69092	Loss: 152.314
+64000/69092	Loss: 155.569
+67200/69092	Loss: 151.621
+Training time 0:07:33.470198
+Epoch: 30 Average loss: 151.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 827)
+0/69092	Loss: 155.492
+3200/69092	Loss: 153.382
+6400/69092	Loss: 151.534
+9600/69092	Loss: 150.828
+12800/69092	Loss: 153.038
+16000/69092	Loss: 151.518
+19200/69092	Loss: 151.304
+22400/69092	Loss: 150.959
+25600/69092	Loss: 150.637
+28800/69092	Loss: 151.818
+32000/69092	Loss: 151.033
+35200/69092	Loss: 152.163
+38400/69092	Loss: 153.237
+41600/69092	Loss: 151.388
+44800/69092	Loss: 151.100
+48000/69092	Loss: 150.104
+51200/69092	Loss: 154.188
+54400/69092	Loss: 154.144
+57600/69092	Loss: 150.934
+60800/69092	Loss: 151.874
+64000/69092	Loss: 151.437
+67200/69092	Loss: 150.266
+Training time 0:07:37.138291
+Epoch: 31 Average loss: 151.80
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 828)
+0/69092	Loss: 145.907
+3200/69092	Loss: 151.533
+6400/69092	Loss: 154.072
+9600/69092	Loss: 151.454
+12800/69092	Loss: 150.346
+16000/69092	Loss: 149.936
+19200/69092	Loss: 151.889
+22400/69092	Loss: 148.086
+25600/69092	Loss: 153.147
+28800/69092	Loss: 153.771
+32000/69092	Loss: 152.930
+35200/69092	Loss: 150.331
+38400/69092	Loss: 152.814
+41600/69092	Loss: 153.773
+44800/69092	Loss: 150.495
+48000/69092	Loss: 151.142
+51200/69092	Loss: 151.384
+54400/69092	Loss: 152.779
+57600/69092	Loss: 150.765
+60800/69092	Loss: 149.029
+64000/69092	Loss: 150.336
+67200/69092	Loss: 152.609
+Training time 0:07:35.584028
+Epoch: 32 Average loss: 151.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 829)
+0/69092	Loss: 131.127
+3200/69092	Loss: 152.275
+6400/69092	Loss: 153.022
+9600/69092	Loss: 150.722
+12800/69092	Loss: 149.923
+16000/69092	Loss: 150.498
+19200/69092	Loss: 150.895
+22400/69092	Loss: 152.347
+25600/69092	Loss: 151.595
+28800/69092	Loss: 150.419
+32000/69092	Loss: 153.956
+35200/69092	Loss: 153.850
+38400/69092	Loss: 151.821
+41600/69092	Loss: 151.555
+44800/69092	Loss: 152.504
+48000/69092	Loss: 152.158
+51200/69092	Loss: 148.888
+54400/69092	Loss: 149.542
+57600/69092	Loss: 149.583
+60800/69092	Loss: 151.856
+64000/69092	Loss: 150.854
+67200/69092	Loss: 153.969
+Training time 0:07:51.138900
+Epoch: 33 Average loss: 151.56
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 830)
+0/69092	Loss: 145.941
+3200/69092	Loss: 151.467
+6400/69092	Loss: 152.570
+9600/69092	Loss: 152.221
+12800/69092	Loss: 150.075
+16000/69092	Loss: 152.178
+19200/69092	Loss: 152.883
+22400/69092	Loss: 150.432
+25600/69092	Loss: 150.659
+28800/69092	Loss: 152.024
+32000/69092	Loss: 152.508
+35200/69092	Loss: 150.870
+38400/69092	Loss: 150.071
+41600/69092	Loss: 150.047
+44800/69092	Loss: 149.818
+48000/69092	Loss: 152.068
+51200/69092	Loss: 151.641
+54400/69092	Loss: 155.692
+57600/69092	Loss: 150.311
+60800/69092	Loss: 150.921
+64000/69092	Loss: 151.945
+67200/69092	Loss: 150.429
+Training time 0:07:48.640179
+Epoch: 34 Average loss: 151.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 831)
+0/69092	Loss: 129.463
+3200/69092	Loss: 152.059
+6400/69092	Loss: 149.939
+9600/69092	Loss: 151.276
+12800/69092	Loss: 153.012
+16000/69092	Loss: 150.880
+19200/69092	Loss: 150.761
+22400/69092	Loss: 153.611
+25600/69092	Loss: 150.532
+28800/69092	Loss: 155.550
+32000/69092	Loss: 152.714
+35200/69092	Loss: 151.665
+38400/69092	Loss: 150.973
+41600/69092	Loss: 151.548
+44800/69092	Loss: 152.894
+48000/69092	Loss: 152.537
+51200/69092	Loss: 151.179
+54400/69092	Loss: 153.387
+57600/69092	Loss: 147.593
+60800/69092	Loss: 149.746
+64000/69092	Loss: 149.527
+67200/69092	Loss: 151.966
+Training time 0:07:34.838033
+Epoch: 35 Average loss: 151.66
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 832)
+0/69092	Loss: 146.773
+3200/69092	Loss: 151.064
+6400/69092	Loss: 151.500
+9600/69092	Loss: 151.055
+12800/69092	Loss: 152.780
+16000/69092	Loss: 152.913
+19200/69092	Loss: 150.440
+22400/69092	Loss: 151.940
+25600/69092	Loss: 150.062
+28800/69092	Loss: 150.541
+32000/69092	Loss: 152.565
+35200/69092	Loss: 152.666
+38400/69092	Loss: 149.760
+41600/69092	Loss: 150.890
+44800/69092	Loss: 152.341
+48000/69092	Loss: 153.297
+51200/69092	Loss: 150.884
+54400/69092	Loss: 148.739
+57600/69092	Loss: 152.008
+60800/69092	Loss: 151.627
+64000/69092	Loss: 150.045
+67200/69092	Loss: 152.656
+Training time 0:07:35.291730
+Epoch: 36 Average loss: 151.47
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 833)
+0/69092	Loss: 146.509
+3200/69092	Loss: 150.445
+6400/69092	Loss: 151.660
+9600/69092	Loss: 153.585
+12800/69092	Loss: 150.631
+16000/69092	Loss: 152.061
+19200/69092	Loss: 151.235
+22400/69092	Loss: 153.355
+25600/69092	Loss: 148.362
+28800/69092	Loss: 150.806
+32000/69092	Loss: 151.053
+35200/69092	Loss: 150.152
+38400/69092	Loss: 148.463
+41600/69092	Loss: 151.203
+44800/69092	Loss: 154.476
+48000/69092	Loss: 155.432
+51200/69092	Loss: 152.111
+54400/69092	Loss: 153.823
+57600/69092	Loss: 154.021
+60800/69092	Loss: 149.723
+64000/69092	Loss: 152.438
+67200/69092	Loss: 149.385
+Training time 0:07:36.515783
+Epoch: 37 Average loss: 151.67
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 834)
+0/69092	Loss: 153.602
+3200/69092	Loss: 151.257
+6400/69092	Loss: 149.391
+9600/69092	Loss: 150.068
+12800/69092	Loss: 152.997
+16000/69092	Loss: 150.922
+19200/69092	Loss: 154.546
+22400/69092	Loss: 151.994
+25600/69092	Loss: 152.501
+28800/69092	Loss: 151.521
+32000/69092	Loss: 152.743
+35200/69092	Loss: 151.628
+38400/69092	Loss: 155.490
+41600/69092	Loss: 150.549
+44800/69092	Loss: 150.071
+48000/69092	Loss: 151.341
+51200/69092	Loss: 151.829
+54400/69092	Loss: 151.698
+57600/69092	Loss: 148.534
+60800/69092	Loss: 150.604
+64000/69092	Loss: 151.572
+67200/69092	Loss: 152.958
+Training time 0:07:34.411869
+Epoch: 38 Average loss: 151.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 835)
+0/69092	Loss: 161.981
+3200/69092	Loss: 152.470
+6400/69092	Loss: 151.932
+9600/69092	Loss: 152.589
+12800/69092	Loss: 151.797
+16000/69092	Loss: 149.790
+19200/69092	Loss: 152.149
+22400/69092	Loss: 151.319
+25600/69092	Loss: 152.050
+28800/69092	Loss: 152.242
+32000/69092	Loss: 149.891
+35200/69092	Loss: 152.207
+38400/69092	Loss: 154.751
+41600/69092	Loss: 151.576
+44800/69092	Loss: 149.018
+48000/69092	Loss: 152.876
+51200/69092	Loss: 149.972
+54400/69092	Loss: 152.175
+57600/69092	Loss: 153.034
+60800/69092	Loss: 148.984
+64000/69092	Loss: 148.672
+67200/69092	Loss: 153.463
+Training time 0:07:35.626440
+Epoch: 39 Average loss: 151.56
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 836)
+0/69092	Loss: 158.717
+3200/69092	Loss: 148.959
+6400/69092	Loss: 152.216
+9600/69092	Loss: 151.690
+12800/69092	Loss: 148.565
+16000/69092	Loss: 150.666
+19200/69092	Loss: 150.117
+22400/69092	Loss: 152.342
+25600/69092	Loss: 152.197
+28800/69092	Loss: 153.327
+32000/69092	Loss: 150.696
+35200/69092	Loss: 152.002
+38400/69092	Loss: 154.478
+41600/69092	Loss: 152.650
+44800/69092	Loss: 149.524
+48000/69092	Loss: 151.688
+51200/69092	Loss: 152.667
+54400/69092	Loss: 152.383
+57600/69092	Loss: 150.812
+60800/69092	Loss: 153.931
+64000/69092	Loss: 152.876
+67200/69092	Loss: 152.458
+Training time 0:07:45.286150
+Epoch: 40 Average loss: 151.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 837)
+0/69092	Loss: 162.840
+3200/69092	Loss: 151.954
+6400/69092	Loss: 151.287
+9600/69092	Loss: 150.269
+12800/69092	Loss: 152.269
+16000/69092	Loss: 149.740
+19200/69092	Loss: 154.775
+22400/69092	Loss: 149.637
+25600/69092	Loss: 151.240
+28800/69092	Loss: 149.026
+32000/69092	Loss: 151.486
+35200/69092	Loss: 151.374
+38400/69092	Loss: 152.272
+41600/69092	Loss: 152.155
+44800/69092	Loss: 156.598
+48000/69092	Loss: 151.002
+51200/69092	Loss: 151.720
+54400/69092	Loss: 149.406
+57600/69092	Loss: 149.929
+60800/69092	Loss: 149.740
+64000/69092	Loss: 152.415
+67200/69092	Loss: 152.816
+Training time 0:07:33.936036
+Epoch: 41 Average loss: 151.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 838)
+0/69092	Loss: 150.645
+3200/69092	Loss: 151.761
+6400/69092	Loss: 150.145
+9600/69092	Loss: 152.392
+12800/69092	Loss: 152.893
+16000/69092	Loss: 151.411
+19200/69092	Loss: 148.751
+22400/69092	Loss: 151.250
+25600/69092	Loss: 152.111
+28800/69092	Loss: 148.938
+32000/69092	Loss: 153.270
+35200/69092	Loss: 153.319
+38400/69092	Loss: 150.267
+41600/69092	Loss: 149.395
+44800/69092	Loss: 149.878
+48000/69092	Loss: 151.724
+51200/69092	Loss: 151.297
+54400/69092	Loss: 151.145
+57600/69092	Loss: 151.265
+60800/69092	Loss: 151.728
+64000/69092	Loss: 151.701
+67200/69092	Loss: 151.539
+Training time 0:07:55.005597
+Epoch: 42 Average loss: 151.24
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 839)
+0/69092	Loss: 183.931
+3200/69092	Loss: 151.163
+6400/69092	Loss: 152.234
+9600/69092	Loss: 151.751
+12800/69092	Loss: 152.093
+16000/69092	Loss: 152.687
+19200/69092	Loss: 151.363
+22400/69092	Loss: 151.641
+25600/69092	Loss: 153.672
+28800/69092	Loss: 150.082
+32000/69092	Loss: 151.247
+35200/69092	Loss: 152.237
+38400/69092	Loss: 151.965
+41600/69092	Loss: 150.709
+44800/69092	Loss: 149.321
+48000/69092	Loss: 152.310
+51200/69092	Loss: 152.118
+54400/69092	Loss: 148.331
+57600/69092	Loss: 149.578
+60800/69092	Loss: 150.470
+64000/69092	Loss: 152.448
+67200/69092	Loss: 153.658
+Training time 0:07:35.024454
+Epoch: 43 Average loss: 151.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 840)
+0/69092	Loss: 150.344
+3200/69092	Loss: 154.014
+6400/69092	Loss: 153.034
+9600/69092	Loss: 151.526
+12800/69092	Loss: 150.034
+16000/69092	Loss: 149.227
+19200/69092	Loss: 153.081
+22400/69092	Loss: 151.226
+25600/69092	Loss: 150.088
+28800/69092	Loss: 153.720
+32000/69092	Loss: 151.633
+35200/69092	Loss: 148.493
+38400/69092	Loss: 149.547
+41600/69092	Loss: 151.836
+44800/69092	Loss: 151.819
+48000/69092	Loss: 150.160
+51200/69092	Loss: 152.762
+54400/69092	Loss: 149.306
+57600/69092	Loss: 152.050
+60800/69092	Loss: 151.088
+64000/69092	Loss: 150.549
+67200/69092	Loss: 154.260
+Training time 0:07:34.248350
+Epoch: 44 Average loss: 151.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 841)
+0/69092	Loss: 155.962
+3200/69092	Loss: 152.279
+6400/69092	Loss: 153.646
+9600/69092	Loss: 150.635
+12800/69092	Loss: 150.855
+16000/69092	Loss: 146.692
+19200/69092	Loss: 151.541
+22400/69092	Loss: 150.950
+25600/69092	Loss: 149.900
+28800/69092	Loss: 151.448
+32000/69092	Loss: 151.423
+35200/69092	Loss: 152.091
+38400/69092	Loss: 152.075
+41600/69092	Loss: 150.752
+44800/69092	Loss: 149.251
+48000/69092	Loss: 154.978
+51200/69092	Loss: 148.872
+54400/69092	Loss: 151.395
+57600/69092	Loss: 150.361
+60800/69092	Loss: 151.489
+64000/69092	Loss: 154.696
+67200/69092	Loss: 154.022
+Training time 0:07:39.461431
+Epoch: 45 Average loss: 151.44
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 842)
+0/69092	Loss: 151.089
+3200/69092	Loss: 152.291
+6400/69092	Loss: 151.832
+9600/69092	Loss: 153.371
+12800/69092	Loss: 151.524
+16000/69092	Loss: 149.537
+19200/69092	Loss: 151.702
+22400/69092	Loss: 150.057
+25600/69092	Loss: 154.001
+28800/69092	Loss: 149.155
+32000/69092	Loss: 150.513
+35200/69092	Loss: 152.533
+38400/69092	Loss: 153.268
+41600/69092	Loss: 148.851
+44800/69092	Loss: 152.209
+48000/69092	Loss: 152.880
+51200/69092	Loss: 152.949
+54400/69092	Loss: 152.736
+57600/69092	Loss: 152.959
+60800/69092	Loss: 151.585
+64000/69092	Loss: 150.524
+67200/69092	Loss: 149.943
+Training time 0:07:39.102713
+Epoch: 46 Average loss: 151.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 843)
+0/69092	Loss: 146.557
+3200/69092	Loss: 149.225
+6400/69092	Loss: 150.049
+9600/69092	Loss: 150.623
+12800/69092	Loss: 152.907
+16000/69092	Loss: 153.392
+19200/69092	Loss: 151.544
+22400/69092	Loss: 151.809
+25600/69092	Loss: 152.952
+28800/69092	Loss: 151.328
+32000/69092	Loss: 152.578
+35200/69092	Loss: 151.836
+38400/69092	Loss: 152.135
+41600/69092	Loss: 152.685
+44800/69092	Loss: 151.322
+48000/69092	Loss: 150.688
+51200/69092	Loss: 151.443
+54400/69092	Loss: 153.286
+57600/69092	Loss: 149.521
+60800/69092	Loss: 150.660
+64000/69092	Loss: 152.052
+67200/69092	Loss: 151.998
+Training time 0:07:35.342869
+Epoch: 47 Average loss: 151.69
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 844)
+0/69092	Loss: 143.089
+3200/69092	Loss: 151.485
+6400/69092	Loss: 153.235
+9600/69092	Loss: 154.274
+12800/69092	Loss: 150.935
+16000/69092	Loss: 149.854
+19200/69092	Loss: 149.337
+22400/69092	Loss: 154.559
+25600/69092	Loss: 149.585
+28800/69092	Loss: 151.836
+32000/69092	Loss: 152.825
+35200/69092	Loss: 149.223
+38400/69092	Loss: 151.225
+41600/69092	Loss: 149.979
+44800/69092	Loss: 152.462
+48000/69092	Loss: 150.496
+51200/69092	Loss: 150.364
+54400/69092	Loss: 152.760
+57600/69092	Loss: 151.801
+60800/69092	Loss: 152.488
+64000/69092	Loss: 153.734
+67200/69092	Loss: 150.663
+Training time 0:07:49.695895
+Epoch: 48 Average loss: 151.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 845)
+0/69092	Loss: 155.660
+3200/69092	Loss: 150.560
+6400/69092	Loss: 150.629
+9600/69092	Loss: 152.177
+12800/69092	Loss: 151.549
+16000/69092	Loss: 151.071
+19200/69092	Loss: 148.713
+22400/69092	Loss: 150.422
+25600/69092	Loss: 152.487
+28800/69092	Loss: 151.357
+32000/69092	Loss: 154.991
+35200/69092	Loss: 150.415
+38400/69092	Loss: 150.284
+41600/69092	Loss: 151.071
+44800/69092	Loss: 154.770
+48000/69092	Loss: 152.408
+51200/69092	Loss: 152.929
+54400/69092	Loss: 151.278
+57600/69092	Loss: 150.417
+60800/69092	Loss: 150.844
+64000/69092	Loss: 151.480
+67200/69092	Loss: 150.186
+Training time 0:07:40.542448
+Epoch: 49 Average loss: 151.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 846)
+0/69092	Loss: 155.733
+3200/69092	Loss: 154.211
+6400/69092	Loss: 148.923
+9600/69092	Loss: 152.061
+12800/69092	Loss: 150.150
+16000/69092	Loss: 151.785
+19200/69092	Loss: 149.939
+22400/69092	Loss: 152.052
+25600/69092	Loss: 152.723
+28800/69092	Loss: 150.755
+32000/69092	Loss: 152.961
+35200/69092	Loss: 152.570
+38400/69092	Loss: 150.670
+41600/69092	Loss: 152.345
+44800/69092	Loss: 152.134
+48000/69092	Loss: 150.101
+51200/69092	Loss: 151.016
+54400/69092	Loss: 149.897
+57600/69092	Loss: 154.775
+60800/69092	Loss: 151.545
+64000/69092	Loss: 152.591
+67200/69092	Loss: 150.957
+Training time 0:07:38.406691
+Epoch: 50 Average loss: 151.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 847)
+0/69092	Loss: 140.377
+3200/69092	Loss: 150.537
+6400/69092	Loss: 151.419
+9600/69092	Loss: 152.083
+12800/69092	Loss: 151.928
+16000/69092	Loss: 150.602
+19200/69092	Loss: 152.386
+22400/69092	Loss: 154.785
+25600/69092	Loss: 151.679
+28800/69092	Loss: 150.657
+32000/69092	Loss: 152.711
+35200/69092	Loss: 151.516
+38400/69092	Loss: 149.067
+41600/69092	Loss: 149.770
+44800/69092	Loss: 153.697
+48000/69092	Loss: 152.634
+51200/69092	Loss: 153.059
+54400/69092	Loss: 152.175
+57600/69092	Loss: 153.382
+60800/69092	Loss: 148.785
+64000/69092	Loss: 150.690
+67200/69092	Loss: 150.496
+Training time 0:07:47.536340
+Epoch: 51 Average loss: 151.58
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 848)
+0/69092	Loss: 136.843
+3200/69092	Loss: 149.979
+6400/69092	Loss: 152.106
+9600/69092	Loss: 150.426
+12800/69092	Loss: 152.593
+16000/69092	Loss: 150.988
+19200/69092	Loss: 151.268
+22400/69092	Loss: 152.821
+25600/69092	Loss: 150.912
+28800/69092	Loss: 154.224
+32000/69092	Loss: 151.247
+35200/69092	Loss: 151.740
+38400/69092	Loss: 150.941
+41600/69092	Loss: 152.373
+44800/69092	Loss: 151.265
+48000/69092	Loss: 152.015
+51200/69092	Loss: 151.144
+54400/69092	Loss: 150.975
+57600/69092	Loss: 151.627
+60800/69092	Loss: 148.726
+64000/69092	Loss: 156.755
+67200/69092	Loss: 148.798
+Training time 0:07:58.776896
+Epoch: 52 Average loss: 151.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 849)
+0/69092	Loss: 140.561
+3200/69092	Loss: 150.403
+6400/69092	Loss: 155.091
+9600/69092	Loss: 151.266
+12800/69092	Loss: 151.431
+16000/69092	Loss: 153.583
+19200/69092	Loss: 150.372
+22400/69092	Loss: 153.775
+25600/69092	Loss: 149.314
+28800/69092	Loss: 150.687
+32000/69092	Loss: 150.352
+35200/69092	Loss: 149.310
+38400/69092	Loss: 150.123
+41600/69092	Loss: 153.417
+44800/69092	Loss: 152.001
+48000/69092	Loss: 151.352
+51200/69092	Loss: 151.352
+54400/69092	Loss: 150.156
+57600/69092	Loss: 151.690
+60800/69092	Loss: 150.803
+64000/69092	Loss: 154.677
+67200/69092	Loss: 151.108
+Training time 0:07:36.522039
+Epoch: 53 Average loss: 151.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 850)
+0/69092	Loss: 162.074
+3200/69092	Loss: 151.919
+6400/69092	Loss: 150.039
+9600/69092	Loss: 154.313
+12800/69092	Loss: 152.460
+16000/69092	Loss: 153.334
+19200/69092	Loss: 149.642
+22400/69092	Loss: 151.049
+25600/69092	Loss: 152.598
+28800/69092	Loss: 153.376
+32000/69092	Loss: 150.193
+35200/69092	Loss: 148.767
+38400/69092	Loss: 149.622
+41600/69092	Loss: 150.426
+44800/69092	Loss: 151.896
+48000/69092	Loss: 149.380
+51200/69092	Loss: 151.168
+54400/69092	Loss: 149.517
+57600/69092	Loss: 153.738
+60800/69092	Loss: 150.471
+64000/69092	Loss: 152.249
+67200/69092	Loss: 151.627
+Training time 0:07:38.594072
+Epoch: 54 Average loss: 151.36
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 851)
+0/69092	Loss: 148.631
+3200/69092	Loss: 151.909
+6400/69092	Loss: 153.851
+9600/69092	Loss: 151.910
+12800/69092	Loss: 153.049
+16000/69092	Loss: 151.858
+19200/69092	Loss: 151.358
+22400/69092	Loss: 149.659
+25600/69092	Loss: 151.006
+28800/69092	Loss: 151.739
+32000/69092	Loss: 149.778
+35200/69092	Loss: 150.882
+38400/69092	Loss: 151.412
+41600/69092	Loss: 152.538
+44800/69092	Loss: 151.463
+48000/69092	Loss: 152.800
+51200/69092	Loss: 152.533
+54400/69092	Loss: 149.130
+57600/69092	Loss: 151.907
+60800/69092	Loss: 148.845
+64000/69092	Loss: 151.295
+67200/69092	Loss: 153.621
+Training time 0:07:36.093060
+Epoch: 55 Average loss: 151.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 852)
+0/69092	Loss: 158.281
+3200/69092	Loss: 151.695
+6400/69092	Loss: 149.784
+9600/69092	Loss: 151.923
+12800/69092	Loss: 150.744
+16000/69092	Loss: 148.405
+19200/69092	Loss: 151.635
+22400/69092	Loss: 152.307
+25600/69092	Loss: 152.283
+28800/69092	Loss: 151.932
+32000/69092	Loss: 152.264
+35200/69092	Loss: 149.167
+38400/69092	Loss: 151.545
+41600/69092	Loss: 150.594
+44800/69092	Loss: 151.744
+48000/69092	Loss: 152.171
+51200/69092	Loss: 152.604
+54400/69092	Loss: 153.203
+57600/69092	Loss: 150.825
+60800/69092	Loss: 151.207
+64000/69092	Loss: 151.133
+67200/69092	Loss: 152.664
+Training time 0:07:38.075063
+Epoch: 56 Average loss: 151.42
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 853)
+0/69092	Loss: 163.182
+3200/69092	Loss: 151.793
+6400/69092	Loss: 151.067
+9600/69092	Loss: 154.832
+12800/69092	Loss: 148.680
+16000/69092	Loss: 152.565
+19200/69092	Loss: 151.734
+22400/69092	Loss: 150.807
+25600/69092	Loss: 152.454
+28800/69092	Loss: 150.769
+32000/69092	Loss: 150.016
+35200/69092	Loss: 153.698
+38400/69092	Loss: 149.397
+41600/69092	Loss: 151.375
+44800/69092	Loss: 152.518
+48000/69092	Loss: 150.920
+51200/69092	Loss: 152.198
+54400/69092	Loss: 151.408
+57600/69092	Loss: 150.845
+60800/69092	Loss: 151.092
+64000/69092	Loss: 150.236
+67200/69092	Loss: 151.326
+Training time 0:07:42.185598
+Epoch: 57 Average loss: 151.46
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 854)
+0/69092	Loss: 144.853
+3200/69092	Loss: 148.688
+6400/69092	Loss: 152.467
+9600/69092	Loss: 152.406
+12800/69092	Loss: 152.451
+16000/69092	Loss: 150.961
+19200/69092	Loss: 150.909
+22400/69092	Loss: 152.136
+25600/69092	Loss: 152.761
+28800/69092	Loss: 151.629
+32000/69092	Loss: 151.163
+35200/69092	Loss: 152.129
+38400/69092	Loss: 151.678
+41600/69092	Loss: 149.007
+44800/69092	Loss: 151.170
+48000/69092	Loss: 152.365
+51200/69092	Loss: 153.188
+54400/69092	Loss: 155.184
+57600/69092	Loss: 151.104
+60800/69092	Loss: 151.530
+64000/69092	Loss: 148.222
+67200/69092	Loss: 150.165
+Training time 0:07:39.779970
+Epoch: 58 Average loss: 151.47
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 855)
+0/69092	Loss: 153.227
+3200/69092	Loss: 151.947
+6400/69092	Loss: 152.006
+9600/69092	Loss: 153.038
+12800/69092	Loss: 153.663
+16000/69092	Loss: 152.115
+19200/69092	Loss: 150.457
+22400/69092	Loss: 151.314
+25600/69092	Loss: 149.759
+28800/69092	Loss: 153.268
+32000/69092	Loss: 152.711
+35200/69092	Loss: 147.877
+38400/69092	Loss: 152.865
+41600/69092	Loss: 149.362
+44800/69092	Loss: 151.283
+48000/69092	Loss: 150.177
+51200/69092	Loss: 152.851
+54400/69092	Loss: 151.225
+57600/69092	Loss: 150.886
+60800/69092	Loss: 150.500
+64000/69092	Loss: 152.566
+67200/69092	Loss: 151.522
+Training time 0:07:37.075589
+Epoch: 59 Average loss: 151.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 856)
+0/69092	Loss: 147.013
+3200/69092	Loss: 153.650
+6400/69092	Loss: 152.426
+9600/69092	Loss: 152.810
+12800/69092	Loss: 151.935
+16000/69092	Loss: 155.987
+19200/69092	Loss: 152.130
+22400/69092	Loss: 150.510
+25600/69092	Loss: 149.378
+28800/69092	Loss: 149.973
+32000/69092	Loss: 153.151
+35200/69092	Loss: 150.832
+38400/69092	Loss: 148.988
+41600/69092	Loss: 150.571
+44800/69092	Loss: 151.220
+48000/69092	Loss: 152.081
+51200/69092	Loss: 152.567
+54400/69092	Loss: 150.113
+57600/69092	Loss: 152.749
+60800/69092	Loss: 150.156
+64000/69092	Loss: 151.934
+67200/69092	Loss: 151.577
+Training time 0:07:36.800745
+Epoch: 60 Average loss: 151.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 857)
+0/69092	Loss: 150.134
+3200/69092	Loss: 150.763
+6400/69092	Loss: 153.411
+9600/69092	Loss: 152.628
+12800/69092	Loss: 150.582
+16000/69092	Loss: 150.822
+19200/69092	Loss: 153.413
+22400/69092	Loss: 151.991
+25600/69092	Loss: 150.710
+28800/69092	Loss: 153.838
+32000/69092	Loss: 149.281
+35200/69092	Loss: 148.797
+38400/69092	Loss: 153.284
+41600/69092	Loss: 151.293
+44800/69092	Loss: 152.779
+48000/69092	Loss: 148.917
+51200/69092	Loss: 151.181
+54400/69092	Loss: 149.702
+57600/69092	Loss: 150.129
+60800/69092	Loss: 152.238
+64000/69092	Loss: 151.912
+67200/69092	Loss: 153.346
+Training time 0:07:35.187880
+Epoch: 61 Average loss: 151.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 858)
+0/69092	Loss: 147.975
+3200/69092	Loss: 150.023
+6400/69092	Loss: 153.001
+9600/69092	Loss: 151.785
+12800/69092	Loss: 153.763
+16000/69092	Loss: 150.788
+19200/69092	Loss: 150.391
+22400/69092	Loss: 151.880
+25600/69092	Loss: 153.504
+28800/69092	Loss: 154.019
+32000/69092	Loss: 151.893
+35200/69092	Loss: 152.371
+38400/69092	Loss: 152.318
+41600/69092	Loss: 152.111
+44800/69092	Loss: 151.928
+48000/69092	Loss: 151.303
+51200/69092	Loss: 150.538
+54400/69092	Loss: 152.962
+57600/69092	Loss: 148.381
+60800/69092	Loss: 150.177
+64000/69092	Loss: 150.390
+67200/69092	Loss: 150.073
+Training time 0:07:32.187509
+Epoch: 62 Average loss: 151.61
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 859)
+0/69092	Loss: 169.056
+3200/69092	Loss: 148.712
+6400/69092	Loss: 148.413
+9600/69092	Loss: 150.207
+12800/69092	Loss: 152.430
+16000/69092	Loss: 152.445
+19200/69092	Loss: 152.584
+22400/69092	Loss: 149.667
+25600/69092	Loss: 154.336
+28800/69092	Loss: 147.804
+32000/69092	Loss: 149.177
+35200/69092	Loss: 150.044
+38400/69092	Loss: 151.559
+41600/69092	Loss: 155.681
+44800/69092	Loss: 152.565
+48000/69092	Loss: 151.673
+51200/69092	Loss: 153.146
+54400/69092	Loss: 152.596
+57600/69092	Loss: 150.351
+60800/69092	Loss: 151.416
+64000/69092	Loss: 152.239
+67200/69092	Loss: 151.553
+Training time 0:07:34.560857
+Epoch: 63 Average loss: 151.47
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 860)
+0/69092	Loss: 145.945
+3200/69092	Loss: 151.033
+6400/69092	Loss: 151.174
+9600/69092	Loss: 151.210
+12800/69092	Loss: 150.499
+16000/69092	Loss: 152.411
+19200/69092	Loss: 150.989
+22400/69092	Loss: 150.905
+25600/69092	Loss: 151.837
+28800/69092	Loss: 151.898
+32000/69092	Loss: 151.616
+35200/69092	Loss: 152.144
+38400/69092	Loss: 150.950
+41600/69092	Loss: 154.086
+44800/69092	Loss: 151.463
+48000/69092	Loss: 151.348
+51200/69092	Loss: 152.976
+54400/69092	Loss: 152.047
+57600/69092	Loss: 149.097
+60800/69092	Loss: 152.755
+64000/69092	Loss: 151.627
+67200/69092	Loss: 152.789
+Training time 0:07:56.579525
+Epoch: 64 Average loss: 151.66
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 861)
+0/69092	Loss: 146.176
+3200/69092	Loss: 148.223
+6400/69092	Loss: 149.564
+9600/69092	Loss: 151.475
+12800/69092	Loss: 149.558
+16000/69092	Loss: 151.422
+19200/69092	Loss: 154.957
+22400/69092	Loss: 150.334
+25600/69092	Loss: 152.287
+28800/69092	Loss: 151.307
+32000/69092	Loss: 149.633
+35200/69092	Loss: 152.780
+38400/69092	Loss: 152.389
+41600/69092	Loss: 149.597
+44800/69092	Loss: 152.851
+48000/69092	Loss: 150.653
+51200/69092	Loss: 152.210
+54400/69092	Loss: 152.172
+57600/69092	Loss: 153.998
+60800/69092	Loss: 154.679
+64000/69092	Loss: 151.385
+67200/69092	Loss: 151.006
+Training time 0:07:42.847622
+Epoch: 65 Average loss: 151.54
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 862)
+0/69092	Loss: 154.149
+3200/69092	Loss: 149.388
+6400/69092	Loss: 152.301
+9600/69092	Loss: 151.748
+12800/69092	Loss: 149.220
+16000/69092	Loss: 152.403
+19200/69092	Loss: 149.946
+22400/69092	Loss: 150.778
+25600/69092	Loss: 152.194
+28800/69092	Loss: 154.048
+32000/69092	Loss: 151.090
+35200/69092	Loss: 151.482
+38400/69092	Loss: 150.429
+41600/69092	Loss: 151.166
+44800/69092	Loss: 150.006
+48000/69092	Loss: 152.620
+51200/69092	Loss: 151.766
+54400/69092	Loss: 152.974
+57600/69092	Loss: 149.831
+60800/69092	Loss: 150.454
+64000/69092	Loss: 149.608
+67200/69092	Loss: 153.691
+Training time 0:07:37.368375
+Epoch: 66 Average loss: 151.28
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 863)
+0/69092	Loss: 151.393
+3200/69092	Loss: 151.296
+6400/69092	Loss: 147.542
+9600/69092	Loss: 151.600
+12800/69092	Loss: 152.295
+16000/69092	Loss: 151.298
+19200/69092	Loss: 152.330
+22400/69092	Loss: 153.543
+25600/69092	Loss: 153.862
+28800/69092	Loss: 152.523
+32000/69092	Loss: 153.246
+35200/69092	Loss: 153.467
+38400/69092	Loss: 151.394
+41600/69092	Loss: 149.819
+44800/69092	Loss: 150.496
+48000/69092	Loss: 150.882
+51200/69092	Loss: 152.111
+54400/69092	Loss: 150.156
+57600/69092	Loss: 153.272
+60800/69092	Loss: 150.958
+64000/69092	Loss: 151.789
+67200/69092	Loss: 150.645
+Training time 0:07:37.792409
+Epoch: 67 Average loss: 151.66
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 864)
+0/69092	Loss: 170.446
+3200/69092	Loss: 153.697
+6400/69092	Loss: 152.718
+9600/69092	Loss: 150.773
+12800/69092	Loss: 152.108
+16000/69092	Loss: 152.803
+19200/69092	Loss: 152.607
+22400/69092	Loss: 152.027
+25600/69092	Loss: 150.403
+28800/69092	Loss: 148.508
+32000/69092	Loss: 151.515
+35200/69092	Loss: 150.197
+38400/69092	Loss: 152.050
+41600/69092	Loss: 148.399
+44800/69092	Loss: 152.840
+48000/69092	Loss: 151.724
+51200/69092	Loss: 150.307
+54400/69092	Loss: 152.615
+57600/69092	Loss: 151.746
+60800/69092	Loss: 152.285
+64000/69092	Loss: 150.272
+67200/69092	Loss: 151.935
+Training time 0:07:42.186948
+Epoch: 68 Average loss: 151.61
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 865)
+0/69092	Loss: 155.991
+3200/69092	Loss: 152.881
+6400/69092	Loss: 150.641
+9600/69092	Loss: 153.638
+12800/69092	Loss: 151.079
+16000/69092	Loss: 150.153
+19200/69092	Loss: 150.928
+22400/69092	Loss: 148.706
+25600/69092	Loss: 152.960
+28800/69092	Loss: 149.290
+32000/69092	Loss: 150.741
+35200/69092	Loss: 150.429
+38400/69092	Loss: 152.109
+41600/69092	Loss: 151.485
+44800/69092	Loss: 153.924
+48000/69092	Loss: 150.636
+51200/69092	Loss: 154.407
+54400/69092	Loss: 151.364
+57600/69092	Loss: 153.029
+60800/69092	Loss: 150.284
+64000/69092	Loss: 150.788
+67200/69092	Loss: 153.225
+Training time 0:07:33.606851
+Epoch: 69 Average loss: 151.58
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 866)
+0/69092	Loss: 152.879
+3200/69092	Loss: 152.723
+6400/69092	Loss: 152.343
+9600/69092	Loss: 153.286
+12800/69092	Loss: 151.546
+16000/69092	Loss: 150.674
+19200/69092	Loss: 151.705
+22400/69092	Loss: 152.203
+25600/69092	Loss: 152.026
+28800/69092	Loss: 152.854
+32000/69092	Loss: 150.951
+35200/69092	Loss: 152.716
+38400/69092	Loss: 151.200
+41600/69092	Loss: 150.397
+44800/69092	Loss: 152.115
+48000/69092	Loss: 148.521
+51200/69092	Loss: 149.884
+54400/69092	Loss: 150.266
+57600/69092	Loss: 152.231
+60800/69092	Loss: 150.078
+64000/69092	Loss: 152.986
+67200/69092	Loss: 153.517
+Training time 0:07:37.050520
+Epoch: 70 Average loss: 151.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 867)
+0/69092	Loss: 149.063
+3200/69092	Loss: 152.799
+6400/69092	Loss: 153.356
+9600/69092	Loss: 149.920
+12800/69092	Loss: 149.809
+16000/69092	Loss: 154.313
+19200/69092	Loss: 152.109
+22400/69092	Loss: 151.976
+25600/69092	Loss: 151.311
+28800/69092	Loss: 151.980
+32000/69092	Loss: 152.076
+35200/69092	Loss: 152.732
+38400/69092	Loss: 152.986
+41600/69092	Loss: 150.907
+44800/69092	Loss: 148.753
+48000/69092	Loss: 150.983
+51200/69092	Loss: 149.974
+54400/69092	Loss: 149.888
+57600/69092	Loss: 149.023
+60800/69092	Loss: 151.059
+64000/69092	Loss: 149.782
+67200/69092	Loss: 150.526
+Training time 0:07:37.835208
+Epoch: 71 Average loss: 151.34
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 868)
+0/69092	Loss: 164.662
+3200/69092	Loss: 152.846
+6400/69092	Loss: 151.462
+9600/69092	Loss: 151.064
+12800/69092	Loss: 151.844
+16000/69092	Loss: 149.955
+19200/69092	Loss: 148.535
+22400/69092	Loss: 150.732
+25600/69092	Loss: 151.644
+28800/69092	Loss: 149.863
+32000/69092	Loss: 150.861
+35200/69092	Loss: 151.746
+38400/69092	Loss: 150.364
+41600/69092	Loss: 153.433
+44800/69092	Loss: 151.907
+48000/69092	Loss: 153.137
+51200/69092	Loss: 149.829
+54400/69092	Loss: 152.759
+57600/69092	Loss: 153.306
+60800/69092	Loss: 151.135
+64000/69092	Loss: 151.388
+67200/69092	Loss: 151.485
+Training time 0:07:38.297053
+Epoch: 72 Average loss: 151.43
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 869)
+0/69092	Loss: 157.771
+3200/69092	Loss: 151.041
+6400/69092	Loss: 150.920
+9600/69092	Loss: 152.116
+12800/69092	Loss: 151.117
+16000/69092	Loss: 150.886
+19200/69092	Loss: 153.310
+22400/69092	Loss: 151.706
+25600/69092	Loss: 150.601
+28800/69092	Loss: 150.425
+32000/69092	Loss: 150.411
+35200/69092	Loss: 148.931
+38400/69092	Loss: 154.019
+41600/69092	Loss: 152.004
+44800/69092	Loss: 151.884
+48000/69092	Loss: 149.600
+51200/69092	Loss: 152.308
+54400/69092	Loss: 152.061
+57600/69092	Loss: 148.121
+60800/69092	Loss: 152.427
+64000/69092	Loss: 152.344
+67200/69092	Loss: 152.203
+Training time 0:07:52.942758
+Epoch: 73 Average loss: 151.45
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 870)
+0/69092	Loss: 148.119
+3200/69092	Loss: 150.712
+6400/69092	Loss: 152.390
+9600/69092	Loss: 152.926
+12800/69092	Loss: 151.616
+16000/69092	Loss: 149.947
+19200/69092	Loss: 150.700
+22400/69092	Loss: 149.983
+25600/69092	Loss: 152.097
+28800/69092	Loss: 152.446
+32000/69092	Loss: 154.134
+35200/69092	Loss: 150.350
+38400/69092	Loss: 152.253
+41600/69092	Loss: 151.443
+44800/69092	Loss: 152.741
+48000/69092	Loss: 151.163
+51200/69092	Loss: 151.111
+54400/69092	Loss: 151.078
+57600/69092	Loss: 150.303
+60800/69092	Loss: 154.820
+64000/69092	Loss: 150.865
+67200/69092	Loss: 150.962
+Training time 0:07:35.776608
+Epoch: 74 Average loss: 151.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 871)
+0/69092	Loss: 147.972
+3200/69092	Loss: 148.852
+6400/69092	Loss: 152.856
+9600/69092	Loss: 150.040
+12800/69092	Loss: 147.537
+16000/69092	Loss: 153.254
+19200/69092	Loss: 152.623
+22400/69092	Loss: 150.306
+25600/69092	Loss: 152.989
+28800/69092	Loss: 152.159
+32000/69092	Loss: 154.063
+35200/69092	Loss: 152.573
+38400/69092	Loss: 151.725
+41600/69092	Loss: 151.475
+44800/69092	Loss: 150.166
+48000/69092	Loss: 155.101
+51200/69092	Loss: 151.782
+54400/69092	Loss: 152.329
+57600/69092	Loss: 149.719
+60800/69092	Loss: 152.479
+64000/69092	Loss: 149.745
+67200/69092	Loss: 150.588
+Training time 0:07:35.483603
+Epoch: 75 Average loss: 151.59
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 872)
+0/69092	Loss: 140.566
+3200/69092	Loss: 150.002
+6400/69092	Loss: 152.128
+9600/69092	Loss: 151.915
+12800/69092	Loss: 152.106
+16000/69092	Loss: 150.701
+19200/69092	Loss: 151.165
+22400/69092	Loss: 150.934
+25600/69092	Loss: 151.687
+28800/69092	Loss: 149.870
+32000/69092	Loss: 153.237
+35200/69092	Loss: 149.838
+38400/69092	Loss: 152.331
+41600/69092	Loss: 149.753
+44800/69092	Loss: 152.738
+48000/69092	Loss: 150.817
+51200/69092	Loss: 151.148
+54400/69092	Loss: 150.511
+57600/69092	Loss: 152.361
+60800/69092	Loss: 150.435
+64000/69092	Loss: 152.482
+67200/69092	Loss: 149.576
+Training time 0:07:40.647560
+Epoch: 76 Average loss: 151.31
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 873)
+0/69092	Loss: 175.019
+3200/69092	Loss: 153.450
+6400/69092	Loss: 152.658
+9600/69092	Loss: 152.091
+12800/69092	Loss: 150.961
+16000/69092	Loss: 152.048
+19200/69092	Loss: 154.208
+22400/69092	Loss: 148.509
+25600/69092	Loss: 152.884
+28800/69092	Loss: 148.494
+32000/69092	Loss: 150.876
+35200/69092	Loss: 150.145
+38400/69092	Loss: 151.725
+41600/69092	Loss: 150.463
+44800/69092	Loss: 153.040
+48000/69092	Loss: 151.438
+51200/69092	Loss: 151.968
+54400/69092	Loss: 148.669
+57600/69092	Loss: 152.886
+60800/69092	Loss: 153.448
+64000/69092	Loss: 150.613
+67200/69092	Loss: 151.963
+Training time 0:07:33.939496
+Epoch: 77 Average loss: 151.53
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 874)
+0/69092	Loss: 148.194
+3200/69092	Loss: 151.244
+6400/69092	Loss: 148.929
+9600/69092	Loss: 149.664
+12800/69092	Loss: 151.336
+16000/69092	Loss: 152.821
+19200/69092	Loss: 153.150
+22400/69092	Loss: 152.796
+25600/69092	Loss: 147.603
+28800/69092	Loss: 153.180
+32000/69092	Loss: 148.301
+35200/69092	Loss: 151.931
+38400/69092	Loss: 150.962
+41600/69092	Loss: 151.369
+44800/69092	Loss: 151.380
+48000/69092	Loss: 152.627
+51200/69092	Loss: 153.190
+54400/69092	Loss: 153.314
+57600/69092	Loss: 153.476
+60800/69092	Loss: 150.728
+64000/69092	Loss: 150.906
+67200/69092	Loss: 148.881
+Training time 0:07:57.715041
+Epoch: 78 Average loss: 151.25
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 875)
+0/69092	Loss: 146.389
+3200/69092	Loss: 152.284
+6400/69092	Loss: 150.465
+9600/69092	Loss: 150.060
+12800/69092	Loss: 150.105
+16000/69092	Loss: 150.448
+19200/69092	Loss: 153.003
+22400/69092	Loss: 154.831
+25600/69092	Loss: 153.177
+28800/69092	Loss: 148.600
+32000/69092	Loss: 151.578
+35200/69092	Loss: 150.732
+38400/69092	Loss: 149.679
+41600/69092	Loss: 152.871
+44800/69092	Loss: 151.491
+48000/69092	Loss: 152.220
+51200/69092	Loss: 151.054
+54400/69092	Loss: 153.449
+57600/69092	Loss: 153.129
+60800/69092	Loss: 150.026
+64000/69092	Loss: 149.647
+67200/69092	Loss: 151.158
+Training time 0:07:40.608221
+Epoch: 79 Average loss: 151.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 876)
+0/69092	Loss: 132.077
+3200/69092	Loss: 151.664
+6400/69092	Loss: 151.464
+9600/69092	Loss: 151.544
+12800/69092	Loss: 149.698
+16000/69092	Loss: 153.136
+19200/69092	Loss: 150.185
+22400/69092	Loss: 150.527
+25600/69092	Loss: 151.198
+28800/69092	Loss: 150.775
+32000/69092	Loss: 151.247
+35200/69092	Loss: 150.618
+38400/69092	Loss: 151.768
+41600/69092	Loss: 149.998
+44800/69092	Loss: 152.774
+48000/69092	Loss: 151.701
+51200/69092	Loss: 151.204
+54400/69092	Loss: 153.007
+57600/69092	Loss: 150.206
+60800/69092	Loss: 151.677
+64000/69092	Loss: 152.326
+67200/69092	Loss: 153.497
+Training time 0:07:38.716555
+Epoch: 80 Average loss: 151.46
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 877)
+0/69092	Loss: 155.279
+3200/69092	Loss: 152.674
+6400/69092	Loss: 152.262
+9600/69092	Loss: 152.250
+12800/69092	Loss: 149.598
+16000/69092	Loss: 153.996
+19200/69092	Loss: 149.634
+22400/69092	Loss: 153.440
+25600/69092	Loss: 150.359
+28800/69092	Loss: 152.092
+32000/69092	Loss: 151.356
+35200/69092	Loss: 148.492
+38400/69092	Loss: 152.233
+41600/69092	Loss: 150.583
+44800/69092	Loss: 150.103
+48000/69092	Loss: 150.627
+51200/69092	Loss: 152.497
+54400/69092	Loss: 149.655
+57600/69092	Loss: 152.860
+60800/69092	Loss: 152.174
+64000/69092	Loss: 151.200
+67200/69092	Loss: 153.268
+Training time 0:07:46.567610
+Epoch: 81 Average loss: 151.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 878)
+0/69092	Loss: 148.904
+3200/69092	Loss: 151.772
+6400/69092	Loss: 148.686
+9600/69092	Loss: 151.858
+12800/69092	Loss: 151.878
+16000/69092	Loss: 152.589
+19200/69092	Loss: 155.627
+22400/69092	Loss: 151.760
+25600/69092	Loss: 152.694
+28800/69092	Loss: 153.236
+32000/69092	Loss: 151.818
+35200/69092	Loss: 151.159
+38400/69092	Loss: 152.159
+41600/69092	Loss: 152.296
+44800/69092	Loss: 152.003
+48000/69092	Loss: 150.205
+51200/69092	Loss: 149.469
+54400/69092	Loss: 147.805
+57600/69092	Loss: 151.206
+60800/69092	Loss: 151.589
+64000/69092	Loss: 151.707
+67200/69092	Loss: 151.902
+Training time 0:07:37.600077
+Epoch: 82 Average loss: 151.59
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 879)
+0/69092	Loss: 164.760
+3200/69092	Loss: 150.540
+6400/69092	Loss: 150.227
+9600/69092	Loss: 152.567
+12800/69092	Loss: 153.974
+16000/69092	Loss: 147.926
+19200/69092	Loss: 153.066
+22400/69092	Loss: 155.024
+25600/69092	Loss: 151.530
+28800/69092	Loss: 149.971
+32000/69092	Loss: 153.349
+35200/69092	Loss: 149.885
+38400/69092	Loss: 150.838
+41600/69092	Loss: 153.046
+44800/69092	Loss: 153.558
+48000/69092	Loss: 152.719
+51200/69092	Loss: 153.469
+54400/69092	Loss: 149.714
+57600/69092	Loss: 150.189
+60800/69092	Loss: 149.686
+64000/69092	Loss: 153.459
+67200/69092	Loss: 151.777
+Training time 0:07:38.415977
+Epoch: 83 Average loss: 151.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 880)
+0/69092	Loss: 162.769
+3200/69092	Loss: 152.163
+6400/69092	Loss: 153.496
+9600/69092	Loss: 152.533
+12800/69092	Loss: 151.115
+16000/69092	Loss: 150.944
+19200/69092	Loss: 152.540
+22400/69092	Loss: 152.076
+25600/69092	Loss: 151.318
+28800/69092	Loss: 149.871
+32000/69092	Loss: 151.224
+35200/69092	Loss: 151.019
+38400/69092	Loss: 151.872
+41600/69092	Loss: 152.052
+44800/69092	Loss: 151.556
+48000/69092	Loss: 150.753
+51200/69092	Loss: 149.376
+54400/69092	Loss: 149.057
+57600/69092	Loss: 152.320
+60800/69092	Loss: 153.210
+64000/69092	Loss: 152.460
+67200/69092	Loss: 151.521
+Training time 0:07:33.711978
+Epoch: 84 Average loss: 151.47
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 881)
+0/69092	Loss: 141.111
+3200/69092	Loss: 151.446
+6400/69092	Loss: 150.608
+9600/69092	Loss: 150.939
+12800/69092	Loss: 152.575
+16000/69092	Loss: 150.781
+19200/69092	Loss: 152.780
+22400/69092	Loss: 152.547
+25600/69092	Loss: 149.345
+28800/69092	Loss: 153.721
+32000/69092	Loss: 153.068
+35200/69092	Loss: 149.089
+38400/69092	Loss: 151.671
+41600/69092	Loss: 150.596
+44800/69092	Loss: 153.497
+48000/69092	Loss: 148.934
+51200/69092	Loss: 149.873
+54400/69092	Loss: 151.871
+57600/69092	Loss: 151.323
+60800/69092	Loss: 150.910
+64000/69092	Loss: 153.238
+67200/69092	Loss: 151.919
+Training time 0:07:54.364856
+Epoch: 85 Average loss: 151.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 882)
+0/69092	Loss: 162.261
+3200/69092	Loss: 148.440
+6400/69092	Loss: 152.706
+9600/69092	Loss: 149.196
+12800/69092	Loss: 152.875
+16000/69092	Loss: 151.714
+19200/69092	Loss: 149.560
+22400/69092	Loss: 152.348
+25600/69092	Loss: 151.359
+28800/69092	Loss: 150.500
+32000/69092	Loss: 152.552
+35200/69092	Loss: 152.464
+38400/69092	Loss: 152.728
+41600/69092	Loss: 152.489
+44800/69092	Loss: 151.485
+48000/69092	Loss: 150.166
+51200/69092	Loss: 156.189
+54400/69092	Loss: 149.404
+57600/69092	Loss: 151.032
+60800/69092	Loss: 151.603
+64000/69092	Loss: 151.235
+67200/69092	Loss: 151.769
+Training time 0:07:39.289184
+Epoch: 86 Average loss: 151.53
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 883)
+0/69092	Loss: 176.861
+3200/69092	Loss: 152.551
+6400/69092	Loss: 149.110
+9600/69092	Loss: 154.435
+12800/69092	Loss: 149.980
+16000/69092	Loss: 149.305
+19200/69092	Loss: 153.687
+22400/69092	Loss: 152.641
+25600/69092	Loss: 150.999
+28800/69092	Loss: 149.878
+32000/69092	Loss: 151.861
+35200/69092	Loss: 151.251
+38400/69092	Loss: 150.109
+41600/69092	Loss: 152.600
+44800/69092	Loss: 152.776
+48000/69092	Loss: 150.123
+51200/69092	Loss: 151.485
+54400/69092	Loss: 152.279
+57600/69092	Loss: 149.676
+60800/69092	Loss: 151.028
+64000/69092	Loss: 151.030
+67200/69092	Loss: 151.203
+Training time 0:07:35.373838
+Epoch: 87 Average loss: 151.34
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 884)
+0/69092	Loss: 153.482
+3200/69092	Loss: 153.651
+6400/69092	Loss: 154.553
+9600/69092	Loss: 151.406
+12800/69092	Loss: 150.757
+16000/69092	Loss: 150.184
+19200/69092	Loss: 152.285
+22400/69092	Loss: 150.965
+25600/69092	Loss: 154.127
+28800/69092	Loss: 149.651
+32000/69092	Loss: 151.519
+35200/69092	Loss: 153.777
+38400/69092	Loss: 150.398
+41600/69092	Loss: 150.349
+44800/69092	Loss: 154.070
+48000/69092	Loss: 148.891
+51200/69092	Loss: 149.017
+54400/69092	Loss: 152.366
+57600/69092	Loss: 149.803
+60800/69092	Loss: 150.851
+64000/69092	Loss: 151.345
+67200/69092	Loss: 150.895
+Training time 0:07:50.131878
+Epoch: 88 Average loss: 151.53
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 885)
+0/69092	Loss: 143.799
+3200/69092	Loss: 148.467
+6400/69092	Loss: 150.767
+9600/69092	Loss: 151.863
+12800/69092	Loss: 150.831
+16000/69092	Loss: 151.992
+19200/69092	Loss: 149.041
+22400/69092	Loss: 151.428
+25600/69092	Loss: 155.027
+28800/69092	Loss: 148.773
+32000/69092	Loss: 151.724
+35200/69092	Loss: 151.577
+38400/69092	Loss: 151.777
+41600/69092	Loss: 154.385
+44800/69092	Loss: 151.314
+48000/69092	Loss: 152.915
+51200/69092	Loss: 151.027
+54400/69092	Loss: 153.338
+57600/69092	Loss: 151.407
+60800/69092	Loss: 151.961
+64000/69092	Loss: 152.864
+67200/69092	Loss: 150.913
+Training time 0:07:51.068566
+Epoch: 89 Average loss: 151.62
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 886)
+0/69092	Loss: 157.546
+3200/69092	Loss: 153.194
+6400/69092	Loss: 150.980
+9600/69092	Loss: 151.157
+12800/69092	Loss: 151.822
+16000/69092	Loss: 151.735
+19200/69092	Loss: 149.325
+22400/69092	Loss: 151.724
+25600/69092	Loss: 153.192
+28800/69092	Loss: 152.907
+32000/69092	Loss: 151.824
+35200/69092	Loss: 150.518
+38400/69092	Loss: 154.142
+41600/69092	Loss: 153.308
+44800/69092	Loss: 150.174
+48000/69092	Loss: 150.697
+51200/69092	Loss: 150.051
+54400/69092	Loss: 150.680
+57600/69092	Loss: 148.826
+60800/69092	Loss: 149.197
+64000/69092	Loss: 153.010
+67200/69092	Loss: 151.971
+Training time 0:07:51.080143
+Epoch: 90 Average loss: 151.40
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 887)
+0/69092	Loss: 159.020
+3200/69092	Loss: 150.331
+6400/69092	Loss: 154.572
+9600/69092	Loss: 150.962
+12800/69092	Loss: 152.509
+16000/69092	Loss: 150.354
+19200/69092	Loss: 150.918
+22400/69092	Loss: 150.014
+25600/69092	Loss: 152.484
+28800/69092	Loss: 152.718
+32000/69092	Loss: 149.829
+35200/69092	Loss: 152.499
+38400/69092	Loss: 151.121
+41600/69092	Loss: 151.080
+44800/69092	Loss: 151.831
+48000/69092	Loss: 151.317
+51200/69092	Loss: 152.472
+54400/69092	Loss: 151.541
+57600/69092	Loss: 149.862
+60800/69092	Loss: 151.022
+64000/69092	Loss: 150.477
+67200/69092	Loss: 152.143
+Training time 0:07:40.137377
+Epoch: 91 Average loss: 151.45
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 888)
+0/69092	Loss: 151.678
+3200/69092	Loss: 151.702
+6400/69092	Loss: 152.180
+9600/69092	Loss: 152.016
+12800/69092	Loss: 151.444
+16000/69092	Loss: 152.884
+19200/69092	Loss: 150.936
+22400/69092	Loss: 150.607
+25600/69092	Loss: 152.027
+28800/69092	Loss: 153.034
+32000/69092	Loss: 149.741
+35200/69092	Loss: 151.221
+38400/69092	Loss: 152.065
+41600/69092	Loss: 152.622
+44800/69092	Loss: 153.016
+48000/69092	Loss: 152.754
+51200/69092	Loss: 152.119
+54400/69092	Loss: 152.164
+57600/69092	Loss: 149.970
+60800/69092	Loss: 150.801
+64000/69092	Loss: 150.955
+67200/69092	Loss: 150.412
+Training time 0:07:52.897097
+Epoch: 92 Average loss: 151.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 889)
+0/69092	Loss: 163.479
+3200/69092	Loss: 150.120
+6400/69092	Loss: 150.210
+9600/69092	Loss: 151.268
+12800/69092	Loss: 151.710
+16000/69092	Loss: 151.681
+19200/69092	Loss: 152.679
+22400/69092	Loss: 152.099
+25600/69092	Loss: 147.713
+28800/69092	Loss: 152.231
+32000/69092	Loss: 152.320
+35200/69092	Loss: 154.435
+38400/69092	Loss: 149.799
+41600/69092	Loss: 149.733
+44800/69092	Loss: 152.707
+48000/69092	Loss: 153.996
+51200/69092	Loss: 152.315
+54400/69092	Loss: 151.434
+57600/69092	Loss: 151.247
+60800/69092	Loss: 150.553
+64000/69092	Loss: 152.636
+67200/69092	Loss: 150.287
+Training time 0:07:35.952629
+Epoch: 93 Average loss: 151.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 890)
+0/69092	Loss: 149.656
+3200/69092	Loss: 151.266
+6400/69092	Loss: 153.111
+9600/69092	Loss: 153.139
+12800/69092	Loss: 147.987
+16000/69092	Loss: 150.603
+19200/69092	Loss: 152.333
+22400/69092	Loss: 150.884
+25600/69092	Loss: 151.856
+28800/69092	Loss: 151.026
+32000/69092	Loss: 151.486
+35200/69092	Loss: 153.454
+38400/69092	Loss: 151.554
+41600/69092	Loss: 151.957
+44800/69092	Loss: 150.872
+48000/69092	Loss: 150.631
+51200/69092	Loss: 151.841
+54400/69092	Loss: 151.096
+57600/69092	Loss: 150.099
+60800/69092	Loss: 150.060
+64000/69092	Loss: 151.091
+67200/69092	Loss: 153.183
+Training time 0:07:34.815005
+Epoch: 94 Average loss: 151.43
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 891)
+0/69092	Loss: 146.697
+3200/69092	Loss: 151.784
+6400/69092	Loss: 149.451
+9600/69092	Loss: 152.945
+12800/69092	Loss: 149.684
+16000/69092	Loss: 149.272
+19200/69092	Loss: 154.081
+22400/69092	Loss: 150.217
+25600/69092	Loss: 153.595
+28800/69092	Loss: 149.243
+32000/69092	Loss: 151.404
+35200/69092	Loss: 151.538
+38400/69092	Loss: 152.753
+41600/69092	Loss: 151.557
+44800/69092	Loss: 151.340
+48000/69092	Loss: 152.216
+51200/69092	Loss: 151.222
+54400/69092	Loss: 149.355
+57600/69092	Loss: 153.309
+60800/69092	Loss: 152.917
+64000/69092	Loss: 151.826
+67200/69092	Loss: 150.871
+Training time 0:07:42.369064
+Epoch: 95 Average loss: 151.39
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 892)
+0/69092	Loss: 132.722
+3200/69092	Loss: 152.614
+6400/69092	Loss: 149.095
+9600/69092	Loss: 148.463
+12800/69092	Loss: 154.037
+16000/69092	Loss: 151.243
+19200/69092	Loss: 149.769
+22400/69092	Loss: 151.363
+25600/69092	Loss: 153.165
+28800/69092	Loss: 152.653
+32000/69092	Loss: 153.832
+35200/69092	Loss: 150.578
+38400/69092	Loss: 150.591
+41600/69092	Loss: 151.344
+44800/69092	Loss: 152.977
+48000/69092	Loss: 151.501
+51200/69092	Loss: 155.654
+54400/69092	Loss: 150.654
+57600/69092	Loss: 152.273
+60800/69092	Loss: 150.871
+64000/69092	Loss: 152.093
+67200/69092	Loss: 149.928
+Training time 0:07:40.563998
+Epoch: 96 Average loss: 151.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 893)
+0/69092	Loss: 158.394
+3200/69092	Loss: 151.229
+6400/69092	Loss: 151.547
+9600/69092	Loss: 149.583
+12800/69092	Loss: 151.756
+16000/69092	Loss: 152.531
+19200/69092	Loss: 150.526
+22400/69092	Loss: 149.856
+25600/69092	Loss: 153.197
+28800/69092	Loss: 152.801
+32000/69092	Loss: 151.376
+35200/69092	Loss: 149.091
+38400/69092	Loss: 153.837
+41600/69092	Loss: 150.527
+44800/69092	Loss: 151.316
+48000/69092	Loss: 151.643
+51200/69092	Loss: 151.929
+54400/69092	Loss: 150.770
+57600/69092	Loss: 151.318
+60800/69092	Loss: 150.065
+64000/69092	Loss: 150.733
+67200/69092	Loss: 153.145
+Training time 0:07:45.530033
+Epoch: 97 Average loss: 151.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 894)
+0/69092	Loss: 165.743
+3200/69092	Loss: 152.942
+6400/69092	Loss: 151.343
+9600/69092	Loss: 155.051
+12800/69092	Loss: 150.427
+16000/69092	Loss: 153.537
+19200/69092	Loss: 151.910
+22400/69092	Loss: 149.785
+25600/69092	Loss: 154.403
+28800/69092	Loss: 150.624
+32000/69092	Loss: 150.162
+35200/69092	Loss: 150.642
+38400/69092	Loss: 152.267
+41600/69092	Loss: 149.553
+44800/69092	Loss: 152.384
+48000/69092	Loss: 150.848
+51200/69092	Loss: 154.525
+54400/69092	Loss: 151.814
+57600/69092	Loss: 152.285
+60800/69092	Loss: 149.554
+64000/69092	Loss: 150.372
+67200/69092	Loss: 149.517
+Training time 0:07:41.393850
+Epoch: 98 Average loss: 151.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 895)
+0/69092	Loss: 148.125
+3200/69092	Loss: 152.650
+6400/69092	Loss: 154.048
+9600/69092	Loss: 154.121
+12800/69092	Loss: 149.044
+16000/69092	Loss: 149.968
+19200/69092	Loss: 152.629
+22400/69092	Loss: 151.965
+25600/69092	Loss: 151.777
+28800/69092	Loss: 151.206
+32000/69092	Loss: 150.733
+35200/69092	Loss: 153.568
+38400/69092	Loss: 151.080
+41600/69092	Loss: 149.641
+44800/69092	Loss: 151.921
+48000/69092	Loss: 151.333
+51200/69092	Loss: 149.293
+54400/69092	Loss: 151.745
+57600/69092	Loss: 151.967
+60800/69092	Loss: 148.697
+64000/69092	Loss: 152.313
+67200/69092	Loss: 152.915
+Training time 0:07:43.305919
+Epoch: 99 Average loss: 151.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 896)
+0/69092	Loss: 157.737
+3200/69092	Loss: 151.856
+6400/69092	Loss: 151.661
+9600/69092	Loss: 149.485
+12800/69092	Loss: 152.336
+16000/69092	Loss: 152.246
+19200/69092	Loss: 150.339
+22400/69092	Loss: 150.714
+25600/69092	Loss: 152.132
+28800/69092	Loss: 149.841
+32000/69092	Loss: 151.223
+35200/69092	Loss: 149.853
+38400/69092	Loss: 150.628
+41600/69092	Loss: 150.985
+44800/69092	Loss: 149.466
+48000/69092	Loss: 154.050
+51200/69092	Loss: 151.470
+54400/69092	Loss: 153.108
+57600/69092	Loss: 151.644
+60800/69092	Loss: 151.227
+64000/69092	Loss: 151.662
+67200/69092	Loss: 148.947
+Training time 0:07:43.103732
+Epoch: 100 Average loss: 151.30
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 897)
+0/69092	Loss: 139.435
+3200/69092	Loss: 151.818
+6400/69092	Loss: 151.119
+9600/69092	Loss: 151.283
+12800/69092	Loss: 151.404
+16000/69092	Loss: 153.324
+19200/69092	Loss: 152.203
+22400/69092	Loss: 150.871
+25600/69092	Loss: 151.851
+28800/69092	Loss: 152.013
+32000/69092	Loss: 151.537
+35200/69092	Loss: 153.320
+38400/69092	Loss: 150.302
+41600/69092	Loss: 151.758
+44800/69092	Loss: 151.733
+48000/69092	Loss: 153.290
+51200/69092	Loss: 152.065
+54400/69092	Loss: 146.482
+57600/69092	Loss: 152.299
+60800/69092	Loss: 152.533
+64000/69092	Loss: 150.166
+67200/69092	Loss: 150.168
+Training time 0:07:53.142403
+Epoch: 101 Average loss: 151.46
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 898)
+0/69092	Loss: 150.759
+3200/69092	Loss: 150.691
+6400/69092	Loss: 152.753
+9600/69092	Loss: 152.361
+12800/69092	Loss: 151.122
+16000/69092	Loss: 148.944
+19200/69092	Loss: 151.744
+22400/69092	Loss: 154.734
+25600/69092	Loss: 151.083
+28800/69092	Loss: 149.688
+32000/69092	Loss: 152.595
+35200/69092	Loss: 152.274
+38400/69092	Loss: 151.103
+41600/69092	Loss: 152.834
+44800/69092	Loss: 151.022
+48000/69092	Loss: 150.979
+51200/69092	Loss: 149.973
+54400/69092	Loss: 150.438
+57600/69092	Loss: 152.553
+60800/69092	Loss: 151.034
+64000/69092	Loss: 152.376
+67200/69092	Loss: 151.672
+Training time 0:07:37.514345
+Epoch: 102 Average loss: 151.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 899)
+0/69092	Loss: 177.508
+3200/69092	Loss: 152.606
+6400/69092	Loss: 152.283
+9600/69092	Loss: 148.295
+12800/69092	Loss: 151.339
+16000/69092	Loss: 153.645
+19200/69092	Loss: 151.798
+22400/69092	Loss: 153.114
+25600/69092	Loss: 152.247
+28800/69092	Loss: 152.481
+32000/69092	Loss: 151.484
+35200/69092	Loss: 151.385
+38400/69092	Loss: 149.273
+41600/69092	Loss: 148.435
+44800/69092	Loss: 149.123
+48000/69092	Loss: 152.659
+51200/69092	Loss: 152.627
+54400/69092	Loss: 153.370
+57600/69092	Loss: 149.766
+60800/69092	Loss: 149.074
+64000/69092	Loss: 149.879
+67200/69092	Loss: 150.215
+Training time 0:07:36.319376
+Epoch: 103 Average loss: 151.28
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 900)
+0/69092	Loss: 143.156
+3200/69092	Loss: 151.639
+6400/69092	Loss: 153.048
+9600/69092	Loss: 150.752
+12800/69092	Loss: 148.393
+16000/69092	Loss: 151.419
+19200/69092	Loss: 149.919
+22400/69092	Loss: 152.721
+25600/69092	Loss: 149.942
+28800/69092	Loss: 151.455
+32000/69092	Loss: 152.018
+35200/69092	Loss: 150.035
+38400/69092	Loss: 151.944
+41600/69092	Loss: 149.496
+44800/69092	Loss: 150.375
+48000/69092	Loss: 151.705
+51200/69092	Loss: 153.085
+54400/69092	Loss: 153.474
+57600/69092	Loss: 152.073
+60800/69092	Loss: 154.008
+64000/69092	Loss: 152.584
+67200/69092	Loss: 151.138
+Training time 0:07:56.406031
+Epoch: 104 Average loss: 151.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 901)
+0/69092	Loss: 165.233
+3200/69092	Loss: 151.321
+6400/69092	Loss: 153.195
+9600/69092	Loss: 150.820
+12800/69092	Loss: 150.396
+16000/69092	Loss: 152.134
+19200/69092	Loss: 150.121
+22400/69092	Loss: 153.466
+25600/69092	Loss: 152.980
+28800/69092	Loss: 153.869
+32000/69092	Loss: 151.198
+35200/69092	Loss: 151.766
+38400/69092	Loss: 150.067
+41600/69092	Loss: 150.087
+44800/69092	Loss: 151.755
+48000/69092	Loss: 152.414
+51200/69092	Loss: 151.720
+54400/69092	Loss: 150.343
+57600/69092	Loss: 148.168
+60800/69092	Loss: 150.746
+64000/69092	Loss: 151.576
+67200/69092	Loss: 150.761
+Training time 0:07:43.661213
+Epoch: 105 Average loss: 151.46
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 902)
+0/69092	Loss: 146.604
+3200/69092	Loss: 152.449
+6400/69092	Loss: 151.446
+9600/69092	Loss: 152.866
+12800/69092	Loss: 152.050
+16000/69092	Loss: 151.969
+19200/69092	Loss: 149.835
+22400/69092	Loss: 149.119
+25600/69092	Loss: 150.592
+28800/69092	Loss: 151.768
+32000/69092	Loss: 151.755
+35200/69092	Loss: 149.949
+38400/69092	Loss: 153.261
+41600/69092	Loss: 150.041
+44800/69092	Loss: 151.270
+48000/69092	Loss: 150.028
+51200/69092	Loss: 149.866
+54400/69092	Loss: 152.386
+57600/69092	Loss: 151.076
+60800/69092	Loss: 154.246
+64000/69092	Loss: 153.755
+67200/69092	Loss: 149.399
+Training time 0:07:35.772736
+Epoch: 106 Average loss: 151.44
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 903)
+0/69092	Loss: 146.718
+3200/69092	Loss: 154.045
+6400/69092	Loss: 151.719
+9600/69092	Loss: 150.495
+12800/69092	Loss: 151.347
+16000/69092	Loss: 147.822
+19200/69092	Loss: 151.888
+22400/69092	Loss: 152.787
+25600/69092	Loss: 150.599
+28800/69092	Loss: 151.054
+32000/69092	Loss: 151.965
+35200/69092	Loss: 151.209
+38400/69092	Loss: 150.557
+41600/69092	Loss: 152.109
+44800/69092	Loss: 151.280
+48000/69092	Loss: 151.640
+51200/69092	Loss: 151.572
+54400/69092	Loss: 152.225
+57600/69092	Loss: 149.797
+60800/69092	Loss: 148.725
+64000/69092	Loss: 150.581
+67200/69092	Loss: 152.225
+Training time 0:07:34.337732
+Epoch: 107 Average loss: 151.24
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 904)
+0/69092	Loss: 148.489
+3200/69092	Loss: 153.499
+6400/69092	Loss: 150.819
+9600/69092	Loss: 151.166
+12800/69092	Loss: 152.612
+16000/69092	Loss: 148.260
+19200/69092	Loss: 151.130
+22400/69092	Loss: 152.847
+25600/69092	Loss: 151.573
+28800/69092	Loss: 151.488
+32000/69092	Loss: 150.933
+35200/69092	Loss: 149.576
+38400/69092	Loss: 151.064
+41600/69092	Loss: 153.102
+44800/69092	Loss: 151.842
+48000/69092	Loss: 149.934
+51200/69092	Loss: 151.099
+54400/69092	Loss: 152.865
+57600/69092	Loss: 150.884
+60800/69092	Loss: 150.083
+64000/69092	Loss: 153.264
+67200/69092	Loss: 151.809
+Training time 0:07:42.232368
+Epoch: 108 Average loss: 151.35
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 905)
+0/69092	Loss: 151.527
+3200/69092	Loss: 150.381
+6400/69092	Loss: 151.409
+9600/69092	Loss: 152.144
+12800/69092	Loss: 150.401
+16000/69092	Loss: 149.757
+19200/69092	Loss: 152.949
+22400/69092	Loss: 151.044
+25600/69092	Loss: 149.624
+28800/69092	Loss: 151.317
+32000/69092	Loss: 151.304
+35200/69092	Loss: 152.259
+38400/69092	Loss: 153.894
+41600/69092	Loss: 152.094
+44800/69092	Loss: 151.369
+48000/69092	Loss: 150.070
+51200/69092	Loss: 152.494
+54400/69092	Loss: 151.574
+57600/69092	Loss: 152.465
+60800/69092	Loss: 152.010
+64000/69092	Loss: 150.174
+67200/69092	Loss: 150.667
+Training time 0:07:36.722938
+Epoch: 109 Average loss: 151.37
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 906)
+0/69092	Loss: 125.892
+3200/69092	Loss: 152.042
+6400/69092	Loss: 151.201
+9600/69092	Loss: 150.779
+12800/69092	Loss: 151.454
+16000/69092	Loss: 152.048
+19200/69092	Loss: 151.438
+22400/69092	Loss: 150.652
+25600/69092	Loss: 152.461
+28800/69092	Loss: 153.321
+32000/69092	Loss: 154.214
+35200/69092	Loss: 150.505
+38400/69092	Loss: 150.507
+41600/69092	Loss: 154.431
+44800/69092	Loss: 152.689
+48000/69092	Loss: 152.679
+51200/69092	Loss: 150.218
+54400/69092	Loss: 150.897
+57600/69092	Loss: 149.717
+60800/69092	Loss: 150.404
+64000/69092	Loss: 150.079
+67200/69092	Loss: 151.367
+Training time 0:07:44.129451
+Epoch: 110 Average loss: 151.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 907)
+0/69092	Loss: 147.243
+3200/69092	Loss: 152.565
+6400/69092	Loss: 149.439
+9600/69092	Loss: 151.038
+12800/69092	Loss: 151.094
+16000/69092	Loss: 149.406
+19200/69092	Loss: 149.134
+22400/69092	Loss: 151.980
+25600/69092	Loss: 153.981
+28800/69092	Loss: 153.876
+32000/69092	Loss: 154.702
+35200/69092	Loss: 149.567
+38400/69092	Loss: 150.614
+41600/69092	Loss: 150.392
+44800/69092	Loss: 149.862
+48000/69092	Loss: 150.744
+51200/69092	Loss: 151.150
+54400/69092	Loss: 150.578
+57600/69092	Loss: 153.044
+60800/69092	Loss: 154.562
+64000/69092	Loss: 152.086
+67200/69092	Loss: 150.764
+Training time 0:07:37.534872
+Epoch: 111 Average loss: 151.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 908)
+0/69092	Loss: 173.649
+3200/69092	Loss: 151.838
+6400/69092	Loss: 151.378
+9600/69092	Loss: 150.939
+12800/69092	Loss: 151.517
+16000/69092	Loss: 152.590
+19200/69092	Loss: 150.400
+22400/69092	Loss: 151.948
+25600/69092	Loss: 151.186
+28800/69092	Loss: 148.228
+32000/69092	Loss: 149.957
+35200/69092	Loss: 150.422
+38400/69092	Loss: 149.014
+41600/69092	Loss: 153.795
+44800/69092	Loss: 150.486
+48000/69092	Loss: 153.006
+51200/69092	Loss: 150.860
+54400/69092	Loss: 152.941
+57600/69092	Loss: 150.360
+60800/69092	Loss: 153.025
+64000/69092	Loss: 149.598
+67200/69092	Loss: 154.917
+Training time 0:07:45.409074
+Epoch: 112 Average loss: 151.45
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 909)
+0/69092	Loss: 149.609
+3200/69092	Loss: 150.810
+6400/69092	Loss: 150.274
+9600/69092	Loss: 150.584
+12800/69092	Loss: 151.060
+16000/69092	Loss: 150.193
+19200/69092	Loss: 152.068
+22400/69092	Loss: 150.325
+25600/69092	Loss: 151.293
+28800/69092	Loss: 152.517
+32000/69092	Loss: 152.809
+35200/69092	Loss: 152.860
+38400/69092	Loss: 153.586
+41600/69092	Loss: 150.560
+44800/69092	Loss: 153.344
+48000/69092	Loss: 149.599
+51200/69092	Loss: 151.207
+54400/69092	Loss: 153.610
+57600/69092	Loss: 149.566
+60800/69092	Loss: 149.413
+64000/69092	Loss: 151.353
+67200/69092	Loss: 153.570
+Training time 0:07:54.981671
+Epoch: 113 Average loss: 151.43
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 910)
+0/69092	Loss: 144.998
+3200/69092	Loss: 151.353
+6400/69092	Loss: 153.139
+9600/69092	Loss: 152.563
+12800/69092	Loss: 151.941
+16000/69092	Loss: 150.398
+19200/69092	Loss: 151.273
+22400/69092	Loss: 151.755
+25600/69092	Loss: 152.129
+28800/69092	Loss: 149.613
+32000/69092	Loss: 154.309
+35200/69092	Loss: 152.101
+38400/69092	Loss: 154.426
+41600/69092	Loss: 150.935
+44800/69092	Loss: 151.034
+48000/69092	Loss: 149.470
+51200/69092	Loss: 151.719
+54400/69092	Loss: 150.375
+57600/69092	Loss: 149.638
+60800/69092	Loss: 152.823
+64000/69092	Loss: 150.772
+67200/69092	Loss: 150.935
+Training time 0:07:33.264126
+Epoch: 114 Average loss: 151.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 911)
+0/69092	Loss: 142.994
+3200/69092	Loss: 153.644
+6400/69092	Loss: 151.376
+9600/69092	Loss: 150.338
+12800/69092	Loss: 150.488
+16000/69092	Loss: 153.243
+19200/69092	Loss: 151.167
+22400/69092	Loss: 151.611
+25600/69092	Loss: 149.909
+28800/69092	Loss: 150.841
+32000/69092	Loss: 151.587
+35200/69092	Loss: 152.647
+38400/69092	Loss: 151.409
+41600/69092	Loss: 152.997
+44800/69092	Loss: 152.912
+48000/69092	Loss: 151.887
+51200/69092	Loss: 150.695
+54400/69092	Loss: 152.019
+57600/69092	Loss: 151.228
+60800/69092	Loss: 150.380
+64000/69092	Loss: 150.044
+67200/69092	Loss: 149.774
+Training time 0:07:38.506687
+Epoch: 115 Average loss: 151.40
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 912)
+0/69092	Loss: 156.308
+3200/69092	Loss: 150.914
+6400/69092	Loss: 154.129
+9600/69092	Loss: 154.683
+12800/69092	Loss: 152.993
+16000/69092	Loss: 150.762
+19200/69092	Loss: 149.033
+22400/69092	Loss: 148.239
+25600/69092	Loss: 152.287
+28800/69092	Loss: 152.040
+32000/69092	Loss: 151.876
+35200/69092	Loss: 149.819
+38400/69092	Loss: 149.002
+41600/69092	Loss: 154.284
+44800/69092	Loss: 151.874
+48000/69092	Loss: 151.499
+51200/69092	Loss: 151.405
+54400/69092	Loss: 150.912
+57600/69092	Loss: 150.138
+60800/69092	Loss: 150.580
+64000/69092	Loss: 150.884
+67200/69092	Loss: 150.559
+Training time 0:07:38.096699
+Epoch: 116 Average loss: 151.30
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 913)
+0/69092	Loss: 141.612
+3200/69092	Loss: 149.199
+6400/69092	Loss: 152.284
+9600/69092	Loss: 149.168
+12800/69092	Loss: 149.723
+16000/69092	Loss: 151.776
+19200/69092	Loss: 152.113
+22400/69092	Loss: 150.250
+25600/69092	Loss: 152.536
+28800/69092	Loss: 153.413
+32000/69092	Loss: 154.031
+35200/69092	Loss: 151.454
+38400/69092	Loss: 149.730
+41600/69092	Loss: 152.665
+44800/69092	Loss: 151.905
+48000/69092	Loss: 151.106
+51200/69092	Loss: 151.221
+54400/69092	Loss: 151.693
+57600/69092	Loss: 152.620
+60800/69092	Loss: 150.047
+64000/69092	Loss: 150.633
+67200/69092	Loss: 149.653
+Training time 0:07:41.130272
+Epoch: 117 Average loss: 151.31
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 914)
+0/69092	Loss: 155.953
+3200/69092	Loss: 149.312
+6400/69092	Loss: 152.249
+9600/69092	Loss: 151.618
+12800/69092	Loss: 151.824
+16000/69092	Loss: 150.747
+19200/69092	Loss: 150.063
+22400/69092	Loss: 149.770
+25600/69092	Loss: 152.689
+28800/69092	Loss: 153.044
+32000/69092	Loss: 153.086
+35200/69092	Loss: 152.088
+38400/69092	Loss: 150.299
+41600/69092	Loss: 152.036
+44800/69092	Loss: 152.260
+48000/69092	Loss: 147.098
+51200/69092	Loss: 153.311
+54400/69092	Loss: 150.711
+57600/69092	Loss: 150.065
+60800/69092	Loss: 151.125
+64000/69092	Loss: 152.485
+67200/69092	Loss: 152.314
+Training time 0:07:37.825595
+Epoch: 118 Average loss: 151.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 915)
+0/69092	Loss: 148.051
+3200/69092	Loss: 154.283
+6400/69092	Loss: 151.714
+9600/69092	Loss: 150.922
+12800/69092	Loss: 152.883
+16000/69092	Loss: 153.030
+19200/69092	Loss: 151.173
+22400/69092	Loss: 152.366
+25600/69092	Loss: 149.495
+28800/69092	Loss: 148.783
+32000/69092	Loss: 154.459
+35200/69092	Loss: 152.983
+38400/69092	Loss: 150.659
+41600/69092	Loss: 153.003
+44800/69092	Loss: 151.932
+48000/69092	Loss: 152.443
+51200/69092	Loss: 149.858
+54400/69092	Loss: 149.497
+57600/69092	Loss: 150.831
+60800/69092	Loss: 150.863
+64000/69092	Loss: 151.705
+67200/69092	Loss: 151.566
+Training time 0:07:44.524489
+Epoch: 119 Average loss: 151.61
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 916)
+0/69092	Loss: 142.340
+3200/69092	Loss: 149.670
+6400/69092	Loss: 152.443
+9600/69092	Loss: 150.113
+12800/69092	Loss: 147.185
+16000/69092	Loss: 150.174
+19200/69092	Loss: 152.503
+22400/69092	Loss: 150.977
+25600/69092	Loss: 150.322
+28800/69092	Loss: 153.315
+32000/69092	Loss: 152.230
+35200/69092	Loss: 152.723
+38400/69092	Loss: 151.079
+41600/69092	Loss: 154.848
+44800/69092	Loss: 149.747
+48000/69092	Loss: 152.488
+51200/69092	Loss: 151.711
+54400/69092	Loss: 153.382
+57600/69092	Loss: 152.753
+60800/69092	Loss: 153.032
+64000/69092	Loss: 150.018
+67200/69092	Loss: 149.703
+Training time 0:07:40.885898
+Epoch: 120 Average loss: 151.47
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 917)
+0/69092	Loss: 164.281
+3200/69092	Loss: 151.590
+6400/69092	Loss: 151.736
+9600/69092	Loss: 151.577
+12800/69092	Loss: 150.526
+16000/69092	Loss: 153.429
+19200/69092	Loss: 151.341
+22400/69092	Loss: 154.072
+25600/69092	Loss: 152.463
+28800/69092	Loss: 149.213
+32000/69092	Loss: 149.914
+35200/69092	Loss: 151.247
+38400/69092	Loss: 151.235
+41600/69092	Loss: 150.678
+44800/69092	Loss: 150.713
+48000/69092	Loss: 151.425
+51200/69092	Loss: 151.093
+54400/69092	Loss: 152.958
+57600/69092	Loss: 149.996
+60800/69092	Loss: 150.891
+64000/69092	Loss: 151.416
+67200/69092	Loss: 151.186
+Training time 0:07:40.110124
+Epoch: 121 Average loss: 151.44
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 918)
+0/69092	Loss: 151.546
+3200/69092	Loss: 154.108
+6400/69092	Loss: 150.318
+9600/69092	Loss: 153.542
+12800/69092	Loss: 150.893
+16000/69092	Loss: 151.538
+19200/69092	Loss: 151.993
+22400/69092	Loss: 149.791
+25600/69092	Loss: 153.092
+28800/69092	Loss: 153.002
+32000/69092	Loss: 150.149
+35200/69092	Loss: 150.776
+38400/69092	Loss: 151.102
+41600/69092	Loss: 155.553
+44800/69092	Loss: 151.075
+48000/69092	Loss: 151.019
+51200/69092	Loss: 149.472
+54400/69092	Loss: 150.907
+57600/69092	Loss: 147.349
+60800/69092	Loss: 150.102
+64000/69092	Loss: 151.381
+67200/69092	Loss: 151.375
+Training time 0:07:40.865243
+Epoch: 122 Average loss: 151.39
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 919)
+0/69092	Loss: 153.755
+3200/69092	Loss: 152.052
+6400/69092	Loss: 151.914
+9600/69092	Loss: 150.326
+12800/69092	Loss: 152.523
+16000/69092	Loss: 149.649
+19200/69092	Loss: 152.185
+22400/69092	Loss: 150.844
+25600/69092	Loss: 151.141
+28800/69092	Loss: 153.327
+32000/69092	Loss: 152.586
+35200/69092	Loss: 153.870
+38400/69092	Loss: 148.910
+41600/69092	Loss: 149.012
+44800/69092	Loss: 152.260
+48000/69092	Loss: 152.266
+51200/69092	Loss: 151.286
+54400/69092	Loss: 150.506
+57600/69092	Loss: 152.536
+60800/69092	Loss: 150.690
+64000/69092	Loss: 150.083
+67200/69092	Loss: 151.849
+Training time 0:07:48.615941
+Epoch: 123 Average loss: 151.38
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 920)
+0/69092	Loss: 153.725
+3200/69092	Loss: 152.735
+6400/69092	Loss: 150.295
+9600/69092	Loss: 150.218
+12800/69092	Loss: 150.871
+16000/69092	Loss: 148.731
+19200/69092	Loss: 149.065
+22400/69092	Loss: 148.538
+25600/69092	Loss: 151.412
+28800/69092	Loss: 151.277
+32000/69092	Loss: 151.501
+35200/69092	Loss: 152.738
+38400/69092	Loss: 155.225
+41600/69092	Loss: 153.449
+44800/69092	Loss: 149.839
+48000/69092	Loss: 152.095
+51200/69092	Loss: 151.263
+54400/69092	Loss: 150.984
+57600/69092	Loss: 154.250
+60800/69092	Loss: 149.270
+64000/69092	Loss: 151.713
+67200/69092	Loss: 150.166
+Training time 0:07:40.258479
+Epoch: 124 Average loss: 151.18
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 921)
+0/69092	Loss: 142.312
+3200/69092	Loss: 149.601
+6400/69092	Loss: 153.045
+9600/69092	Loss: 154.507
+12800/69092	Loss: 152.208
+16000/69092	Loss: 151.183
+19200/69092	Loss: 151.878
+22400/69092	Loss: 152.822
+25600/69092	Loss: 152.257
+28800/69092	Loss: 149.383
+32000/69092	Loss: 153.064
+35200/69092	Loss: 150.889
+38400/69092	Loss: 150.712
+41600/69092	Loss: 150.904
+44800/69092	Loss: 150.949
+48000/69092	Loss: 151.822
+51200/69092	Loss: 152.137
+54400/69092	Loss: 151.709
+57600/69092	Loss: 152.184
+60800/69092	Loss: 150.664
+64000/69092	Loss: 150.333
+67200/69092	Loss: 153.974
+Training time 0:07:39.217246
+Epoch: 125 Average loss: 151.69
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 922)
+0/69092	Loss: 159.935
+3200/69092	Loss: 150.666
+6400/69092	Loss: 151.595
+9600/69092	Loss: 150.919
+12800/69092	Loss: 152.729
+16000/69092	Loss: 151.851
+19200/69092	Loss: 152.421
+22400/69092	Loss: 153.180
+25600/69092	Loss: 152.496
+28800/69092	Loss: 151.596
+32000/69092	Loss: 150.062
+35200/69092	Loss: 149.879
+38400/69092	Loss: 150.485
+41600/69092	Loss: 149.738
+44800/69092	Loss: 150.755
+48000/69092	Loss: 150.068
+51200/69092	Loss: 152.259
+54400/69092	Loss: 151.634
+57600/69092	Loss: 152.558
+60800/69092	Loss: 151.090
+64000/69092	Loss: 149.036
+67200/69092	Loss: 152.283
+Training time 0:07:40.821096
+Epoch: 126 Average loss: 151.31
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 923)
+0/69092	Loss: 133.395
+3200/69092	Loss: 151.205
+6400/69092	Loss: 153.174
+9600/69092	Loss: 152.048
+12800/69092	Loss: 150.364
+16000/69092	Loss: 149.779
+19200/69092	Loss: 151.923
+22400/69092	Loss: 151.112
+25600/69092	Loss: 151.557
+28800/69092	Loss: 151.695
+32000/69092	Loss: 151.893
+35200/69092	Loss: 153.473
+38400/69092	Loss: 150.701
+41600/69092	Loss: 148.429
+44800/69092	Loss: 152.116
+48000/69092	Loss: 150.101
+51200/69092	Loss: 149.370
+54400/69092	Loss: 152.866
+57600/69092	Loss: 151.995
+60800/69092	Loss: 149.668
+64000/69092	Loss: 149.759
+67200/69092	Loss: 153.295
+Training time 0:07:33.827181
+Epoch: 127 Average loss: 151.27
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 924)
+0/69092	Loss: 139.178
+3200/69092	Loss: 152.090
+6400/69092	Loss: 150.405
+9600/69092	Loss: 150.435
+12800/69092	Loss: 154.370
+16000/69092	Loss: 152.774
+19200/69092	Loss: 150.386
+22400/69092	Loss: 151.599
+25600/69092	Loss: 153.623
+28800/69092	Loss: 152.030
+32000/69092	Loss: 151.782
+35200/69092	Loss: 146.994
+38400/69092	Loss: 152.255
+41600/69092	Loss: 151.885
+44800/69092	Loss: 153.996
+48000/69092	Loss: 150.656
+51200/69092	Loss: 150.490
+54400/69092	Loss: 150.645
+57600/69092	Loss: 152.508
+60800/69092	Loss: 150.855
+64000/69092	Loss: 147.958
+67200/69092	Loss: 151.810
+Training time 0:07:39.201312
+Epoch: 128 Average loss: 151.29
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 925)
+0/69092	Loss: 156.363
+3200/69092	Loss: 151.579
+6400/69092	Loss: 149.007
+9600/69092	Loss: 151.809
+12800/69092	Loss: 152.189
+16000/69092	Loss: 152.400
+19200/69092	Loss: 153.051
+22400/69092	Loss: 153.260
+25600/69092	Loss: 149.170
+28800/69092	Loss: 149.261
+32000/69092	Loss: 149.228
+35200/69092	Loss: 153.453
+38400/69092	Loss: 151.917
+41600/69092	Loss: 149.064
+44800/69092	Loss: 149.448
+48000/69092	Loss: 149.718
+51200/69092	Loss: 151.338
+54400/69092	Loss: 153.480
+57600/69092	Loss: 152.084
+60800/69092	Loss: 150.879
+64000/69092	Loss: 151.104
+67200/69092	Loss: 152.700
+Training time 0:07:29.239496
+Epoch: 129 Average loss: 151.34
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 926)
+0/69092	Loss: 153.602
+3200/69092	Loss: 149.365
+6400/69092	Loss: 152.429
+9600/69092	Loss: 153.624
+12800/69092	Loss: 150.918
+16000/69092	Loss: 149.167
+19200/69092	Loss: 151.346
+22400/69092	Loss: 153.452
+25600/69092	Loss: 150.274
+28800/69092	Loss: 153.584
+32000/69092	Loss: 151.051
+35200/69092	Loss: 152.301
+38400/69092	Loss: 152.248
+41600/69092	Loss: 150.312
+44800/69092	Loss: 150.440
+48000/69092	Loss: 150.268
+51200/69092	Loss: 151.808
+54400/69092	Loss: 148.809
+57600/69092	Loss: 152.787
+60800/69092	Loss: 150.325
+64000/69092	Loss: 153.076
+67200/69092	Loss: 152.864
+Training time 0:07:31.459204
+Epoch: 130 Average loss: 151.52
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 927)
+0/69092	Loss: 145.687
+3200/69092	Loss: 150.562
+6400/69092	Loss: 151.754
+9600/69092	Loss: 151.882
+12800/69092	Loss: 150.695
+16000/69092	Loss: 151.925
+19200/69092	Loss: 150.311
+22400/69092	Loss: 150.984
+25600/69092	Loss: 150.768
+28800/69092	Loss: 149.421
+32000/69092	Loss: 152.532
+35200/69092	Loss: 148.857
+38400/69092	Loss: 148.691
+41600/69092	Loss: 153.912
+44800/69092	Loss: 153.506
+48000/69092	Loss: 150.628
+51200/69092	Loss: 148.804
+54400/69092	Loss: 154.073
+57600/69092	Loss: 150.662
+60800/69092	Loss: 153.195
+64000/69092	Loss: 153.375
+67200/69092	Loss: 149.911
+Training time 0:07:34.103900
+Epoch: 131 Average loss: 151.28
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 928)
+0/69092	Loss: 158.890
+3200/69092	Loss: 148.898
+6400/69092	Loss: 152.258
+9600/69092	Loss: 148.922
+12800/69092	Loss: 151.149
+16000/69092	Loss: 151.924
+19200/69092	Loss: 149.390
+22400/69092	Loss: 151.368
+25600/69092	Loss: 151.039
+28800/69092	Loss: 150.526
+32000/69092	Loss: 151.997
+35200/69092	Loss: 150.298
+38400/69092	Loss: 149.817
+41600/69092	Loss: 153.578
+44800/69092	Loss: 150.472
+48000/69092	Loss: 152.785
+51200/69092	Loss: 151.896
+54400/69092	Loss: 152.163
+57600/69092	Loss: 151.637
+60800/69092	Loss: 152.326
+64000/69092	Loss: 152.074
+67200/69092	Loss: 150.963
+Training time 0:07:30.411037
+Epoch: 132 Average loss: 151.21
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 929)
+0/69092	Loss: 152.476
+3200/69092	Loss: 151.153
+6400/69092	Loss: 150.819
+9600/69092	Loss: 151.512
+12800/69092	Loss: 151.300
+16000/69092	Loss: 150.884
+19200/69092	Loss: 152.737
+22400/69092	Loss: 153.723
+25600/69092	Loss: 150.138
+28800/69092	Loss: 152.493
+32000/69092	Loss: 150.295
+35200/69092	Loss: 147.729
+38400/69092	Loss: 149.652
+41600/69092	Loss: 153.145
+44800/69092	Loss: 150.353
+48000/69092	Loss: 149.840
+51200/69092	Loss: 149.113
+54400/69092	Loss: 154.326
+57600/69092	Loss: 150.752
+60800/69092	Loss: 154.172
+64000/69092	Loss: 151.482
+67200/69092	Loss: 149.927
+Training time 0:07:35.144481
+Epoch: 133 Average loss: 151.29
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 930)
+0/69092	Loss: 150.330
+3200/69092	Loss: 150.738
+6400/69092	Loss: 153.947
+9600/69092	Loss: 154.037
+12800/69092	Loss: 152.520
+16000/69092	Loss: 153.493
+19200/69092	Loss: 149.971
+22400/69092	Loss: 152.351
+25600/69092	Loss: 151.293
+28800/69092	Loss: 150.689
+32000/69092	Loss: 151.960
+35200/69092	Loss: 151.174
+38400/69092	Loss: 149.856
+41600/69092	Loss: 149.570
+44800/69092	Loss: 151.184
+48000/69092	Loss: 148.480
+51200/69092	Loss: 150.741
+54400/69092	Loss: 152.689
+57600/69092	Loss: 152.733
+60800/69092	Loss: 151.415
+64000/69092	Loss: 151.705
+67200/69092	Loss: 150.536
+Training time 0:07:31.230422
+Epoch: 134 Average loss: 151.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 931)
+0/69092	Loss: 156.602
+3200/69092	Loss: 155.902
+6400/69092	Loss: 149.523
+9600/69092	Loss: 150.878
+12800/69092	Loss: 150.130
+16000/69092	Loss: 149.182
+19200/69092	Loss: 151.504
+22400/69092	Loss: 151.428
+25600/69092	Loss: 151.358
+28800/69092	Loss: 150.165
+32000/69092	Loss: 153.422
+35200/69092	Loss: 151.532
+38400/69092	Loss: 153.305
+41600/69092	Loss: 151.262
+44800/69092	Loss: 148.662
+48000/69092	Loss: 151.726
+51200/69092	Loss: 150.145
+54400/69092	Loss: 151.123
+57600/69092	Loss: 150.252
+60800/69092	Loss: 153.389
+64000/69092	Loss: 152.228
+67200/69092	Loss: 153.550
+Training time 0:07:42.546566
+Epoch: 135 Average loss: 151.45
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 932)
+0/69092	Loss: 192.917
+3200/69092	Loss: 150.780
+6400/69092	Loss: 149.718
+9600/69092	Loss: 152.790
+12800/69092	Loss: 155.841
+16000/69092	Loss: 149.099
+19200/69092	Loss: 152.797
+22400/69092	Loss: 151.635
+25600/69092	Loss: 149.675
+28800/69092	Loss: 150.155
+32000/69092	Loss: 152.205
+35200/69092	Loss: 150.884
+38400/69092	Loss: 150.843
+41600/69092	Loss: 152.562
+44800/69092	Loss: 150.871
+48000/69092	Loss: 151.262
+51200/69092	Loss: 152.155
+54400/69092	Loss: 149.894
+57600/69092	Loss: 152.348
+60800/69092	Loss: 151.301
+64000/69092	Loss: 154.194
+67200/69092	Loss: 151.420
+Training time 0:07:34.404030
+Epoch: 136 Average loss: 151.53
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 933)
+0/69092	Loss: 154.081
+3200/69092	Loss: 151.023
+6400/69092	Loss: 150.659
+9600/69092	Loss: 150.859
+12800/69092	Loss: 150.957
+16000/69092	Loss: 151.402
+19200/69092	Loss: 149.551
+22400/69092	Loss: 150.514
+25600/69092	Loss: 150.607
+28800/69092	Loss: 146.690
+32000/69092	Loss: 152.425
+35200/69092	Loss: 150.959
+38400/69092	Loss: 151.241
+41600/69092	Loss: 153.284
+44800/69092	Loss: 150.841
+48000/69092	Loss: 151.468
+51200/69092	Loss: 154.135
+54400/69092	Loss: 150.535
+57600/69092	Loss: 152.113
+60800/69092	Loss: 151.415
+64000/69092	Loss: 151.924
+67200/69092	Loss: 152.794
+Training time 0:07:41.406707
+Epoch: 137 Average loss: 151.26
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 934)
+0/69092	Loss: 151.758
+3200/69092	Loss: 152.303
+6400/69092	Loss: 150.552
+9600/69092	Loss: 153.624
+12800/69092	Loss: 151.600
+16000/69092	Loss: 152.235
+19200/69092	Loss: 149.450
+22400/69092	Loss: 153.171
+25600/69092	Loss: 150.775
+28800/69092	Loss: 149.502
+32000/69092	Loss: 154.112
+35200/69092	Loss: 151.205
+38400/69092	Loss: 150.401
+41600/69092	Loss: 151.936
+44800/69092	Loss: 151.007
+48000/69092	Loss: 149.750
+51200/69092	Loss: 151.773
+54400/69092	Loss: 151.719
+57600/69092	Loss: 150.312
+60800/69092	Loss: 150.264
+64000/69092	Loss: 152.165
+67200/69092	Loss: 153.599
+Training time 0:07:51.149834
+Epoch: 138 Average loss: 151.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 935)
+0/69092	Loss: 163.942
+3200/69092	Loss: 153.892
+6400/69092	Loss: 152.419
+9600/69092	Loss: 149.816
+12800/69092	Loss: 149.134
+16000/69092	Loss: 149.846
+19200/69092	Loss: 151.529
+22400/69092	Loss: 148.865
+25600/69092	Loss: 150.458
+28800/69092	Loss: 153.477
+32000/69092	Loss: 151.430
+35200/69092	Loss: 151.400
+38400/69092	Loss: 149.812
+41600/69092	Loss: 149.920
+44800/69092	Loss: 155.557
+48000/69092	Loss: 151.174
+51200/69092	Loss: 151.239
+54400/69092	Loss: 152.275
+57600/69092	Loss: 152.798
+60800/69092	Loss: 148.169
+64000/69092	Loss: 151.449
+67200/69092	Loss: 155.051
+Training time 0:07:34.220237
+Epoch: 139 Average loss: 151.38
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 936)
+0/69092	Loss: 135.889
+3200/69092	Loss: 149.259
+6400/69092	Loss: 150.723
+9600/69092	Loss: 149.894
+12800/69092	Loss: 152.169
+16000/69092	Loss: 152.595
+19200/69092	Loss: 153.289
+22400/69092	Loss: 151.341
+25600/69092	Loss: 150.578
+28800/69092	Loss: 149.681
+32000/69092	Loss: 150.240
+35200/69092	Loss: 151.527
+38400/69092	Loss: 152.612
+41600/69092	Loss: 151.566
+44800/69092	Loss: 151.978
+48000/69092	Loss: 153.291
+51200/69092	Loss: 152.420
+54400/69092	Loss: 150.876
+57600/69092	Loss: 151.893
+60800/69092	Loss: 149.141
+64000/69092	Loss: 151.689
+67200/69092	Loss: 152.193
+Training time 0:07:37.798861
+Epoch: 140 Average loss: 151.38
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 937)
+0/69092	Loss: 154.060
+3200/69092	Loss: 151.337
+6400/69092	Loss: 149.624
+9600/69092	Loss: 153.368
+12800/69092	Loss: 151.766
+16000/69092	Loss: 150.789
+19200/69092	Loss: 153.736
+22400/69092	Loss: 149.811
+25600/69092	Loss: 148.097
+28800/69092	Loss: 153.147
+32000/69092	Loss: 150.933
+35200/69092	Loss: 151.689
+38400/69092	Loss: 149.050
+41600/69092	Loss: 151.974
+44800/69092	Loss: 153.462
+48000/69092	Loss: 150.815
+51200/69092	Loss: 150.851
+54400/69092	Loss: 152.239
+57600/69092	Loss: 150.101
+60800/69092	Loss: 151.103
+64000/69092	Loss: 153.330
+67200/69092	Loss: 151.500
+Training time 0:07:47.568019
+Epoch: 141 Average loss: 151.37
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 938)
+0/69092	Loss: 165.318
+3200/69092	Loss: 151.236
+6400/69092	Loss: 148.331
+9600/69092	Loss: 153.908
+12800/69092	Loss: 150.460
+16000/69092	Loss: 155.007
+19200/69092	Loss: 151.594
+22400/69092	Loss: 150.946
+25600/69092	Loss: 150.128
+28800/69092	Loss: 154.425
+32000/69092	Loss: 150.489
+35200/69092	Loss: 150.490
+38400/69092	Loss: 151.721
+41600/69092	Loss: 150.946
+44800/69092	Loss: 150.970
+48000/69092	Loss: 153.242
+51200/69092	Loss: 150.033
+54400/69092	Loss: 150.964
+57600/69092	Loss: 151.133
+60800/69092	Loss: 149.568
+64000/69092	Loss: 152.084
+67200/69092	Loss: 152.417
+Training time 0:07:38.374045
+Epoch: 142 Average loss: 151.45
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last' (iter 939)
+0/69092	Loss: 142.387
+3200/69092	Loss: 148.898
+6400/69092	Loss: 152.681
+9600/69092	Loss: 150.284
+12800/69092	Loss: 151.873
+16000/69092	Loss: 150.691
diff --git a/OAR.2073647.stderr b/OAR.2073647.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..768d34c20f7db93ff5f20685260f859f72fc0e77
--- /dev/null
+++ b/OAR.2073647.stderr
@@ -0,0 +1,3 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+## OAR [2020-07-06 17:10:05] Job 2073647 KILLED ##
diff --git a/OAR.2073647.stdout b/OAR.2073647.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..0c79a03968ca8afb550c8655dfcbf10854b3a8ea
--- /dev/null
+++ b/OAR.2073647.stdout
@@ -0,0 +1,1285 @@
+Namespace(batch_size=256, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_256', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce GTX 1080 Ti
+GeForce GTX 1080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 765335
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last (iter 728)'
+0/69092	Loss: 108.722
+12800/69092	Loss: 111.769
+25600/69092	Loss: 111.041
+38400/69092	Loss: 110.182
+51200/69092	Loss: 111.193
+64000/69092	Loss: 111.485
+Training time 0:12:50.917397
+Epoch: 1 Average loss: 111.12
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 729)
+0/69092	Loss: 118.472
+12800/69092	Loss: 111.021
+25600/69092	Loss: 110.994
+38400/69092	Loss: 110.750
+51200/69092	Loss: 110.677
+64000/69092	Loss: 111.111
+Training time 0:09:42.548435
+Epoch: 2 Average loss: 111.09
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 730)
+0/69092	Loss: 111.381
+12800/69092	Loss: 110.644
+25600/69092	Loss: 110.944
+38400/69092	Loss: 110.808
+51200/69092	Loss: 111.205
+64000/69092	Loss: 111.103
+Training time 0:09:11.095322
+Epoch: 3 Average loss: 111.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 731)
+0/69092	Loss: 114.332
+12800/69092	Loss: 111.023
+25600/69092	Loss: 111.035
+38400/69092	Loss: 110.424
+51200/69092	Loss: 111.363
+64000/69092	Loss: 111.774
+Training time 0:08:52.508478
+Epoch: 4 Average loss: 111.13
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 732)
+0/69092	Loss: 119.026
+12800/69092	Loss: 110.528
+25600/69092	Loss: 111.693
+38400/69092	Loss: 110.988
+51200/69092	Loss: 110.733
+64000/69092	Loss: 110.715
+Training time 0:09:21.937621
+Epoch: 5 Average loss: 110.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 733)
+0/69092	Loss: 108.146
+12800/69092	Loss: 111.403
+25600/69092	Loss: 111.106
+38400/69092	Loss: 110.541
+51200/69092	Loss: 111.245
+64000/69092	Loss: 111.007
+Training time 0:09:30.392595
+Epoch: 6 Average loss: 111.01
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 734)
+0/69092	Loss: 113.794
+12800/69092	Loss: 110.684
+25600/69092	Loss: 110.569
+38400/69092	Loss: 110.473
+51200/69092	Loss: 111.011
+64000/69092	Loss: 111.652
+Training time 0:09:35.919293
+Epoch: 7 Average loss: 110.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 735)
+0/69092	Loss: 115.122
+12800/69092	Loss: 111.179
+25600/69092	Loss: 110.384
+38400/69092	Loss: 110.799
+51200/69092	Loss: 111.416
+64000/69092	Loss: 111.023
+Training time 0:09:27.262362
+Epoch: 8 Average loss: 111.08
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 736)
+0/69092	Loss: 115.438
+12800/69092	Loss: 110.856
+25600/69092	Loss: 110.571
+38400/69092	Loss: 111.065
+51200/69092	Loss: 110.808
+64000/69092	Loss: 111.537
+Training time 0:09:14.635852
+Epoch: 9 Average loss: 111.04
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 737)
+0/69092	Loss: 116.129
+12800/69092	Loss: 110.795
+25600/69092	Loss: 112.093
+38400/69092	Loss: 110.329
+51200/69092	Loss: 110.786
+64000/69092	Loss: 110.971
+Training time 0:09:33.102811
+Epoch: 10 Average loss: 111.03
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 738)
+0/69092	Loss: 105.028
+12800/69092	Loss: 110.760
+25600/69092	Loss: 110.789
+38400/69092	Loss: 111.709
+51200/69092	Loss: 111.264
+64000/69092	Loss: 110.362
+Training time 0:09:31.890882
+Epoch: 11 Average loss: 110.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 739)
+0/69092	Loss: 108.533
+12800/69092	Loss: 111.041
+25600/69092	Loss: 111.805
+38400/69092	Loss: 110.619
+51200/69092	Loss: 111.334
+64000/69092	Loss: 110.778
+Training time 0:09:30.715261
+Epoch: 12 Average loss: 111.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 740)
+0/69092	Loss: 108.909
+12800/69092	Loss: 110.857
+25600/69092	Loss: 110.783
+38400/69092	Loss: 111.424
+51200/69092	Loss: 111.517
+64000/69092	Loss: 110.597
+Training time 0:09:28.943902
+Epoch: 13 Average loss: 111.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 741)
+0/69092	Loss: 108.396
+12800/69092	Loss: 110.911
+25600/69092	Loss: 111.253
+38400/69092	Loss: 110.931
+51200/69092	Loss: 110.386
+64000/69092	Loss: 110.619
+Training time 0:09:27.970261
+Epoch: 14 Average loss: 110.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 742)
+0/69092	Loss: 111.882
+12800/69092	Loss: 111.296
+25600/69092	Loss: 110.975
+38400/69092	Loss: 111.392
+51200/69092	Loss: 110.892
+64000/69092	Loss: 110.304
+Training time 0:09:16.109476
+Epoch: 15 Average loss: 111.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 743)
+0/69092	Loss: 110.869
+12800/69092	Loss: 110.965
+25600/69092	Loss: 110.654
+38400/69092	Loss: 111.196
+51200/69092	Loss: 110.621
+64000/69092	Loss: 111.541
+Training time 0:09:39.838887
+Epoch: 16 Average loss: 110.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 744)
+0/69092	Loss: 112.494
+12800/69092	Loss: 111.245
+25600/69092	Loss: 110.699
+38400/69092	Loss: 110.605
+51200/69092	Loss: 110.514
+64000/69092	Loss: 111.295
+Training time 0:09:20.638673
+Epoch: 17 Average loss: 110.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 745)
+0/69092	Loss: 109.675
+12800/69092	Loss: 111.226
+25600/69092	Loss: 110.258
+38400/69092	Loss: 111.344
+51200/69092	Loss: 111.517
+64000/69092	Loss: 110.551
+Training time 0:09:26.955377
+Epoch: 18 Average loss: 110.99
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 746)
+0/69092	Loss: 108.544
+12800/69092	Loss: 111.181
+25600/69092	Loss: 111.452
+38400/69092	Loss: 111.120
+51200/69092	Loss: 110.681
+64000/69092	Loss: 110.614
+Training time 0:09:29.038946
+Epoch: 19 Average loss: 111.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 747)
+0/69092	Loss: 114.664
+12800/69092	Loss: 110.344
+25600/69092	Loss: 111.641
+38400/69092	Loss: 111.159
+51200/69092	Loss: 110.458
+64000/69092	Loss: 110.285
+Training time 0:09:22.146378
+Epoch: 20 Average loss: 110.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 748)
+0/69092	Loss: 107.660
+12800/69092	Loss: 110.671
+25600/69092	Loss: 110.731
+38400/69092	Loss: 111.661
+51200/69092	Loss: 110.905
+64000/69092	Loss: 111.217
+Training time 0:09:23.430340
+Epoch: 21 Average loss: 110.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 749)
+0/69092	Loss: 106.079
+12800/69092	Loss: 110.776
+25600/69092	Loss: 111.176
+38400/69092	Loss: 110.900
+51200/69092	Loss: 110.411
+64000/69092	Loss: 111.377
+Training time 0:09:26.846976
+Epoch: 22 Average loss: 110.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 750)
+0/69092	Loss: 114.890
+12800/69092	Loss: 110.829
+25600/69092	Loss: 110.961
+38400/69092	Loss: 109.853
+51200/69092	Loss: 111.639
+64000/69092	Loss: 110.591
+Training time 0:09:32.735858
+Epoch: 23 Average loss: 110.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 751)
+0/69092	Loss: 113.187
+12800/69092	Loss: 110.524
+25600/69092	Loss: 110.147
+38400/69092	Loss: 111.201
+51200/69092	Loss: 111.177
+64000/69092	Loss: 111.199
+Training time 0:09:31.917799
+Epoch: 24 Average loss: 110.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 752)
+0/69092	Loss: 110.364
+12800/69092	Loss: 111.024
+25600/69092	Loss: 112.059
+38400/69092	Loss: 110.908
+51200/69092	Loss: 110.672
+64000/69092	Loss: 110.566
+Training time 0:09:21.939992
+Epoch: 25 Average loss: 111.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 753)
+0/69092	Loss: 109.060
+12800/69092	Loss: 111.556
+25600/69092	Loss: 110.863
+38400/69092	Loss: 110.807
+51200/69092	Loss: 110.126
+64000/69092	Loss: 111.303
+Training time 0:09:38.005277
+Epoch: 26 Average loss: 110.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 754)
+0/69092	Loss: 103.543
+12800/69092	Loss: 110.507
+25600/69092	Loss: 111.684
+38400/69092	Loss: 111.196
+51200/69092	Loss: 110.785
+64000/69092	Loss: 110.943
+Training time 0:09:21.809287
+Epoch: 27 Average loss: 111.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 755)
+0/69092	Loss: 114.147
+12800/69092	Loss: 110.551
+25600/69092	Loss: 111.071
+38400/69092	Loss: 111.689
+51200/69092	Loss: 110.300
+64000/69092	Loss: 110.318
+Training time 0:09:26.235358
+Epoch: 28 Average loss: 110.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 756)
+0/69092	Loss: 112.000
+12800/69092	Loss: 111.224
+25600/69092	Loss: 112.045
+38400/69092	Loss: 110.952
+51200/69092	Loss: 110.337
+64000/69092	Loss: 110.128
+Training time 0:09:22.257001
+Epoch: 29 Average loss: 110.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 757)
+0/69092	Loss: 108.528
+12800/69092	Loss: 111.069
+25600/69092	Loss: 110.553
+38400/69092	Loss: 111.450
+51200/69092	Loss: 111.261
+64000/69092	Loss: 110.485
+Training time 0:09:16.983149
+Epoch: 30 Average loss: 110.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 758)
+0/69092	Loss: 115.859
+12800/69092	Loss: 111.616
+25600/69092	Loss: 110.740
+38400/69092	Loss: 110.353
+51200/69092	Loss: 111.360
+64000/69092	Loss: 110.719
+Training time 0:09:54.731527
+Epoch: 31 Average loss: 110.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 759)
+0/69092	Loss: 111.381
+12800/69092	Loss: 110.646
+25600/69092	Loss: 110.058
+38400/69092	Loss: 110.738
+51200/69092	Loss: 111.080
+64000/69092	Loss: 111.261
+Training time 0:09:16.553942
+Epoch: 32 Average loss: 110.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 760)
+0/69092	Loss: 110.746
+12800/69092	Loss: 111.595
+25600/69092	Loss: 110.628
+38400/69092	Loss: 111.136
+51200/69092	Loss: 111.155
+64000/69092	Loss: 110.105
+Training time 0:09:05.338645
+Epoch: 33 Average loss: 110.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 761)
+0/69092	Loss: 113.203
+12800/69092	Loss: 111.038
+25600/69092	Loss: 111.675
+38400/69092	Loss: 110.887
+51200/69092	Loss: 110.927
+64000/69092	Loss: 110.654
+Training time 0:09:34.197636
+Epoch: 34 Average loss: 111.03
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 762)
+0/69092	Loss: 110.218
+12800/69092	Loss: 111.339
+25600/69092	Loss: 111.423
+38400/69092	Loss: 110.442
+51200/69092	Loss: 109.938
+64000/69092	Loss: 111.407
+Training time 0:09:03.749859
+Epoch: 35 Average loss: 110.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 763)
+0/69092	Loss: 106.947
+12800/69092	Loss: 111.473
+25600/69092	Loss: 110.609
+38400/69092	Loss: 111.658
+51200/69092	Loss: 111.304
+64000/69092	Loss: 110.435
+Training time 0:09:20.644634
+Epoch: 36 Average loss: 111.01
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 764)
+0/69092	Loss: 108.108
+12800/69092	Loss: 111.297
+25600/69092	Loss: 110.830
+38400/69092	Loss: 110.317
+51200/69092	Loss: 110.617
+64000/69092	Loss: 110.754
+Training time 0:09:15.332540
+Epoch: 37 Average loss: 110.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 765)
+0/69092	Loss: 110.004
+12800/69092	Loss: 110.830
+25600/69092	Loss: 110.717
+38400/69092	Loss: 110.325
+51200/69092	Loss: 110.496
+64000/69092	Loss: 111.425
+Training time 0:09:25.173369
+Epoch: 38 Average loss: 110.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 766)
+0/69092	Loss: 105.573
+12800/69092	Loss: 110.753
+25600/69092	Loss: 111.396
+38400/69092	Loss: 110.258
+51200/69092	Loss: 111.492
+64000/69092	Loss: 111.294
+Training time 0:09:41.659884
+Epoch: 39 Average loss: 110.99
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 767)
+0/69092	Loss: 108.419
+12800/69092	Loss: 110.709
+25600/69092	Loss: 111.199
+38400/69092	Loss: 110.095
+51200/69092	Loss: 111.092
+64000/69092	Loss: 110.901
+Training time 0:09:14.703659
+Epoch: 40 Average loss: 110.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 768)
+0/69092	Loss: 113.637
+12800/69092	Loss: 110.347
+25600/69092	Loss: 110.965
+38400/69092	Loss: 111.031
+51200/69092	Loss: 110.508
+64000/69092	Loss: 111.368
+Training time 0:09:21.885794
+Epoch: 41 Average loss: 110.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 769)
+0/69092	Loss: 105.631
+12800/69092	Loss: 110.383
+25600/69092	Loss: 110.511
+38400/69092	Loss: 110.422
+51200/69092	Loss: 112.063
+64000/69092	Loss: 111.508
+Training time 0:09:24.024432
+Epoch: 42 Average loss: 110.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 770)
+0/69092	Loss: 115.095
+12800/69092	Loss: 110.708
+25600/69092	Loss: 110.450
+38400/69092	Loss: 111.719
+51200/69092	Loss: 109.691
+64000/69092	Loss: 110.597
+Training time 0:09:23.937265
+Epoch: 43 Average loss: 110.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 771)
+0/69092	Loss: 107.393
+12800/69092	Loss: 110.297
+25600/69092	Loss: 111.521
+38400/69092	Loss: 110.714
+51200/69092	Loss: 110.861
+64000/69092	Loss: 110.477
+Training time 0:10:23.365242
+Epoch: 44 Average loss: 110.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 772)
+0/69092	Loss: 109.554
+12800/69092	Loss: 110.261
+25600/69092	Loss: 111.825
+38400/69092	Loss: 109.385
+51200/69092	Loss: 111.255
+64000/69092	Loss: 111.497
+Training time 0:09:07.169341
+Epoch: 45 Average loss: 110.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 773)
+0/69092	Loss: 116.077
+12800/69092	Loss: 110.554
+25600/69092	Loss: 110.277
+38400/69092	Loss: 110.429
+51200/69092	Loss: 111.507
+64000/69092	Loss: 110.480
+Training time 0:09:33.652198
+Epoch: 46 Average loss: 110.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 774)
+0/69092	Loss: 109.116
+12800/69092	Loss: 110.612
+25600/69092	Loss: 111.120
+38400/69092	Loss: 110.521
+51200/69092	Loss: 111.198
+64000/69092	Loss: 110.803
+Training time 0:09:23.694512
+Epoch: 47 Average loss: 110.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 775)
+0/69092	Loss: 110.395
+12800/69092	Loss: 110.039
+25600/69092	Loss: 110.418
+38400/69092	Loss: 111.108
+51200/69092	Loss: 110.654
+64000/69092	Loss: 112.227
+Training time 0:09:29.653805
+Epoch: 48 Average loss: 110.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 776)
+0/69092	Loss: 108.087
+12800/69092	Loss: 110.537
+25600/69092	Loss: 110.493
+38400/69092	Loss: 111.042
+51200/69092	Loss: 110.571
+64000/69092	Loss: 110.815
+Training time 0:09:27.424934
+Epoch: 49 Average loss: 110.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 777)
+0/69092	Loss: 109.888
+12800/69092	Loss: 110.678
+25600/69092	Loss: 111.083
+38400/69092	Loss: 111.059
+51200/69092	Loss: 109.860
+64000/69092	Loss: 111.425
+Training time 0:08:54.410094
+Epoch: 50 Average loss: 110.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 778)
+0/69092	Loss: 112.188
+12800/69092	Loss: 111.156
+25600/69092	Loss: 111.841
+38400/69092	Loss: 110.080
+51200/69092	Loss: 110.892
+64000/69092	Loss: 110.658
+Training time 0:09:35.232762
+Epoch: 51 Average loss: 110.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 779)
+0/69092	Loss: 103.264
+12800/69092	Loss: 111.536
+25600/69092	Loss: 109.918
+38400/69092	Loss: 110.863
+51200/69092	Loss: 110.727
+64000/69092	Loss: 111.331
+Training time 0:08:47.956574
+Epoch: 52 Average loss: 110.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 780)
+0/69092	Loss: 113.592
+12800/69092	Loss: 110.269
+25600/69092	Loss: 111.601
+38400/69092	Loss: 110.717
+51200/69092	Loss: 110.301
+64000/69092	Loss: 111.271
+Training time 0:09:21.444065
+Epoch: 53 Average loss: 110.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 781)
+0/69092	Loss: 108.693
+12800/69092	Loss: 110.228
+25600/69092	Loss: 110.811
+38400/69092	Loss: 110.954
+51200/69092	Loss: 110.510
+64000/69092	Loss: 111.624
+Training time 0:09:07.410746
+Epoch: 54 Average loss: 110.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 782)
+0/69092	Loss: 103.967
+12800/69092	Loss: 110.694
+25600/69092	Loss: 111.077
+38400/69092	Loss: 110.095
+51200/69092	Loss: 110.875
+64000/69092	Loss: 111.014
+Training time 0:09:14.922046
+Epoch: 55 Average loss: 110.69
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 783)
+0/69092	Loss: 111.120
+12800/69092	Loss: 110.731
+25600/69092	Loss: 111.300
+38400/69092	Loss: 111.100
+51200/69092	Loss: 110.527
+64000/69092	Loss: 110.682
+Training time 0:09:28.395634
+Epoch: 56 Average loss: 110.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 784)
+0/69092	Loss: 107.371
+12800/69092	Loss: 109.852
+25600/69092	Loss: 110.899
+38400/69092	Loss: 110.503
+51200/69092	Loss: 110.930
+64000/69092	Loss: 112.002
+Training time 0:09:13.943243
+Epoch: 57 Average loss: 110.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 785)
+0/69092	Loss: 114.718
+12800/69092	Loss: 110.516
+25600/69092	Loss: 110.660
+38400/69092	Loss: 110.440
+51200/69092	Loss: 110.680
+64000/69092	Loss: 111.125
+Training time 0:09:01.761234
+Epoch: 58 Average loss: 110.72
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 786)
+0/69092	Loss: 107.819
+12800/69092	Loss: 110.622
+25600/69092	Loss: 110.877
+38400/69092	Loss: 110.857
+51200/69092	Loss: 111.334
+64000/69092	Loss: 110.141
+Training time 0:09:28.778046
+Epoch: 59 Average loss: 110.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 787)
+0/69092	Loss: 106.999
+12800/69092	Loss: 110.307
+25600/69092	Loss: 111.129
+38400/69092	Loss: 110.174
+51200/69092	Loss: 110.798
+64000/69092	Loss: 111.206
+Training time 0:09:31.579343
+Epoch: 60 Average loss: 110.70
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 788)
+0/69092	Loss: 106.323
+12800/69092	Loss: 110.373
+25600/69092	Loss: 111.004
+38400/69092	Loss: 110.273
+51200/69092	Loss: 110.979
+64000/69092	Loss: 110.907
+Training time 0:09:35.626419
+Epoch: 61 Average loss: 110.73
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 789)
+0/69092	Loss: 116.201
+12800/69092	Loss: 110.666
+25600/69092	Loss: 111.164
+38400/69092	Loss: 110.355
+51200/69092	Loss: 110.315
+64000/69092	Loss: 111.331
+Training time 0:09:14.447993
+Epoch: 62 Average loss: 110.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 790)
+0/69092	Loss: 113.965
+12800/69092	Loss: 110.962
+25600/69092	Loss: 110.917
+38400/69092	Loss: 110.439
+51200/69092	Loss: 111.038
+64000/69092	Loss: 111.206
+Training time 0:09:43.207240
+Epoch: 63 Average loss: 110.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 791)
+0/69092	Loss: 109.430
+12800/69092	Loss: 111.008
+25600/69092	Loss: 110.273
+38400/69092	Loss: 110.829
+51200/69092	Loss: 111.109
+64000/69092	Loss: 111.296
+Training time 0:09:07.940413
+Epoch: 64 Average loss: 110.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 792)
+0/69092	Loss: 109.388
+12800/69092	Loss: 110.486
+25600/69092	Loss: 111.653
+38400/69092	Loss: 110.553
+51200/69092	Loss: 110.533
+64000/69092	Loss: 111.202
+Training time 0:09:09.833629
+Epoch: 65 Average loss: 110.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 793)
+0/69092	Loss: 104.720
+12800/69092	Loss: 110.922
+25600/69092	Loss: 110.895
+38400/69092	Loss: 111.097
+51200/69092	Loss: 110.356
+64000/69092	Loss: 110.858
+Training time 0:09:24.944779
+Epoch: 66 Average loss: 110.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 794)
+0/69092	Loss: 107.669
+12800/69092	Loss: 110.905
+25600/69092	Loss: 111.141
+38400/69092	Loss: 110.614
+51200/69092	Loss: 110.986
+64000/69092	Loss: 110.421
+Training time 0:09:16.543716
+Epoch: 67 Average loss: 110.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 795)
+0/69092	Loss: 113.192
+12800/69092	Loss: 110.770
+25600/69092	Loss: 110.409
+38400/69092	Loss: 110.689
+51200/69092	Loss: 111.417
+64000/69092	Loss: 111.049
+Training time 0:09:32.051056
+Epoch: 68 Average loss: 110.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 796)
+0/69092	Loss: 112.199
+12800/69092	Loss: 110.057
+25600/69092	Loss: 111.591
+38400/69092	Loss: 111.081
+51200/69092	Loss: 109.164
+64000/69092	Loss: 111.199
+Training time 0:09:45.081340
+Epoch: 69 Average loss: 110.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 797)
+0/69092	Loss: 106.831
+12800/69092	Loss: 110.352
+25600/69092	Loss: 110.350
+38400/69092	Loss: 110.250
+51200/69092	Loss: 111.470
+64000/69092	Loss: 110.668
+Training time 0:09:14.544888
+Epoch: 70 Average loss: 110.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 798)
+0/69092	Loss: 113.878
+12800/69092	Loss: 110.857
+25600/69092	Loss: 110.477
+38400/69092	Loss: 110.961
+51200/69092	Loss: 111.401
+64000/69092	Loss: 110.299
+Training time 0:09:13.631755
+Epoch: 71 Average loss: 110.87
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 799)
+0/69092	Loss: 110.599
+12800/69092	Loss: 111.133
+25600/69092	Loss: 110.335
+38400/69092	Loss: 110.928
+51200/69092	Loss: 110.199
+64000/69092	Loss: 110.929
+Training time 0:09:08.233061
+Epoch: 72 Average loss: 110.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 800)
+0/69092	Loss: 111.680
+12800/69092	Loss: 110.415
+25600/69092	Loss: 109.988
+38400/69092	Loss: 111.468
+51200/69092	Loss: 111.468
+64000/69092	Loss: 110.725
+Training time 0:09:11.325134
+Epoch: 73 Average loss: 110.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 801)
+0/69092	Loss: 107.396
+12800/69092	Loss: 110.507
+25600/69092	Loss: 109.940
+38400/69092	Loss: 111.694
+51200/69092	Loss: 110.797
+64000/69092	Loss: 110.296
+Training time 0:09:29.676659
+Epoch: 74 Average loss: 110.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 802)
+0/69092	Loss: 111.676
+12800/69092	Loss: 110.461
+25600/69092	Loss: 110.492
+38400/69092	Loss: 111.101
+51200/69092	Loss: 110.632
+64000/69092	Loss: 110.672
+Training time 0:09:05.906074
+Epoch: 75 Average loss: 110.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 803)
+0/69092	Loss: 112.054
+12800/69092	Loss: 110.984
+25600/69092	Loss: 110.414
+38400/69092	Loss: 110.621
+51200/69092	Loss: 110.603
+64000/69092	Loss: 111.128
+Training time 0:09:32.638334
+Epoch: 76 Average loss: 110.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 804)
+0/69092	Loss: 106.933
+12800/69092	Loss: 109.913
+25600/69092	Loss: 111.064
+38400/69092	Loss: 110.595
+51200/69092	Loss: 110.109
+64000/69092	Loss: 111.180
+Training time 0:09:42.792656
+Epoch: 77 Average loss: 110.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 805)
+0/69092	Loss: 110.726
+12800/69092	Loss: 111.207
+25600/69092	Loss: 110.603
+38400/69092	Loss: 111.033
+51200/69092	Loss: 110.874
+64000/69092	Loss: 109.952
+Training time 0:09:39.582453
+Epoch: 78 Average loss: 110.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 806)
+0/69092	Loss: 112.277
+12800/69092	Loss: 110.543
+25600/69092	Loss: 110.230
+38400/69092	Loss: 111.120
+51200/69092	Loss: 111.396
+64000/69092	Loss: 110.047
+Training time 0:09:15.718235
+Epoch: 79 Average loss: 110.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 807)
+0/69092	Loss: 111.844
+12800/69092	Loss: 110.929
+25600/69092	Loss: 111.159
+38400/69092	Loss: 110.613
+51200/69092	Loss: 111.185
+64000/69092	Loss: 110.582
+Training time 0:09:11.576576
+Epoch: 80 Average loss: 110.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 808)
+0/69092	Loss: 107.992
+12800/69092	Loss: 110.108
+25600/69092	Loss: 110.508
+38400/69092	Loss: 110.977
+51200/69092	Loss: 110.487
+64000/69092	Loss: 110.423
+Training time 0:09:21.274824
+Epoch: 81 Average loss: 110.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 809)
+0/69092	Loss: 109.205
+12800/69092	Loss: 110.442
+25600/69092	Loss: 109.896
+38400/69092	Loss: 111.430
+51200/69092	Loss: 110.768
+64000/69092	Loss: 110.871
+Training time 0:09:42.119095
+Epoch: 82 Average loss: 110.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 810)
+0/69092	Loss: 103.766
+12800/69092	Loss: 111.101
+25600/69092	Loss: 110.351
+38400/69092	Loss: 111.058
+51200/69092	Loss: 110.465
+64000/69092	Loss: 111.212
+Training time 0:09:09.753667
+Epoch: 83 Average loss: 110.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 811)
+0/69092	Loss: 107.883
+12800/69092	Loss: 111.215
+25600/69092	Loss: 110.932
+38400/69092	Loss: 111.436
+51200/69092	Loss: 110.905
+64000/69092	Loss: 109.741
+Training time 0:09:40.094972
+Epoch: 84 Average loss: 110.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 812)
+0/69092	Loss: 113.163
+12800/69092	Loss: 111.128
+25600/69092	Loss: 110.817
+38400/69092	Loss: 110.731
+51200/69092	Loss: 111.000
+64000/69092	Loss: 110.024
+Training time 0:09:20.497057
+Epoch: 85 Average loss: 110.70
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 813)
+0/69092	Loss: 108.458
+12800/69092	Loss: 109.776
+25600/69092	Loss: 110.576
+38400/69092	Loss: 111.410
+51200/69092	Loss: 111.095
+64000/69092	Loss: 110.718
+Training time 0:09:12.810462
+Epoch: 86 Average loss: 110.73
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 814)
+0/69092	Loss: 104.994
+12800/69092	Loss: 111.258
+25600/69092	Loss: 111.109
+38400/69092	Loss: 109.538
+51200/69092	Loss: 111.264
+64000/69092	Loss: 110.145
+Training time 0:09:00.101882
+Epoch: 87 Average loss: 110.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 815)
+0/69092	Loss: 109.292
+12800/69092	Loss: 110.546
+25600/69092	Loss: 110.846
+38400/69092	Loss: 110.351
+51200/69092	Loss: 111.075
+64000/69092	Loss: 111.178
+Training time 0:09:31.204758
+Epoch: 88 Average loss: 110.72
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 816)
+0/69092	Loss: 110.052
+12800/69092	Loss: 111.120
+25600/69092	Loss: 109.840
+38400/69092	Loss: 110.721
+51200/69092	Loss: 111.175
+64000/69092	Loss: 110.536
+Training time 0:08:57.774653
+Epoch: 89 Average loss: 110.72
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 817)
+0/69092	Loss: 119.815
+12800/69092	Loss: 110.189
+25600/69092	Loss: 109.965
+38400/69092	Loss: 111.429
+51200/69092	Loss: 110.971
+64000/69092	Loss: 110.336
+Training time 0:09:29.941374
+Epoch: 90 Average loss: 110.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 818)
+0/69092	Loss: 109.860
+12800/69092	Loss: 111.020
+25600/69092	Loss: 109.924
+38400/69092	Loss: 111.336
+51200/69092	Loss: 110.517
+64000/69092	Loss: 110.184
+Training time 0:09:24.364463
+Epoch: 91 Average loss: 110.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 819)
+0/69092	Loss: 109.001
+12800/69092	Loss: 110.340
+25600/69092	Loss: 111.048
+38400/69092	Loss: 110.527
+51200/69092	Loss: 110.367
+64000/69092	Loss: 110.272
+Training time 0:08:57.566618
+Epoch: 92 Average loss: 110.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 820)
+0/69092	Loss: 104.126
+12800/69092	Loss: 110.573
+25600/69092	Loss: 110.813
+38400/69092	Loss: 110.816
+51200/69092	Loss: 109.755
+64000/69092	Loss: 110.878
+Training time 0:09:03.412078
+Epoch: 93 Average loss: 110.57
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 821)
+0/69092	Loss: 108.554
+12800/69092	Loss: 109.801
+25600/69092	Loss: 111.819
+38400/69092	Loss: 110.925
+51200/69092	Loss: 110.261
+64000/69092	Loss: 111.312
+Training time 0:09:31.002607
+Epoch: 94 Average loss: 110.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 822)
+0/69092	Loss: 106.443
+12800/69092	Loss: 109.902
+25600/69092	Loss: 110.375
+38400/69092	Loss: 110.660
+51200/69092	Loss: 110.759
+64000/69092	Loss: 111.541
+Training time 0:09:18.002569
+Epoch: 95 Average loss: 110.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 823)
+0/69092	Loss: 107.398
+12800/69092	Loss: 109.581
+25600/69092	Loss: 111.191
+38400/69092	Loss: 111.395
+51200/69092	Loss: 110.605
+64000/69092	Loss: 110.493
+Training time 0:09:28.393583
+Epoch: 96 Average loss: 110.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 824)
+0/69092	Loss: 110.220
+12800/69092	Loss: 110.445
+25600/69092	Loss: 110.862
+38400/69092	Loss: 110.497
+51200/69092	Loss: 110.779
+64000/69092	Loss: 110.767
+Training time 0:09:33.528565
+Epoch: 97 Average loss: 110.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 825)
+0/69092	Loss: 117.846
+12800/69092	Loss: 110.501
+25600/69092	Loss: 110.407
+38400/69092	Loss: 110.654
+51200/69092	Loss: 110.627
+64000/69092	Loss: 110.859
+Training time 0:09:20.117127
+Epoch: 98 Average loss: 110.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 826)
+0/69092	Loss: 105.806
+12800/69092	Loss: 110.053
+25600/69092	Loss: 110.372
+38400/69092	Loss: 110.532
+51200/69092	Loss: 110.372
+64000/69092	Loss: 111.571
+Training time 0:08:40.701518
+Epoch: 99 Average loss: 110.54
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 827)
+0/69092	Loss: 106.543
+12800/69092	Loss: 110.920
+25600/69092	Loss: 110.315
+38400/69092	Loss: 111.535
+51200/69092	Loss: 110.650
+64000/69092	Loss: 110.403
+Training time 0:09:14.096051
+Epoch: 100 Average loss: 110.73
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 828)
+0/69092	Loss: 112.116
+12800/69092	Loss: 110.574
+25600/69092	Loss: 109.391
+38400/69092	Loss: 111.166
+51200/69092	Loss: 111.020
+64000/69092	Loss: 111.379
+Training time 0:09:44.293904
+Epoch: 101 Average loss: 110.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 829)
+0/69092	Loss: 108.356
+12800/69092	Loss: 110.845
+25600/69092	Loss: 110.886
+38400/69092	Loss: 111.231
+51200/69092	Loss: 109.792
+64000/69092	Loss: 110.705
+Training time 0:09:43.141476
+Epoch: 102 Average loss: 110.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 830)
+0/69092	Loss: 106.065
+12800/69092	Loss: 110.636
+25600/69092	Loss: 110.538
+38400/69092	Loss: 111.432
+51200/69092	Loss: 110.778
+64000/69092	Loss: 110.876
+Training time 0:09:10.919842
+Epoch: 103 Average loss: 110.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 831)
+0/69092	Loss: 120.438
+12800/69092	Loss: 109.686
+25600/69092	Loss: 110.314
+38400/69092	Loss: 111.785
+51200/69092	Loss: 110.249
+64000/69092	Loss: 110.609
+Training time 0:09:27.853299
+Epoch: 104 Average loss: 110.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 832)
+0/69092	Loss: 110.595
+12800/69092	Loss: 110.160
+25600/69092	Loss: 110.482
+38400/69092	Loss: 110.654
+51200/69092	Loss: 111.073
+64000/69092	Loss: 110.639
+Training time 0:09:27.059038
+Epoch: 105 Average loss: 110.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 833)
+0/69092	Loss: 106.981
+12800/69092	Loss: 111.485
+25600/69092	Loss: 110.760
+38400/69092	Loss: 110.000
+51200/69092	Loss: 110.279
+64000/69092	Loss: 111.093
+Training time 0:09:25.152512
+Epoch: 106 Average loss: 110.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 834)
+0/69092	Loss: 110.986
+12800/69092	Loss: 110.963
+25600/69092	Loss: 110.512
+38400/69092	Loss: 110.091
+51200/69092	Loss: 109.974
+64000/69092	Loss: 110.977
+Training time 0:08:44.454873
+Epoch: 107 Average loss: 110.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 835)
+0/69092	Loss: 112.354
+12800/69092	Loss: 110.144
+25600/69092	Loss: 111.182
+38400/69092	Loss: 111.277
+51200/69092	Loss: 110.576
+64000/69092	Loss: 110.416
+Training time 0:08:47.514584
+Epoch: 108 Average loss: 110.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 836)
+0/69092	Loss: 116.993
+12800/69092	Loss: 110.769
+25600/69092	Loss: 110.491
+38400/69092	Loss: 109.808
+51200/69092	Loss: 110.572
+64000/69092	Loss: 111.335
+Training time 0:09:38.156651
+Epoch: 109 Average loss: 110.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 837)
+0/69092	Loss: 108.175
+12800/69092	Loss: 110.609
+25600/69092	Loss: 110.064
+38400/69092	Loss: 110.026
+51200/69092	Loss: 111.051
+64000/69092	Loss: 110.888
+Training time 0:09:08.347423
+Epoch: 110 Average loss: 110.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 838)
+0/69092	Loss: 107.197
+12800/69092	Loss: 110.511
+25600/69092	Loss: 111.262
+38400/69092	Loss: 110.479
+51200/69092	Loss: 110.725
+64000/69092	Loss: 110.455
+Training time 0:09:23.611929
+Epoch: 111 Average loss: 110.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 839)
+0/69092	Loss: 116.361
+12800/69092	Loss: 110.514
+25600/69092	Loss: 109.877
+38400/69092	Loss: 110.808
+51200/69092	Loss: 109.813
+64000/69092	Loss: 110.522
+Training time 0:09:12.732763
+Epoch: 112 Average loss: 110.42
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 840)
+0/69092	Loss: 105.930
+12800/69092	Loss: 111.152
+25600/69092	Loss: 110.327
+38400/69092	Loss: 110.064
+51200/69092	Loss: 110.287
+64000/69092	Loss: 110.793
+Training time 0:09:22.571833
+Epoch: 113 Average loss: 110.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 841)
+0/69092	Loss: 116.128
+12800/69092	Loss: 109.647
+25600/69092	Loss: 110.083
+38400/69092	Loss: 111.086
+51200/69092	Loss: 111.549
+64000/69092	Loss: 110.421
+Training time 0:09:23.405122
+Epoch: 114 Average loss: 110.57
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 842)
+0/69092	Loss: 106.056
+12800/69092	Loss: 110.710
+25600/69092	Loss: 111.498
+38400/69092	Loss: 110.963
+51200/69092	Loss: 110.159
+64000/69092	Loss: 110.144
+Training time 0:09:06.206294
+Epoch: 115 Average loss: 110.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 843)
+0/69092	Loss: 111.178
+12800/69092	Loss: 110.435
+25600/69092	Loss: 110.752
+38400/69092	Loss: 110.418
+51200/69092	Loss: 110.192
+64000/69092	Loss: 110.591
+Training time 0:09:39.852707
+Epoch: 116 Average loss: 110.45
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 844)
+0/69092	Loss: 112.482
+12800/69092	Loss: 110.511
+25600/69092	Loss: 110.777
+38400/69092	Loss: 110.404
+51200/69092	Loss: 110.699
+64000/69092	Loss: 110.528
+Training time 0:09:32.608957
+Epoch: 117 Average loss: 110.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 845)
+0/69092	Loss: 110.397
+12800/69092	Loss: 111.069
+25600/69092	Loss: 111.563
+38400/69092	Loss: 109.983
+51200/69092	Loss: 109.842
+64000/69092	Loss: 111.304
+Training time 0:09:41.847353
+Epoch: 118 Average loss: 110.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 846)
+0/69092	Loss: 111.541
+12800/69092	Loss: 109.897
+25600/69092	Loss: 111.014
+38400/69092	Loss: 110.863
+51200/69092	Loss: 110.090
+64000/69092	Loss: 110.441
+Training time 0:09:28.264368
+Epoch: 119 Average loss: 110.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 847)
+0/69092	Loss: 111.272
+12800/69092	Loss: 110.933
+25600/69092	Loss: 110.636
+38400/69092	Loss: 110.295
+51200/69092	Loss: 110.469
+64000/69092	Loss: 110.508
+Training time 0:08:58.640254
+Epoch: 120 Average loss: 110.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 848)
+0/69092	Loss: 112.465
+12800/69092	Loss: 109.964
+25600/69092	Loss: 110.024
+38400/69092	Loss: 110.330
+51200/69092	Loss: 110.639
+64000/69092	Loss: 111.438
+Training time 0:09:21.596255
+Epoch: 121 Average loss: 110.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 849)
+0/69092	Loss: 118.270
+12800/69092	Loss: 111.282
+25600/69092	Loss: 110.149
+38400/69092	Loss: 109.954
+51200/69092	Loss: 109.958
+64000/69092	Loss: 111.181
+Training time 0:09:16.289846
+Epoch: 122 Average loss: 110.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 850)
+0/69092	Loss: 110.169
+12800/69092	Loss: 111.006
+25600/69092	Loss: 110.165
+38400/69092	Loss: 110.450
+51200/69092	Loss: 110.775
+64000/69092	Loss: 110.115
+Training time 0:09:26.057855
+Epoch: 123 Average loss: 110.50
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 851)
+0/69092	Loss: 108.889
+12800/69092	Loss: 110.592
+25600/69092	Loss: 110.551
+38400/69092	Loss: 110.836
+51200/69092	Loss: 110.575
+64000/69092	Loss: 110.835
+Training time 0:09:10.406542
+Epoch: 124 Average loss: 110.70
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 852)
+0/69092	Loss: 111.799
+12800/69092	Loss: 110.133
+25600/69092	Loss: 109.486
+38400/69092	Loss: 110.276
+51200/69092	Loss: 110.870
+64000/69092	Loss: 111.259
+Training time 0:09:11.313073
+Epoch: 125 Average loss: 110.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 853)
+0/69092	Loss: 111.487
+12800/69092	Loss: 110.530
+25600/69092	Loss: 110.150
+38400/69092	Loss: 109.724
+51200/69092	Loss: 110.238
+64000/69092	Loss: 110.872
+Training time 0:09:11.117149
+Epoch: 126 Average loss: 110.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 854)
+0/69092	Loss: 123.888
+12800/69092	Loss: 110.554
+25600/69092	Loss: 110.668
+38400/69092	Loss: 111.352
+51200/69092	Loss: 109.735
+64000/69092	Loss: 110.383
+Training time 0:08:58.827179
+Epoch: 127 Average loss: 110.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 855)
+0/69092	Loss: 108.684
+12800/69092	Loss: 110.252
+25600/69092	Loss: 110.477
+38400/69092	Loss: 110.820
+51200/69092	Loss: 110.424
+64000/69092	Loss: 110.678
+Training time 0:09:03.152078
+Epoch: 128 Average loss: 110.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 856)
+0/69092	Loss: 112.977
+12800/69092	Loss: 110.040
+25600/69092	Loss: 110.962
+38400/69092	Loss: 109.784
+51200/69092	Loss: 110.822
+64000/69092	Loss: 110.423
+Training time 0:09:25.768023
+Epoch: 129 Average loss: 110.45
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 857)
+0/69092	Loss: 113.245
+12800/69092	Loss: 111.059
+25600/69092	Loss: 109.962
+38400/69092	Loss: 110.863
+51200/69092	Loss: 110.278
+64000/69092	Loss: 110.042
+Training time 0:08:57.985347
+Epoch: 130 Average loss: 110.53
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 858)
+0/69092	Loss: 114.785
+12800/69092	Loss: 110.276
+25600/69092	Loss: 110.468
+38400/69092	Loss: 110.324
+51200/69092	Loss: 110.425
+64000/69092	Loss: 110.479
+Training time 0:08:55.078107
+Epoch: 131 Average loss: 110.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 859)
+0/69092	Loss: 114.275
+12800/69092	Loss: 111.197
+25600/69092	Loss: 110.283
+38400/69092	Loss: 110.909
+51200/69092	Loss: 110.412
+64000/69092	Loss: 110.283
+Training time 0:09:26.989719
+Epoch: 132 Average loss: 110.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 860)
+0/69092	Loss: 109.824
+12800/69092	Loss: 109.870
+25600/69092	Loss: 110.879
+38400/69092	Loss: 110.591
+51200/69092	Loss: 110.901
+64000/69092	Loss: 109.260
+Training time 0:09:37.785464
+Epoch: 133 Average loss: 110.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 861)
+0/69092	Loss: 112.696
+12800/69092	Loss: 111.167
+25600/69092	Loss: 109.916
+38400/69092	Loss: 110.680
+51200/69092	Loss: 110.332
+64000/69092	Loss: 109.972
+Training time 0:09:31.872476
+Epoch: 134 Average loss: 110.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 862)
+0/69092	Loss: 107.555
+12800/69092	Loss: 110.143
+25600/69092	Loss: 110.142
+38400/69092	Loss: 111.046
+51200/69092	Loss: 110.600
+64000/69092	Loss: 110.539
+Training time 0:09:17.019553
+Epoch: 135 Average loss: 110.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 863)
+0/69092	Loss: 112.538
+12800/69092	Loss: 109.582
+25600/69092	Loss: 110.707
+38400/69092	Loss: 109.935
+51200/69092	Loss: 110.932
+64000/69092	Loss: 110.877
+Training time 0:09:17.472150
+Epoch: 136 Average loss: 110.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 864)
+0/69092	Loss: 105.532
+12800/69092	Loss: 110.992
+25600/69092	Loss: 110.579
+38400/69092	Loss: 110.271
+51200/69092	Loss: 110.040
+64000/69092	Loss: 111.116
+Training time 0:09:03.335520
+Epoch: 137 Average loss: 110.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_256/checkpoints/last' (iter 865)
+0/69092	Loss: 109.361
+12800/69092	Loss: 110.865
+25600/69092	Loss: 110.507
+38400/69092	Loss: 109.830
+51200/69092	Loss: 110.366
diff --git a/OAR.2073648.stderr b/OAR.2073648.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..8c2b0a227200abd981a210161746b6cb17454d75
--- /dev/null
+++ b/OAR.2073648.stderr
@@ -0,0 +1,3 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+## OAR [2020-07-06 17:10:05] Job 2073648 KILLED ##
diff --git a/OAR.2073648.stdout b/OAR.2073648.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..dcc0f46e71f9c8564abbc5f32592f1e4f170c9d5
--- /dev/null
+++ b/OAR.2073648.stdout
@@ -0,0 +1,3334 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce GTX 1080 Ti
+GeForce GTX 1080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 765335
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last (iter 929)'
+0/69092	Loss: 100.849
+3200/69092	Loss: 110.892
+6400/69092	Loss: 110.727
+9600/69092	Loss: 109.908
+12800/69092	Loss: 113.204
+16000/69092	Loss: 109.874
+19200/69092	Loss: 108.876
+22400/69092	Loss: 109.982
+25600/69092	Loss: 110.812
+28800/69092	Loss: 110.252
+32000/69092	Loss: 110.938
+35200/69092	Loss: 110.095
+38400/69092	Loss: 109.440
+41600/69092	Loss: 109.325
+44800/69092	Loss: 110.153
+48000/69092	Loss: 110.963
+51200/69092	Loss: 110.980
+54400/69092	Loss: 111.173
+57600/69092	Loss: 110.656
+60800/69092	Loss: 107.658
+64000/69092	Loss: 110.596
+67200/69092	Loss: 111.186
+Training time 0:12:41.329477
+Epoch: 1 Average loss: 110.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 930)
+0/69092	Loss: 116.485
+3200/69092	Loss: 109.978
+6400/69092	Loss: 110.684
+9600/69092	Loss: 109.545
+12800/69092	Loss: 108.703
+16000/69092	Loss: 110.500
+19200/69092	Loss: 109.581
+22400/69092	Loss: 111.463
+25600/69092	Loss: 110.190
+28800/69092	Loss: 110.460
+32000/69092	Loss: 109.763
+35200/69092	Loss: 112.021
+38400/69092	Loss: 110.517
+41600/69092	Loss: 111.780
+44800/69092	Loss: 110.398
+48000/69092	Loss: 110.330
+51200/69092	Loss: 111.126
+54400/69092	Loss: 108.190
+57600/69092	Loss: 109.580
+60800/69092	Loss: 109.197
+64000/69092	Loss: 107.998
+67200/69092	Loss: 109.014
+Training time 0:10:11.661029
+Epoch: 2 Average loss: 110.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 931)
+0/69092	Loss: 104.328
+3200/69092	Loss: 109.268
+6400/69092	Loss: 109.760
+9600/69092	Loss: 110.103
+12800/69092	Loss: 110.188
+16000/69092	Loss: 108.597
+19200/69092	Loss: 110.113
+22400/69092	Loss: 108.816
+25600/69092	Loss: 109.361
+28800/69092	Loss: 109.889
+32000/69092	Loss: 111.162
+35200/69092	Loss: 108.928
+38400/69092	Loss: 112.430
+41600/69092	Loss: 110.559
+44800/69092	Loss: 110.144
+48000/69092	Loss: 111.235
+51200/69092	Loss: 110.282
+54400/69092	Loss: 109.522
+57600/69092	Loss: 109.977
+60800/69092	Loss: 111.115
+64000/69092	Loss: 110.645
+67200/69092	Loss: 110.972
+Training time 0:09:39.709244
+Epoch: 3 Average loss: 110.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 932)
+0/69092	Loss: 108.828
+3200/69092	Loss: 110.284
+6400/69092	Loss: 110.382
+9600/69092	Loss: 106.883
+12800/69092	Loss: 110.148
+16000/69092	Loss: 113.084
+19200/69092	Loss: 109.552
+22400/69092	Loss: 108.769
+25600/69092	Loss: 111.203
+28800/69092	Loss: 110.577
+32000/69092	Loss: 110.546
+35200/69092	Loss: 108.450
+38400/69092	Loss: 110.288
+41600/69092	Loss: 111.301
+44800/69092	Loss: 110.825
+48000/69092	Loss: 110.990
+51200/69092	Loss: 108.261
+54400/69092	Loss: 109.103
+57600/69092	Loss: 108.537
+60800/69092	Loss: 109.679
+64000/69092	Loss: 109.810
+67200/69092	Loss: 110.730
+Training time 0:09:52.117677
+Epoch: 4 Average loss: 110.08
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 933)
+0/69092	Loss: 101.167
+3200/69092	Loss: 108.648
+6400/69092	Loss: 110.088
+9600/69092	Loss: 111.332
+12800/69092	Loss: 109.218
+16000/69092	Loss: 111.634
+19200/69092	Loss: 110.557
+22400/69092	Loss: 111.165
+25600/69092	Loss: 108.554
+28800/69092	Loss: 109.655
+32000/69092	Loss: 109.440
+35200/69092	Loss: 109.522
+38400/69092	Loss: 110.165
+41600/69092	Loss: 111.696
+44800/69092	Loss: 110.700
+48000/69092	Loss: 110.255
+51200/69092	Loss: 108.220
+54400/69092	Loss: 109.651
+57600/69092	Loss: 109.740
+60800/69092	Loss: 110.133
+64000/69092	Loss: 109.295
+67200/69092	Loss: 108.310
+Training time 0:09:25.772454
+Epoch: 5 Average loss: 109.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 934)
+0/69092	Loss: 110.209
+3200/69092	Loss: 109.782
+6400/69092	Loss: 107.741
+9600/69092	Loss: 110.935
+12800/69092	Loss: 109.686
+16000/69092	Loss: 112.218
+19200/69092	Loss: 110.139
+22400/69092	Loss: 109.731
+25600/69092	Loss: 108.515
+28800/69092	Loss: 109.562
+32000/69092	Loss: 108.441
+35200/69092	Loss: 107.848
+38400/69092	Loss: 110.805
+41600/69092	Loss: 110.464
+44800/69092	Loss: 110.586
+48000/69092	Loss: 108.876
+51200/69092	Loss: 109.657
+54400/69092	Loss: 110.250
+57600/69092	Loss: 110.417
+60800/69092	Loss: 110.506
+64000/69092	Loss: 110.707
+67200/69092	Loss: 110.146
+Training time 0:09:30.662585
+Epoch: 6 Average loss: 109.87
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 935)
+0/69092	Loss: 124.815
+3200/69092	Loss: 111.305
+6400/69092	Loss: 109.799
+9600/69092	Loss: 111.216
+12800/69092	Loss: 109.129
+16000/69092	Loss: 110.281
+19200/69092	Loss: 111.050
+22400/69092	Loss: 112.108
+25600/69092	Loss: 109.284
+28800/69092	Loss: 108.843
+32000/69092	Loss: 109.346
+35200/69092	Loss: 109.485
+38400/69092	Loss: 108.350
+41600/69092	Loss: 111.311
+44800/69092	Loss: 110.882
+48000/69092	Loss: 108.689
+51200/69092	Loss: 108.626
+54400/69092	Loss: 110.371
+57600/69092	Loss: 110.578
+60800/69092	Loss: 108.876
+64000/69092	Loss: 109.560
+67200/69092	Loss: 109.777
+Training time 0:09:50.445055
+Epoch: 7 Average loss: 109.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 936)
+0/69092	Loss: 111.901
+3200/69092	Loss: 109.261
+6400/69092	Loss: 111.310
+9600/69092	Loss: 108.375
+12800/69092	Loss: 110.236
+16000/69092	Loss: 109.069
+19200/69092	Loss: 109.362
+22400/69092	Loss: 110.474
+25600/69092	Loss: 109.946
+28800/69092	Loss: 110.452
+32000/69092	Loss: 109.352
+35200/69092	Loss: 110.880
+38400/69092	Loss: 109.157
+41600/69092	Loss: 110.096
+44800/69092	Loss: 110.939
+48000/69092	Loss: 109.960
+51200/69092	Loss: 110.264
+54400/69092	Loss: 108.350
+57600/69092	Loss: 107.830
+60800/69092	Loss: 112.005
+64000/69092	Loss: 111.000
+67200/69092	Loss: 111.781
+Training time 0:10:01.101869
+Epoch: 8 Average loss: 110.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 937)
+0/69092	Loss: 103.813
+3200/69092	Loss: 109.813
+6400/69092	Loss: 110.431
+9600/69092	Loss: 110.024
+12800/69092	Loss: 110.216
+16000/69092	Loss: 109.504
+19200/69092	Loss: 110.869
+22400/69092	Loss: 109.662
+25600/69092	Loss: 111.663
+28800/69092	Loss: 109.335
+32000/69092	Loss: 107.370
+35200/69092	Loss: 109.345
+38400/69092	Loss: 109.761
+41600/69092	Loss: 110.735
+44800/69092	Loss: 110.624
+48000/69092	Loss: 110.560
+51200/69092	Loss: 110.884
+54400/69092	Loss: 109.436
+57600/69092	Loss: 110.047
+60800/69092	Loss: 108.684
+64000/69092	Loss: 110.756
+67200/69092	Loss: 109.519
+Training time 0:09:20.203164
+Epoch: 9 Average loss: 110.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 938)
+0/69092	Loss: 108.684
+3200/69092	Loss: 110.669
+6400/69092	Loss: 109.319
+9600/69092	Loss: 110.055
+12800/69092	Loss: 110.047
+16000/69092	Loss: 108.181
+19200/69092	Loss: 111.334
+22400/69092	Loss: 107.835
+25600/69092	Loss: 110.995
+28800/69092	Loss: 108.113
+32000/69092	Loss: 109.638
+35200/69092	Loss: 109.313
+38400/69092	Loss: 110.170
+41600/69092	Loss: 111.594
+44800/69092	Loss: 109.434
+48000/69092	Loss: 109.755
+51200/69092	Loss: 110.266
+54400/69092	Loss: 109.270
+57600/69092	Loss: 110.455
+60800/69092	Loss: 111.685
+64000/69092	Loss: 108.725
+67200/69092	Loss: 111.577
+Training time 0:09:47.302121
+Epoch: 10 Average loss: 109.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 939)
+0/69092	Loss: 118.846
+3200/69092	Loss: 109.046
+6400/69092	Loss: 111.975
+9600/69092	Loss: 109.306
+12800/69092	Loss: 108.267
+16000/69092	Loss: 107.807
+19200/69092	Loss: 110.471
+22400/69092	Loss: 109.888
+25600/69092	Loss: 110.271
+28800/69092	Loss: 110.627
+32000/69092	Loss: 110.349
+35200/69092	Loss: 108.353
+38400/69092	Loss: 109.904
+41600/69092	Loss: 110.000
+44800/69092	Loss: 111.137
+48000/69092	Loss: 110.982
+51200/69092	Loss: 110.426
+54400/69092	Loss: 110.151
+57600/69092	Loss: 110.103
+60800/69092	Loss: 110.788
+64000/69092	Loss: 110.741
+67200/69092	Loss: 110.840
+Training time 0:09:48.105291
+Epoch: 11 Average loss: 110.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 940)
+0/69092	Loss: 114.442
+3200/69092	Loss: 109.057
+6400/69092	Loss: 109.495
+9600/69092	Loss: 110.674
+12800/69092	Loss: 109.861
+16000/69092	Loss: 110.979
+19200/69092	Loss: 111.237
+22400/69092	Loss: 109.628
+25600/69092	Loss: 109.901
+28800/69092	Loss: 110.205
+32000/69092	Loss: 111.370
+35200/69092	Loss: 110.523
+38400/69092	Loss: 108.632
+41600/69092	Loss: 111.517
+44800/69092	Loss: 109.284
+48000/69092	Loss: 109.305
+51200/69092	Loss: 109.643
+54400/69092	Loss: 110.029
+57600/69092	Loss: 110.488
+60800/69092	Loss: 111.066
+64000/69092	Loss: 107.914
+67200/69092	Loss: 109.275
+Training time 0:09:46.692554
+Epoch: 12 Average loss: 110.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 941)
+0/69092	Loss: 112.749
+3200/69092	Loss: 109.741
+6400/69092	Loss: 109.613
+9600/69092	Loss: 109.997
+12800/69092	Loss: 110.088
+16000/69092	Loss: 110.204
+19200/69092	Loss: 109.341
+22400/69092	Loss: 109.334
+25600/69092	Loss: 110.054
+28800/69092	Loss: 109.299
+32000/69092	Loss: 109.417
+35200/69092	Loss: 111.100
+38400/69092	Loss: 109.561
+41600/69092	Loss: 109.575
+44800/69092	Loss: 108.689
+48000/69092	Loss: 109.589
+51200/69092	Loss: 110.427
+54400/69092	Loss: 109.439
+57600/69092	Loss: 111.085
+60800/69092	Loss: 109.520
+64000/69092	Loss: 111.047
+67200/69092	Loss: 110.421
+Training time 0:09:57.676172
+Epoch: 13 Average loss: 109.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 942)
+0/69092	Loss: 115.775
+3200/69092	Loss: 110.452
+6400/69092	Loss: 109.458
+9600/69092	Loss: 110.028
+12800/69092	Loss: 108.496
+16000/69092	Loss: 109.474
+19200/69092	Loss: 112.008
+22400/69092	Loss: 110.529
+25600/69092	Loss: 112.507
+28800/69092	Loss: 110.940
+32000/69092	Loss: 108.307
+35200/69092	Loss: 111.564
+38400/69092	Loss: 111.243
+41600/69092	Loss: 111.302
+44800/69092	Loss: 110.708
+48000/69092	Loss: 108.706
+51200/69092	Loss: 107.567
+54400/69092	Loss: 110.761
+57600/69092	Loss: 110.145
+60800/69092	Loss: 109.537
+64000/69092	Loss: 109.645
+67200/69092	Loss: 109.373
+Training time 0:09:39.795225
+Epoch: 14 Average loss: 110.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 943)
+0/69092	Loss: 111.891
+3200/69092	Loss: 111.539
+6400/69092	Loss: 110.997
+9600/69092	Loss: 110.979
+12800/69092	Loss: 111.068
+16000/69092	Loss: 109.918
+19200/69092	Loss: 108.622
+22400/69092	Loss: 108.562
+25600/69092	Loss: 110.405
+28800/69092	Loss: 110.436
+32000/69092	Loss: 111.500
+35200/69092	Loss: 110.229
+38400/69092	Loss: 110.858
+41600/69092	Loss: 112.382
+44800/69092	Loss: 109.113
+48000/69092	Loss: 109.128
+51200/69092	Loss: 109.043
+54400/69092	Loss: 108.629
+57600/69092	Loss: 110.196
+60800/69092	Loss: 110.518
+64000/69092	Loss: 109.969
+67200/69092	Loss: 107.845
+Training time 0:09:11.807624
+Epoch: 15 Average loss: 110.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 944)
+0/69092	Loss: 105.307
+3200/69092	Loss: 111.676
+6400/69092	Loss: 109.680
+9600/69092	Loss: 109.625
+12800/69092	Loss: 110.054
+16000/69092	Loss: 109.262
+19200/69092	Loss: 109.855
+22400/69092	Loss: 110.965
+25600/69092	Loss: 109.726
+28800/69092	Loss: 109.252
+32000/69092	Loss: 109.909
+35200/69092	Loss: 111.014
+38400/69092	Loss: 110.435
+41600/69092	Loss: 109.251
+44800/69092	Loss: 109.878
+48000/69092	Loss: 111.149
+51200/69092	Loss: 109.453
+54400/69092	Loss: 109.171
+57600/69092	Loss: 109.580
+60800/69092	Loss: 109.357
+64000/69092	Loss: 109.625
+67200/69092	Loss: 108.985
+Training time 0:09:26.719826
+Epoch: 16 Average loss: 109.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 945)
+0/69092	Loss: 113.802
+3200/69092	Loss: 110.720
+6400/69092	Loss: 110.516
+9600/69092	Loss: 108.718
+12800/69092	Loss: 107.139
+16000/69092	Loss: 109.699
+19200/69092	Loss: 109.344
+22400/69092	Loss: 110.459
+25600/69092	Loss: 107.671
+28800/69092	Loss: 110.246
+32000/69092	Loss: 110.141
+35200/69092	Loss: 110.000
+38400/69092	Loss: 110.684
+41600/69092	Loss: 111.225
+44800/69092	Loss: 109.754
+48000/69092	Loss: 109.640
+51200/69092	Loss: 110.313
+54400/69092	Loss: 109.681
+57600/69092	Loss: 109.847
+60800/69092	Loss: 108.549
+64000/69092	Loss: 110.907
+67200/69092	Loss: 110.284
+Training time 0:09:12.625890
+Epoch: 17 Average loss: 109.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 946)
+0/69092	Loss: 111.809
+3200/69092	Loss: 109.939
+6400/69092	Loss: 110.058
+9600/69092	Loss: 111.377
+12800/69092	Loss: 109.438
+16000/69092	Loss: 109.248
+19200/69092	Loss: 110.895
+22400/69092	Loss: 108.640
+25600/69092	Loss: 109.818
+28800/69092	Loss: 109.075
+32000/69092	Loss: 110.351
+35200/69092	Loss: 110.844
+38400/69092	Loss: 109.181
+41600/69092	Loss: 110.982
+44800/69092	Loss: 110.268
+48000/69092	Loss: 107.615
+51200/69092	Loss: 109.679
+54400/69092	Loss: 110.259
+57600/69092	Loss: 109.615
+60800/69092	Loss: 109.567
+64000/69092	Loss: 111.875
+67200/69092	Loss: 109.233
+Training time 0:09:52.886644
+Epoch: 18 Average loss: 109.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 947)
+0/69092	Loss: 121.056
+3200/69092	Loss: 109.085
+6400/69092	Loss: 108.729
+9600/69092	Loss: 108.968
+12800/69092	Loss: 109.767
+16000/69092	Loss: 108.967
+19200/69092	Loss: 111.042
+22400/69092	Loss: 109.615
+25600/69092	Loss: 109.796
+28800/69092	Loss: 111.178
+32000/69092	Loss: 110.762
+35200/69092	Loss: 109.985
+38400/69092	Loss: 109.131
+41600/69092	Loss: 110.685
+44800/69092	Loss: 110.775
+48000/69092	Loss: 109.219
+51200/69092	Loss: 111.029
+54400/69092	Loss: 109.122
+57600/69092	Loss: 109.873
+60800/69092	Loss: 110.023
+64000/69092	Loss: 111.547
+67200/69092	Loss: 109.169
+Training time 0:09:44.186610
+Epoch: 19 Average loss: 109.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 948)
+0/69092	Loss: 120.552
+3200/69092	Loss: 110.605
+6400/69092	Loss: 107.976
+9600/69092	Loss: 108.576
+12800/69092	Loss: 111.709
+16000/69092	Loss: 110.319
+19200/69092	Loss: 110.571
+22400/69092	Loss: 109.953
+25600/69092	Loss: 111.655
+28800/69092	Loss: 111.242
+32000/69092	Loss: 110.470
+35200/69092	Loss: 110.478
+38400/69092	Loss: 109.851
+41600/69092	Loss: 109.894
+44800/69092	Loss: 108.003
+48000/69092	Loss: 109.420
+51200/69092	Loss: 108.525
+54400/69092	Loss: 110.392
+57600/69092	Loss: 108.462
+60800/69092	Loss: 109.949
+64000/69092	Loss: 110.202
+67200/69092	Loss: 110.703
+Training time 0:10:10.724932
+Epoch: 20 Average loss: 109.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 949)
+0/69092	Loss: 104.065
+3200/69092	Loss: 109.470
+6400/69092	Loss: 110.471
+9600/69092	Loss: 110.790
+12800/69092	Loss: 109.120
+16000/69092	Loss: 110.503
+19200/69092	Loss: 110.451
+22400/69092	Loss: 110.142
+25600/69092	Loss: 110.279
+28800/69092	Loss: 109.611
+32000/69092	Loss: 109.450
+35200/69092	Loss: 110.025
+38400/69092	Loss: 111.676
+41600/69092	Loss: 109.132
+44800/69092	Loss: 112.366
+48000/69092	Loss: 109.355
+51200/69092	Loss: 109.265
+54400/69092	Loss: 109.478
+57600/69092	Loss: 110.828
+60800/69092	Loss: 110.748
+64000/69092	Loss: 109.204
+67200/69092	Loss: 109.576
+Training time 0:09:52.822086
+Epoch: 21 Average loss: 110.08
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 950)
+0/69092	Loss: 118.232
+3200/69092	Loss: 109.740
+6400/69092	Loss: 110.399
+9600/69092	Loss: 109.924
+12800/69092	Loss: 110.311
+16000/69092	Loss: 108.396
+19200/69092	Loss: 109.673
+22400/69092	Loss: 109.302
+25600/69092	Loss: 109.713
+28800/69092	Loss: 110.154
+32000/69092	Loss: 109.289
+35200/69092	Loss: 110.692
+38400/69092	Loss: 109.124
+41600/69092	Loss: 109.018
+44800/69092	Loss: 109.421
+48000/69092	Loss: 110.402
+51200/69092	Loss: 110.834
+54400/69092	Loss: 109.512
+57600/69092	Loss: 109.451
+60800/69092	Loss: 110.875
+64000/69092	Loss: 111.067
+67200/69092	Loss: 110.912
+Training time 0:09:33.053883
+Epoch: 22 Average loss: 109.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 951)
+0/69092	Loss: 114.726
+3200/69092	Loss: 108.914
+6400/69092	Loss: 109.178
+9600/69092	Loss: 110.064
+12800/69092	Loss: 109.048
+16000/69092	Loss: 111.037
+19200/69092	Loss: 110.549
+22400/69092	Loss: 109.868
+25600/69092	Loss: 110.990
+28800/69092	Loss: 110.111
+32000/69092	Loss: 110.393
+35200/69092	Loss: 111.285
+38400/69092	Loss: 111.660
+41600/69092	Loss: 109.019
+44800/69092	Loss: 110.090
+48000/69092	Loss: 112.044
+51200/69092	Loss: 110.454
+54400/69092	Loss: 109.942
+57600/69092	Loss: 108.834
+60800/69092	Loss: 110.020
+64000/69092	Loss: 109.516
+67200/69092	Loss: 108.459
+Training time 0:09:57.172410
+Epoch: 23 Average loss: 110.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 952)
+0/69092	Loss: 116.534
+3200/69092	Loss: 109.546
+6400/69092	Loss: 109.347
+9600/69092	Loss: 110.519
+12800/69092	Loss: 110.451
+16000/69092	Loss: 108.098
+19200/69092	Loss: 111.323
+22400/69092	Loss: 109.167
+25600/69092	Loss: 110.024
+28800/69092	Loss: 109.614
+32000/69092	Loss: 109.767
+35200/69092	Loss: 109.853
+38400/69092	Loss: 109.708
+41600/69092	Loss: 110.470
+44800/69092	Loss: 110.592
+48000/69092	Loss: 111.614
+51200/69092	Loss: 107.394
+54400/69092	Loss: 109.627
+57600/69092	Loss: 109.404
+60800/69092	Loss: 111.589
+64000/69092	Loss: 109.854
+67200/69092	Loss: 109.504
+Training time 0:09:35.857220
+Epoch: 24 Average loss: 109.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 953)
+0/69092	Loss: 114.948
+3200/69092	Loss: 110.611
+6400/69092	Loss: 108.821
+9600/69092	Loss: 111.068
+12800/69092	Loss: 108.951
+16000/69092	Loss: 110.240
+19200/69092	Loss: 109.077
+22400/69092	Loss: 111.071
+25600/69092	Loss: 110.978
+28800/69092	Loss: 109.945
+32000/69092	Loss: 109.387
+35200/69092	Loss: 109.972
+38400/69092	Loss: 110.315
+41600/69092	Loss: 109.124
+44800/69092	Loss: 109.530
+48000/69092	Loss: 110.762
+51200/69092	Loss: 111.401
+54400/69092	Loss: 110.935
+57600/69092	Loss: 108.048
+60800/69092	Loss: 109.378
+64000/69092	Loss: 110.239
+67200/69092	Loss: 108.000
+Training time 0:09:50.045880
+Epoch: 25 Average loss: 109.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 954)
+0/69092	Loss: 108.966
+3200/69092	Loss: 109.257
+6400/69092	Loss: 111.118
+9600/69092	Loss: 111.533
+12800/69092	Loss: 110.944
+16000/69092	Loss: 108.941
+19200/69092	Loss: 108.917
+22400/69092	Loss: 110.003
+25600/69092	Loss: 109.403
+28800/69092	Loss: 107.755
+32000/69092	Loss: 109.971
+35200/69092	Loss: 111.855
+38400/69092	Loss: 109.217
+41600/69092	Loss: 109.742
+44800/69092	Loss: 109.509
+48000/69092	Loss: 109.871
+51200/69092	Loss: 109.661
+54400/69092	Loss: 109.472
+57600/69092	Loss: 109.827
+60800/69092	Loss: 109.931
+64000/69092	Loss: 110.080
+67200/69092	Loss: 110.577
+Training time 0:09:41.761523
+Epoch: 26 Average loss: 109.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 955)
+0/69092	Loss: 113.490
+3200/69092	Loss: 110.245
+6400/69092	Loss: 109.807
+9600/69092	Loss: 109.717
+12800/69092	Loss: 110.373
+16000/69092	Loss: 108.715
+19200/69092	Loss: 109.860
+22400/69092	Loss: 110.857
+25600/69092	Loss: 109.997
+28800/69092	Loss: 109.488
+32000/69092	Loss: 110.274
+35200/69092	Loss: 110.355
+38400/69092	Loss: 108.761
+41600/69092	Loss: 108.724
+44800/69092	Loss: 109.370
+48000/69092	Loss: 110.335
+51200/69092	Loss: 108.635
+54400/69092	Loss: 110.619
+57600/69092	Loss: 111.014
+60800/69092	Loss: 108.825
+64000/69092	Loss: 111.314
+67200/69092	Loss: 111.589
+Training time 0:09:25.650776
+Epoch: 27 Average loss: 109.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 956)
+0/69092	Loss: 120.477
+3200/69092	Loss: 109.018
+6400/69092	Loss: 108.904
+9600/69092	Loss: 110.672
+12800/69092	Loss: 110.287
+16000/69092	Loss: 108.620
+19200/69092	Loss: 109.111
+22400/69092	Loss: 108.832
+25600/69092	Loss: 109.338
+28800/69092	Loss: 110.201
+32000/69092	Loss: 109.797
+35200/69092	Loss: 110.017
+38400/69092	Loss: 110.777
+41600/69092	Loss: 108.246
+44800/69092	Loss: 111.980
+48000/69092	Loss: 110.694
+51200/69092	Loss: 110.802
+54400/69092	Loss: 108.300
+57600/69092	Loss: 109.641
+60800/69092	Loss: 110.005
+64000/69092	Loss: 109.531
+67200/69092	Loss: 109.301
+Training time 0:10:06.221637
+Epoch: 28 Average loss: 109.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 957)
+0/69092	Loss: 114.162
+3200/69092	Loss: 111.305
+6400/69092	Loss: 110.024
+9600/69092	Loss: 110.596
+12800/69092	Loss: 110.251
+16000/69092	Loss: 109.079
+19200/69092	Loss: 110.062
+22400/69092	Loss: 108.918
+25600/69092	Loss: 108.469
+28800/69092	Loss: 108.788
+32000/69092	Loss: 110.630
+35200/69092	Loss: 109.170
+38400/69092	Loss: 108.325
+41600/69092	Loss: 108.816
+44800/69092	Loss: 109.323
+48000/69092	Loss: 108.733
+51200/69092	Loss: 109.662
+54400/69092	Loss: 109.448
+57600/69092	Loss: 108.393
+60800/69092	Loss: 111.194
+64000/69092	Loss: 111.564
+67200/69092	Loss: 112.045
+Training time 0:10:00.302035
+Epoch: 29 Average loss: 109.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 958)
+0/69092	Loss: 120.257
+3200/69092	Loss: 110.266
+6400/69092	Loss: 109.394
+9600/69092	Loss: 111.054
+12800/69092	Loss: 109.159
+16000/69092	Loss: 109.892
+19200/69092	Loss: 110.296
+22400/69092	Loss: 109.802
+25600/69092	Loss: 110.835
+28800/69092	Loss: 111.544
+32000/69092	Loss: 108.179
+35200/69092	Loss: 109.584
+38400/69092	Loss: 108.839
+41600/69092	Loss: 108.886
+44800/69092	Loss: 109.983
+48000/69092	Loss: 110.458
+51200/69092	Loss: 109.782
+54400/69092	Loss: 110.509
+57600/69092	Loss: 110.375
+60800/69092	Loss: 109.690
+64000/69092	Loss: 109.546
+67200/69092	Loss: 109.349
+Training time 0:09:22.565747
+Epoch: 30 Average loss: 109.87
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 959)
+0/69092	Loss: 101.501
+3200/69092	Loss: 111.831
+6400/69092	Loss: 109.255
+9600/69092	Loss: 110.849
+12800/69092	Loss: 109.357
+16000/69092	Loss: 109.907
+19200/69092	Loss: 107.548
+22400/69092	Loss: 109.430
+25600/69092	Loss: 108.791
+28800/69092	Loss: 110.252
+32000/69092	Loss: 109.824
+35200/69092	Loss: 112.214
+38400/69092	Loss: 112.134
+41600/69092	Loss: 108.836
+44800/69092	Loss: 108.572
+48000/69092	Loss: 108.661
+51200/69092	Loss: 109.338
+54400/69092	Loss: 108.989
+57600/69092	Loss: 110.290
+60800/69092	Loss: 111.544
+64000/69092	Loss: 111.172
+67200/69092	Loss: 108.555
+Training time 0:09:50.181810
+Epoch: 31 Average loss: 109.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 960)
+0/69092	Loss: 106.285
+3200/69092	Loss: 109.912
+6400/69092	Loss: 110.195
+9600/69092	Loss: 111.441
+12800/69092	Loss: 110.403
+16000/69092	Loss: 110.787
+19200/69092	Loss: 110.337
+22400/69092	Loss: 110.172
+25600/69092	Loss: 109.134
+28800/69092	Loss: 108.633
+32000/69092	Loss: 109.388
+35200/69092	Loss: 109.763
+38400/69092	Loss: 108.487
+41600/69092	Loss: 112.454
+44800/69092	Loss: 110.194
+48000/69092	Loss: 108.854
+51200/69092	Loss: 109.895
+54400/69092	Loss: 109.460
+57600/69092	Loss: 108.417
+60800/69092	Loss: 110.385
+64000/69092	Loss: 108.397
+67200/69092	Loss: 109.865
+Training time 0:09:43.513921
+Epoch: 32 Average loss: 109.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 961)
+0/69092	Loss: 105.236
+3200/69092	Loss: 110.641
+6400/69092	Loss: 108.153
+9600/69092	Loss: 109.300
+12800/69092	Loss: 110.016
+16000/69092	Loss: 107.980
+19200/69092	Loss: 109.421
+22400/69092	Loss: 109.703
+25600/69092	Loss: 109.869
+28800/69092	Loss: 108.514
+32000/69092	Loss: 109.813
+35200/69092	Loss: 111.234
+38400/69092	Loss: 109.531
+41600/69092	Loss: 110.015
+44800/69092	Loss: 111.334
+48000/69092	Loss: 110.539
+51200/69092	Loss: 109.409
+54400/69092	Loss: 110.580
+57600/69092	Loss: 110.200
+60800/69092	Loss: 110.545
+64000/69092	Loss: 112.061
+67200/69092	Loss: 107.346
+Training time 0:09:51.386182
+Epoch: 33 Average loss: 109.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 962)
+0/69092	Loss: 105.681
+3200/69092	Loss: 109.930
+6400/69092	Loss: 109.296
+9600/69092	Loss: 108.854
+12800/69092	Loss: 111.702
+16000/69092	Loss: 110.686
+19200/69092	Loss: 110.924
+22400/69092	Loss: 109.627
+25600/69092	Loss: 109.565
+28800/69092	Loss: 109.815
+32000/69092	Loss: 110.394
+35200/69092	Loss: 110.393
+38400/69092	Loss: 109.578
+41600/69092	Loss: 109.206
+44800/69092	Loss: 110.162
+48000/69092	Loss: 112.173
+51200/69092	Loss: 110.605
+54400/69092	Loss: 109.455
+57600/69092	Loss: 108.654
+60800/69092	Loss: 110.267
+64000/69092	Loss: 110.371
+67200/69092	Loss: 109.031
+Training time 0:09:41.182116
+Epoch: 34 Average loss: 110.04
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 963)
+0/69092	Loss: 112.134
+3200/69092	Loss: 109.169
+6400/69092	Loss: 111.367
+9600/69092	Loss: 112.611
+12800/69092	Loss: 111.506
+16000/69092	Loss: 110.327
+19200/69092	Loss: 108.402
+22400/69092	Loss: 109.891
+25600/69092	Loss: 111.112
+28800/69092	Loss: 110.181
+32000/69092	Loss: 108.794
+35200/69092	Loss: 109.571
+38400/69092	Loss: 108.670
+41600/69092	Loss: 109.831
+44800/69092	Loss: 110.149
+48000/69092	Loss: 109.229
+51200/69092	Loss: 109.133
+54400/69092	Loss: 108.624
+57600/69092	Loss: 108.969
+60800/69092	Loss: 110.683
+64000/69092	Loss: 109.818
+67200/69092	Loss: 111.161
+Training time 0:09:52.128525
+Epoch: 35 Average loss: 109.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 964)
+0/69092	Loss: 114.526
+3200/69092	Loss: 110.310
+6400/69092	Loss: 110.633
+9600/69092	Loss: 110.568
+12800/69092	Loss: 109.060
+16000/69092	Loss: 110.985
+19200/69092	Loss: 108.260
+22400/69092	Loss: 110.367
+25600/69092	Loss: 110.945
+28800/69092	Loss: 109.573
+32000/69092	Loss: 109.710
+35200/69092	Loss: 110.429
+38400/69092	Loss: 109.824
+41600/69092	Loss: 110.823
+44800/69092	Loss: 110.113
+48000/69092	Loss: 109.942
+51200/69092	Loss: 110.036
+54400/69092	Loss: 110.054
+57600/69092	Loss: 110.635
+60800/69092	Loss: 109.760
+64000/69092	Loss: 110.688
+67200/69092	Loss: 109.500
+Training time 0:09:15.753527
+Epoch: 36 Average loss: 110.04
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 965)
+0/69092	Loss: 112.070
+3200/69092	Loss: 109.720
+6400/69092	Loss: 108.799
+9600/69092	Loss: 110.789
+12800/69092	Loss: 109.991
+16000/69092	Loss: 110.895
+19200/69092	Loss: 111.490
+22400/69092	Loss: 110.167
+25600/69092	Loss: 110.909
+28800/69092	Loss: 108.727
+32000/69092	Loss: 108.645
+35200/69092	Loss: 111.309
+38400/69092	Loss: 109.048
+41600/69092	Loss: 107.036
+44800/69092	Loss: 110.065
+48000/69092	Loss: 111.331
+51200/69092	Loss: 109.395
+54400/69092	Loss: 109.773
+57600/69092	Loss: 111.569
+60800/69092	Loss: 110.082
+64000/69092	Loss: 108.185
+67200/69092	Loss: 110.942
+Training time 0:10:07.344917
+Epoch: 37 Average loss: 109.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 966)
+0/69092	Loss: 107.227
+3200/69092	Loss: 111.389
+6400/69092	Loss: 109.520
+9600/69092	Loss: 111.971
+12800/69092	Loss: 112.437
+16000/69092	Loss: 108.659
+19200/69092	Loss: 109.152
+22400/69092	Loss: 109.504
+25600/69092	Loss: 108.105
+28800/69092	Loss: 110.015
+32000/69092	Loss: 110.482
+35200/69092	Loss: 111.777
+38400/69092	Loss: 108.966
+41600/69092	Loss: 109.310
+44800/69092	Loss: 109.582
+48000/69092	Loss: 109.455
+51200/69092	Loss: 109.546
+54400/69092	Loss: 109.138
+57600/69092	Loss: 110.364
+60800/69092	Loss: 109.687
+64000/69092	Loss: 110.955
+67200/69092	Loss: 111.744
+Training time 0:09:38.915663
+Epoch: 38 Average loss: 110.08
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 967)
+0/69092	Loss: 116.668
+3200/69092	Loss: 110.969
+6400/69092	Loss: 111.258
+9600/69092	Loss: 109.870
+12800/69092	Loss: 110.244
+16000/69092	Loss: 110.560
+19200/69092	Loss: 111.165
+22400/69092	Loss: 110.855
+25600/69092	Loss: 108.306
+28800/69092	Loss: 111.792
+32000/69092	Loss: 108.635
+35200/69092	Loss: 109.326
+38400/69092	Loss: 109.116
+41600/69092	Loss: 110.282
+44800/69092	Loss: 109.264
+48000/69092	Loss: 110.383
+51200/69092	Loss: 110.432
+54400/69092	Loss: 109.699
+57600/69092	Loss: 109.611
+60800/69092	Loss: 109.165
+64000/69092	Loss: 109.302
+67200/69092	Loss: 109.116
+Training time 0:10:03.208954
+Epoch: 39 Average loss: 109.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 968)
+0/69092	Loss: 106.118
+3200/69092	Loss: 109.839
+6400/69092	Loss: 109.228
+9600/69092	Loss: 108.848
+12800/69092	Loss: 110.868
+16000/69092	Loss: 108.699
+19200/69092	Loss: 111.005
+22400/69092	Loss: 110.430
+25600/69092	Loss: 108.667
+28800/69092	Loss: 110.014
+32000/69092	Loss: 109.441
+35200/69092	Loss: 111.826
+38400/69092	Loss: 109.252
+41600/69092	Loss: 109.109
+44800/69092	Loss: 110.185
+48000/69092	Loss: 110.136
+51200/69092	Loss: 109.378
+54400/69092	Loss: 110.570
+57600/69092	Loss: 109.370
+60800/69092	Loss: 110.731
+64000/69092	Loss: 109.241
+67200/69092	Loss: 111.206
+Training time 0:09:47.254470
+Epoch: 40 Average loss: 109.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 969)
+0/69092	Loss: 109.406
+3200/69092	Loss: 109.696
+6400/69092	Loss: 108.612
+9600/69092	Loss: 109.655
+12800/69092	Loss: 109.373
+16000/69092	Loss: 109.559
+19200/69092	Loss: 110.542
+22400/69092	Loss: 109.307
+25600/69092	Loss: 108.919
+28800/69092	Loss: 111.054
+32000/69092	Loss: 111.290
+35200/69092	Loss: 110.409
+38400/69092	Loss: 109.053
+41600/69092	Loss: 108.477
+44800/69092	Loss: 110.485
+48000/69092	Loss: 108.989
+51200/69092	Loss: 110.306
+54400/69092	Loss: 109.712
+57600/69092	Loss: 110.063
+60800/69092	Loss: 108.970
+64000/69092	Loss: 111.053
+67200/69092	Loss: 110.489
+Training time 0:09:58.241010
+Epoch: 41 Average loss: 109.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 970)
+0/69092	Loss: 100.507
+3200/69092	Loss: 109.880
+6400/69092	Loss: 107.740
+9600/69092	Loss: 109.030
+12800/69092	Loss: 109.416
+16000/69092	Loss: 111.196
+19200/69092	Loss: 110.674
+22400/69092	Loss: 110.185
+25600/69092	Loss: 109.566
+28800/69092	Loss: 109.042
+32000/69092	Loss: 111.826
+35200/69092	Loss: 110.544
+38400/69092	Loss: 111.217
+41600/69092	Loss: 107.811
+44800/69092	Loss: 109.904
+48000/69092	Loss: 109.952
+51200/69092	Loss: 110.781
+54400/69092	Loss: 110.210
+57600/69092	Loss: 109.358
+60800/69092	Loss: 109.899
+64000/69092	Loss: 110.180
+67200/69092	Loss: 110.480
+Training time 0:08:48.771073
+Epoch: 42 Average loss: 109.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 971)
+0/69092	Loss: 97.424
+3200/69092	Loss: 108.734
+6400/69092	Loss: 110.472
+9600/69092	Loss: 109.192
+12800/69092	Loss: 109.264
+16000/69092	Loss: 110.462
+19200/69092	Loss: 108.597
+22400/69092	Loss: 109.893
+25600/69092	Loss: 111.866
+28800/69092	Loss: 111.663
+32000/69092	Loss: 109.090
+35200/69092	Loss: 108.511
+38400/69092	Loss: 109.332
+41600/69092	Loss: 110.090
+44800/69092	Loss: 109.573
+48000/69092	Loss: 108.026
+51200/69092	Loss: 108.783
+54400/69092	Loss: 112.529
+57600/69092	Loss: 110.637
+60800/69092	Loss: 110.479
+64000/69092	Loss: 109.171
+67200/69092	Loss: 109.733
+Training time 0:09:22.529668
+Epoch: 43 Average loss: 109.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 972)
+0/69092	Loss: 108.482
+3200/69092	Loss: 108.730
+6400/69092	Loss: 109.494
+9600/69092	Loss: 109.743
+12800/69092	Loss: 110.783
+16000/69092	Loss: 110.607
+19200/69092	Loss: 108.334
+22400/69092	Loss: 111.401
+25600/69092	Loss: 109.842
+28800/69092	Loss: 112.170
+32000/69092	Loss: 110.730
+35200/69092	Loss: 109.330
+38400/69092	Loss: 109.702
+41600/69092	Loss: 109.205
+44800/69092	Loss: 110.101
+48000/69092	Loss: 109.739
+51200/69092	Loss: 109.359
+54400/69092	Loss: 108.733
+57600/69092	Loss: 109.831
+60800/69092	Loss: 110.282
+64000/69092	Loss: 109.607
+67200/69092	Loss: 109.492
+Training time 0:09:36.389770
+Epoch: 44 Average loss: 109.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 973)
+0/69092	Loss: 102.352
+3200/69092	Loss: 108.933
+6400/69092	Loss: 109.283
+9600/69092	Loss: 110.233
+12800/69092	Loss: 109.919
+16000/69092	Loss: 110.649
+19200/69092	Loss: 111.195
+22400/69092	Loss: 108.622
+25600/69092	Loss: 110.896
+28800/69092	Loss: 109.175
+32000/69092	Loss: 109.308
+35200/69092	Loss: 109.722
+38400/69092	Loss: 109.405
+41600/69092	Loss: 111.334
+44800/69092	Loss: 110.206
+48000/69092	Loss: 110.267
+51200/69092	Loss: 110.190
+54400/69092	Loss: 111.104
+57600/69092	Loss: 110.619
+60800/69092	Loss: 110.805
+64000/69092	Loss: 109.691
+67200/69092	Loss: 109.607
+Training time 0:09:58.939143
+Epoch: 45 Average loss: 110.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 974)
+0/69092	Loss: 111.265
+3200/69092	Loss: 109.269
+6400/69092	Loss: 109.937
+9600/69092	Loss: 109.679
+12800/69092	Loss: 111.503
+16000/69092	Loss: 110.008
+19200/69092	Loss: 110.346
+22400/69092	Loss: 109.575
+25600/69092	Loss: 110.278
+28800/69092	Loss: 111.269
+32000/69092	Loss: 108.933
+35200/69092	Loss: 110.774
+38400/69092	Loss: 110.337
+41600/69092	Loss: 110.050
+44800/69092	Loss: 108.639
+48000/69092	Loss: 110.814
+51200/69092	Loss: 110.735
+54400/69092	Loss: 108.723
+57600/69092	Loss: 110.659
+60800/69092	Loss: 109.278
+64000/69092	Loss: 109.848
+67200/69092	Loss: 109.435
+Training time 0:09:35.743267
+Epoch: 46 Average loss: 109.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 975)
+0/69092	Loss: 109.214
+3200/69092	Loss: 109.049
+6400/69092	Loss: 109.434
+9600/69092	Loss: 110.284
+12800/69092	Loss: 109.220
+16000/69092	Loss: 109.914
+19200/69092	Loss: 110.088
+22400/69092	Loss: 109.476
+25600/69092	Loss: 110.059
+28800/69092	Loss: 107.733
+32000/69092	Loss: 109.633
+35200/69092	Loss: 109.344
+38400/69092	Loss: 110.374
+41600/69092	Loss: 110.799
+44800/69092	Loss: 111.761
+48000/69092	Loss: 109.216
+51200/69092	Loss: 110.465
+54400/69092	Loss: 110.636
+57600/69092	Loss: 109.732
+60800/69092	Loss: 109.485
+64000/69092	Loss: 110.342
+67200/69092	Loss: 110.162
+Training time 0:09:19.166558
+Epoch: 47 Average loss: 109.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 976)
+0/69092	Loss: 118.404
+3200/69092	Loss: 109.027
+6400/69092	Loss: 110.159
+9600/69092	Loss: 109.710
+12800/69092	Loss: 111.096
+16000/69092	Loss: 111.408
+19200/69092	Loss: 109.845
+22400/69092	Loss: 110.383
+25600/69092	Loss: 108.485
+28800/69092	Loss: 109.666
+32000/69092	Loss: 108.974
+35200/69092	Loss: 108.683
+38400/69092	Loss: 109.937
+41600/69092	Loss: 109.915
+44800/69092	Loss: 108.205
+48000/69092	Loss: 110.005
+51200/69092	Loss: 110.277
+54400/69092	Loss: 110.747
+57600/69092	Loss: 109.642
+60800/69092	Loss: 110.752
+64000/69092	Loss: 109.346
+67200/69092	Loss: 110.103
+Training time 0:09:42.947738
+Epoch: 48 Average loss: 109.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 977)
+0/69092	Loss: 106.546
+3200/69092	Loss: 109.017
+6400/69092	Loss: 108.551
+9600/69092	Loss: 109.321
+12800/69092	Loss: 109.615
+16000/69092	Loss: 109.119
+19200/69092	Loss: 108.870
+22400/69092	Loss: 109.374
+25600/69092	Loss: 109.933
+28800/69092	Loss: 110.945
+32000/69092	Loss: 111.118
+35200/69092	Loss: 110.164
+38400/69092	Loss: 112.185
+41600/69092	Loss: 109.893
+44800/69092	Loss: 110.876
+48000/69092	Loss: 112.349
+51200/69092	Loss: 110.187
+54400/69092	Loss: 108.540
+57600/69092	Loss: 108.920
+60800/69092	Loss: 109.402
+64000/69092	Loss: 109.512
+67200/69092	Loss: 109.407
+Training time 0:09:41.600229
+Epoch: 49 Average loss: 109.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 978)
+0/69092	Loss: 107.909
+3200/69092	Loss: 111.014
+6400/69092	Loss: 109.225
+9600/69092	Loss: 111.137
+12800/69092	Loss: 108.936
+16000/69092	Loss: 109.933
+19200/69092	Loss: 109.868
+22400/69092	Loss: 110.730
+25600/69092	Loss: 109.578
+28800/69092	Loss: 110.765
+32000/69092	Loss: 110.477
+35200/69092	Loss: 109.832
+38400/69092	Loss: 107.875
+41600/69092	Loss: 110.056
+44800/69092	Loss: 110.030
+48000/69092	Loss: 110.290
+51200/69092	Loss: 110.623
+54400/69092	Loss: 109.520
+57600/69092	Loss: 109.983
+60800/69092	Loss: 110.018
+64000/69092	Loss: 109.151
+67200/69092	Loss: 109.756
+Training time 0:10:11.591850
+Epoch: 50 Average loss: 109.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 979)
+0/69092	Loss: 112.156
+3200/69092	Loss: 109.854
+6400/69092	Loss: 110.461
+9600/69092	Loss: 110.673
+12800/69092	Loss: 111.879
+16000/69092	Loss: 109.466
+19200/69092	Loss: 109.672
+22400/69092	Loss: 109.746
+25600/69092	Loss: 111.687
+28800/69092	Loss: 109.142
+32000/69092	Loss: 108.274
+35200/69092	Loss: 111.291
+38400/69092	Loss: 109.810
+41600/69092	Loss: 110.519
+44800/69092	Loss: 109.559
+48000/69092	Loss: 110.053
+51200/69092	Loss: 110.924
+54400/69092	Loss: 109.901
+57600/69092	Loss: 108.652
+60800/69092	Loss: 111.050
+64000/69092	Loss: 111.523
+67200/69092	Loss: 108.035
+Training time 0:09:45.646408
+Epoch: 51 Average loss: 110.12
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 980)
+0/69092	Loss: 101.501
+3200/69092	Loss: 108.269
+6400/69092	Loss: 108.893
+9600/69092	Loss: 110.595
+12800/69092	Loss: 111.328
+16000/69092	Loss: 109.985
+19200/69092	Loss: 111.817
+22400/69092	Loss: 110.348
+25600/69092	Loss: 110.134
+28800/69092	Loss: 110.653
+32000/69092	Loss: 109.158
+35200/69092	Loss: 109.740
+38400/69092	Loss: 108.855
+41600/69092	Loss: 107.795
+44800/69092	Loss: 110.023
+48000/69092	Loss: 110.564
+51200/69092	Loss: 110.052
+54400/69092	Loss: 110.068
+57600/69092	Loss: 108.919
+60800/69092	Loss: 109.091
+64000/69092	Loss: 108.404
+67200/69092	Loss: 110.457
+Training time 0:09:17.648649
+Epoch: 52 Average loss: 109.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 981)
+0/69092	Loss: 101.706
+3200/69092	Loss: 109.731
+6400/69092	Loss: 109.818
+9600/69092	Loss: 109.548
+12800/69092	Loss: 109.297
+16000/69092	Loss: 109.530
+19200/69092	Loss: 109.890
+22400/69092	Loss: 111.203
+25600/69092	Loss: 109.603
+28800/69092	Loss: 109.654
+32000/69092	Loss: 109.072
+35200/69092	Loss: 109.657
+38400/69092	Loss: 111.192
+41600/69092	Loss: 108.345
+44800/69092	Loss: 110.009
+48000/69092	Loss: 109.572
+51200/69092	Loss: 109.907
+54400/69092	Loss: 109.328
+57600/69092	Loss: 110.764
+60800/69092	Loss: 110.277
+64000/69092	Loss: 111.131
+67200/69092	Loss: 109.490
+Training time 0:09:41.020852
+Epoch: 53 Average loss: 109.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 982)
+0/69092	Loss: 109.952
+3200/69092	Loss: 109.830
+6400/69092	Loss: 109.407
+9600/69092	Loss: 110.096
+12800/69092	Loss: 110.872
+16000/69092	Loss: 108.535
+19200/69092	Loss: 109.442
+22400/69092	Loss: 109.445
+25600/69092	Loss: 111.682
+28800/69092	Loss: 111.811
+32000/69092	Loss: 111.540
+35200/69092	Loss: 109.166
+38400/69092	Loss: 110.722
+41600/69092	Loss: 109.629
+44800/69092	Loss: 108.566
+48000/69092	Loss: 109.898
+51200/69092	Loss: 109.739
+54400/69092	Loss: 108.083
+57600/69092	Loss: 109.780
+60800/69092	Loss: 110.278
+64000/69092	Loss: 108.752
+67200/69092	Loss: 111.432
+Training time 0:09:46.076131
+Epoch: 54 Average loss: 109.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 983)
+0/69092	Loss: 121.892
+3200/69092	Loss: 108.674
+6400/69092	Loss: 109.927
+9600/69092	Loss: 110.736
+12800/69092	Loss: 110.426
+16000/69092	Loss: 109.523
+19200/69092	Loss: 110.060
+22400/69092	Loss: 108.039
+25600/69092	Loss: 107.462
+28800/69092	Loss: 109.517
+32000/69092	Loss: 110.880
+35200/69092	Loss: 109.724
+38400/69092	Loss: 110.802
+41600/69092	Loss: 110.441
+44800/69092	Loss: 108.906
+48000/69092	Loss: 110.964
+51200/69092	Loss: 109.531
+54400/69092	Loss: 109.213
+57600/69092	Loss: 110.660
+60800/69092	Loss: 109.762
+64000/69092	Loss: 110.440
+67200/69092	Loss: 110.185
+Training time 0:09:49.341124
+Epoch: 55 Average loss: 109.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 984)
+0/69092	Loss: 113.341
+3200/69092	Loss: 109.095
+6400/69092	Loss: 108.640
+9600/69092	Loss: 108.830
+12800/69092	Loss: 111.374
+16000/69092	Loss: 110.970
+19200/69092	Loss: 110.596
+22400/69092	Loss: 110.321
+25600/69092	Loss: 110.362
+28800/69092	Loss: 110.848
+32000/69092	Loss: 110.161
+35200/69092	Loss: 109.474
+38400/69092	Loss: 109.632
+41600/69092	Loss: 110.097
+44800/69092	Loss: 109.438
+48000/69092	Loss: 112.429
+51200/69092	Loss: 108.416
+54400/69092	Loss: 110.355
+57600/69092	Loss: 108.922
+60800/69092	Loss: 109.368
+64000/69092	Loss: 111.265
+67200/69092	Loss: 110.665
+Training time 0:09:44.359444
+Epoch: 56 Average loss: 110.08
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 985)
+0/69092	Loss: 111.494
+3200/69092	Loss: 109.323
+6400/69092	Loss: 108.265
+9600/69092	Loss: 109.550
+12800/69092	Loss: 109.469
+16000/69092	Loss: 110.305
+19200/69092	Loss: 110.053
+22400/69092	Loss: 110.847
+25600/69092	Loss: 108.924
+28800/69092	Loss: 109.990
+32000/69092	Loss: 110.945
+35200/69092	Loss: 109.409
+38400/69092	Loss: 110.815
+41600/69092	Loss: 110.350
+44800/69092	Loss: 108.901
+48000/69092	Loss: 111.284
+51200/69092	Loss: 108.817
+54400/69092	Loss: 109.965
+57600/69092	Loss: 110.244
+60800/69092	Loss: 108.327
+64000/69092	Loss: 109.514
+67200/69092	Loss: 112.023
+Training time 0:09:30.398458
+Epoch: 57 Average loss: 109.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 986)
+0/69092	Loss: 106.285
+3200/69092	Loss: 109.579
+6400/69092	Loss: 109.837
+9600/69092	Loss: 110.065
+12800/69092	Loss: 108.229
+16000/69092	Loss: 110.524
+19200/69092	Loss: 109.901
+22400/69092	Loss: 108.604
+25600/69092	Loss: 111.377
+28800/69092	Loss: 109.274
+32000/69092	Loss: 109.278
+35200/69092	Loss: 109.899
+38400/69092	Loss: 110.892
+41600/69092	Loss: 108.955
+44800/69092	Loss: 112.049
+48000/69092	Loss: 108.945
+51200/69092	Loss: 109.392
+54400/69092	Loss: 108.316
+57600/69092	Loss: 110.040
+60800/69092	Loss: 110.416
+64000/69092	Loss: 108.352
+67200/69092	Loss: 109.836
+Training time 0:09:28.147049
+Epoch: 58 Average loss: 109.69
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 987)
+0/69092	Loss: 103.122
+3200/69092	Loss: 111.554
+6400/69092	Loss: 109.099
+9600/69092	Loss: 111.845
+12800/69092	Loss: 108.626
+16000/69092	Loss: 110.425
+19200/69092	Loss: 107.408
+22400/69092	Loss: 109.022
+25600/69092	Loss: 111.299
+28800/69092	Loss: 109.599
+32000/69092	Loss: 111.397
+35200/69092	Loss: 108.244
+38400/69092	Loss: 111.585
+41600/69092	Loss: 107.838
+44800/69092	Loss: 109.274
+48000/69092	Loss: 109.108
+51200/69092	Loss: 111.564
+54400/69092	Loss: 109.191
+57600/69092	Loss: 109.630
+60800/69092	Loss: 110.144
+64000/69092	Loss: 109.201
+67200/69092	Loss: 110.112
+Training time 0:09:36.235021
+Epoch: 59 Average loss: 109.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 988)
+0/69092	Loss: 123.109
+3200/69092	Loss: 108.975
+6400/69092	Loss: 109.180
+9600/69092	Loss: 109.837
+12800/69092	Loss: 109.390
+16000/69092	Loss: 110.148
+19200/69092	Loss: 111.012
+22400/69092	Loss: 109.610
+25600/69092	Loss: 110.018
+28800/69092	Loss: 108.966
+32000/69092	Loss: 109.625
+35200/69092	Loss: 109.780
+38400/69092	Loss: 111.556
+41600/69092	Loss: 110.248
+44800/69092	Loss: 108.438
+48000/69092	Loss: 110.413
+51200/69092	Loss: 109.611
+54400/69092	Loss: 109.966
+57600/69092	Loss: 111.923
+60800/69092	Loss: 110.398
+64000/69092	Loss: 109.762
+67200/69092	Loss: 109.835
+Training time 0:09:11.918238
+Epoch: 60 Average loss: 109.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 989)
+0/69092	Loss: 105.415
+3200/69092	Loss: 110.537
+6400/69092	Loss: 110.251
+9600/69092	Loss: 109.671
+12800/69092	Loss: 109.485
+16000/69092	Loss: 108.863
+19200/69092	Loss: 109.272
+22400/69092	Loss: 108.404
+25600/69092	Loss: 109.038
+28800/69092	Loss: 109.038
+32000/69092	Loss: 108.874
+35200/69092	Loss: 108.531
+38400/69092	Loss: 108.546
+41600/69092	Loss: 110.151
+44800/69092	Loss: 110.604
+48000/69092	Loss: 110.680
+51200/69092	Loss: 110.508
+54400/69092	Loss: 111.268
+57600/69092	Loss: 110.676
+60800/69092	Loss: 111.323
+64000/69092	Loss: 109.621
+67200/69092	Loss: 110.589
+Training time 0:09:09.201319
+Epoch: 61 Average loss: 109.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 990)
+0/69092	Loss: 100.039
+3200/69092	Loss: 108.597
+6400/69092	Loss: 109.372
+9600/69092	Loss: 108.721
+12800/69092	Loss: 110.140
+16000/69092	Loss: 112.095
+19200/69092	Loss: 108.828
+22400/69092	Loss: 107.849
+25600/69092	Loss: 110.122
+28800/69092	Loss: 108.723
+32000/69092	Loss: 111.523
+35200/69092	Loss: 108.691
+38400/69092	Loss: 108.834
+41600/69092	Loss: 109.112
+44800/69092	Loss: 110.776
+48000/69092	Loss: 110.508
+51200/69092	Loss: 110.540
+54400/69092	Loss: 111.413
+57600/69092	Loss: 110.860
+60800/69092	Loss: 110.604
+64000/69092	Loss: 109.456
+67200/69092	Loss: 109.998
+Training time 0:09:13.271082
+Epoch: 62 Average loss: 109.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 991)
+0/69092	Loss: 105.217
+3200/69092	Loss: 108.260
+6400/69092	Loss: 109.037
+9600/69092	Loss: 109.386
+12800/69092	Loss: 110.773
+16000/69092	Loss: 110.668
+19200/69092	Loss: 110.454
+22400/69092	Loss: 108.660
+25600/69092	Loss: 109.772
+28800/69092	Loss: 111.190
+32000/69092	Loss: 109.384
+35200/69092	Loss: 109.839
+38400/69092	Loss: 110.429
+41600/69092	Loss: 108.888
+44800/69092	Loss: 111.115
+48000/69092	Loss: 111.268
+51200/69092	Loss: 109.302
+54400/69092	Loss: 109.219
+57600/69092	Loss: 109.040
+60800/69092	Loss: 109.891
+64000/69092	Loss: 110.585
+67200/69092	Loss: 109.202
+Training time 0:09:53.661757
+Epoch: 63 Average loss: 109.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 992)
+0/69092	Loss: 114.394
+3200/69092	Loss: 110.287
+6400/69092	Loss: 109.858
+9600/69092	Loss: 109.631
+12800/69092	Loss: 108.753
+16000/69092	Loss: 110.775
+19200/69092	Loss: 110.479
+22400/69092	Loss: 109.279
+25600/69092	Loss: 109.588
+28800/69092	Loss: 111.930
+32000/69092	Loss: 110.633
+35200/69092	Loss: 110.082
+38400/69092	Loss: 109.884
+41600/69092	Loss: 108.452
+44800/69092	Loss: 111.604
+48000/69092	Loss: 109.282
+51200/69092	Loss: 109.625
+54400/69092	Loss: 109.731
+57600/69092	Loss: 109.520
+60800/69092	Loss: 110.393
+64000/69092	Loss: 110.963
+67200/69092	Loss: 108.692
+Training time 0:10:01.127425
+Epoch: 64 Average loss: 109.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 993)
+0/69092	Loss: 124.592
+3200/69092	Loss: 111.549
+6400/69092	Loss: 108.144
+9600/69092	Loss: 111.863
+12800/69092	Loss: 108.554
+16000/69092	Loss: 109.531
+19200/69092	Loss: 109.053
+22400/69092	Loss: 110.155
+25600/69092	Loss: 109.716
+28800/69092	Loss: 109.811
+32000/69092	Loss: 111.223
+35200/69092	Loss: 110.118
+38400/69092	Loss: 109.607
+41600/69092	Loss: 110.438
+44800/69092	Loss: 111.005
+48000/69092	Loss: 110.132
+51200/69092	Loss: 109.334
+54400/69092	Loss: 111.077
+57600/69092	Loss: 108.757
+60800/69092	Loss: 108.986
+64000/69092	Loss: 108.796
+67200/69092	Loss: 109.112
+Training time 0:09:28.934546
+Epoch: 65 Average loss: 109.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 994)
+0/69092	Loss: 113.085
+3200/69092	Loss: 109.984
+6400/69092	Loss: 109.336
+9600/69092	Loss: 108.569
+12800/69092	Loss: 110.443
+16000/69092	Loss: 109.225
+19200/69092	Loss: 107.671
+22400/69092	Loss: 110.237
+25600/69092	Loss: 110.015
+28800/69092	Loss: 109.258
+32000/69092	Loss: 110.251
+35200/69092	Loss: 110.588
+38400/69092	Loss: 107.606
+41600/69092	Loss: 110.622
+44800/69092	Loss: 108.248
+48000/69092	Loss: 109.229
+51200/69092	Loss: 110.027
+54400/69092	Loss: 109.947
+57600/69092	Loss: 108.869
+60800/69092	Loss: 110.331
+64000/69092	Loss: 110.448
+67200/69092	Loss: 112.286
+Training time 0:09:40.542536
+Epoch: 66 Average loss: 109.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 995)
+0/69092	Loss: 97.397
+3200/69092	Loss: 110.222
+6400/69092	Loss: 108.274
+9600/69092	Loss: 108.580
+12800/69092	Loss: 108.344
+16000/69092	Loss: 108.800
+19200/69092	Loss: 109.966
+22400/69092	Loss: 108.440
+25600/69092	Loss: 109.934
+28800/69092	Loss: 109.907
+32000/69092	Loss: 110.779
+35200/69092	Loss: 109.471
+38400/69092	Loss: 111.230
+41600/69092	Loss: 109.748
+44800/69092	Loss: 109.718
+48000/69092	Loss: 110.817
+51200/69092	Loss: 109.607
+54400/69092	Loss: 113.029
+57600/69092	Loss: 109.430
+60800/69092	Loss: 110.483
+64000/69092	Loss: 110.092
+67200/69092	Loss: 108.999
+Training time 0:09:24.931054
+Epoch: 67 Average loss: 109.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 996)
+0/69092	Loss: 106.747
+3200/69092	Loss: 110.110
+6400/69092	Loss: 109.859
+9600/69092	Loss: 109.335
+12800/69092	Loss: 110.085
+16000/69092	Loss: 110.960
+19200/69092	Loss: 107.890
+22400/69092	Loss: 109.852
+25600/69092	Loss: 109.056
+28800/69092	Loss: 108.131
+32000/69092	Loss: 109.659
+35200/69092	Loss: 109.327
+38400/69092	Loss: 108.499
+41600/69092	Loss: 109.629
+44800/69092	Loss: 110.013
+48000/69092	Loss: 108.801
+51200/69092	Loss: 113.158
+54400/69092	Loss: 111.023
+57600/69092	Loss: 110.505
+60800/69092	Loss: 109.891
+64000/69092	Loss: 109.350
+67200/69092	Loss: 110.297
+Training time 0:09:43.835147
+Epoch: 68 Average loss: 109.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 997)
+0/69092	Loss: 108.101
+3200/69092	Loss: 110.397
+6400/69092	Loss: 111.182
+9600/69092	Loss: 108.486
+12800/69092	Loss: 108.786
+16000/69092	Loss: 110.345
+19200/69092	Loss: 110.101
+22400/69092	Loss: 111.738
+25600/69092	Loss: 110.922
+28800/69092	Loss: 111.029
+32000/69092	Loss: 108.959
+35200/69092	Loss: 110.008
+38400/69092	Loss: 109.716
+41600/69092	Loss: 108.448
+44800/69092	Loss: 109.556
+48000/69092	Loss: 109.331
+51200/69092	Loss: 110.988
+54400/69092	Loss: 110.148
+57600/69092	Loss: 111.302
+60800/69092	Loss: 109.180
+64000/69092	Loss: 109.729
+67200/69092	Loss: 109.619
+Training time 0:09:44.479689
+Epoch: 69 Average loss: 109.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 998)
+0/69092	Loss: 115.747
+3200/69092	Loss: 109.115
+6400/69092	Loss: 109.722
+9600/69092	Loss: 109.877
+12800/69092	Loss: 109.241
+16000/69092	Loss: 111.992
+19200/69092	Loss: 110.075
+22400/69092	Loss: 110.275
+25600/69092	Loss: 109.895
+28800/69092	Loss: 108.509
+32000/69092	Loss: 111.236
+35200/69092	Loss: 109.932
+38400/69092	Loss: 109.302
+41600/69092	Loss: 109.825
+44800/69092	Loss: 109.411
+48000/69092	Loss: 111.387
+51200/69092	Loss: 108.784
+54400/69092	Loss: 108.532
+57600/69092	Loss: 109.904
+60800/69092	Loss: 106.965
+64000/69092	Loss: 110.552
+67200/69092	Loss: 110.410
+Training time 0:09:49.124762
+Epoch: 70 Average loss: 109.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 999)
+0/69092	Loss: 107.647
+3200/69092	Loss: 108.965
+6400/69092	Loss: 109.347
+9600/69092	Loss: 110.007
+12800/69092	Loss: 108.295
+16000/69092	Loss: 109.995
+19200/69092	Loss: 110.010
+22400/69092	Loss: 108.392
+25600/69092	Loss: 109.654
+28800/69092	Loss: 109.507
+32000/69092	Loss: 110.031
+35200/69092	Loss: 109.458
+38400/69092	Loss: 111.370
+41600/69092	Loss: 111.002
+44800/69092	Loss: 110.555
+48000/69092	Loss: 110.261
+51200/69092	Loss: 110.595
+54400/69092	Loss: 110.098
+57600/69092	Loss: 109.914
+60800/69092	Loss: 110.619
+64000/69092	Loss: 109.567
+67200/69092	Loss: 109.967
+Training time 0:10:03.921722
+Epoch: 71 Average loss: 109.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1000)
+0/69092	Loss: 118.594
+3200/69092	Loss: 110.543
+6400/69092	Loss: 109.169
+9600/69092	Loss: 110.722
+12800/69092	Loss: 109.839
+16000/69092	Loss: 108.879
+19200/69092	Loss: 108.609
+22400/69092	Loss: 109.130
+25600/69092	Loss: 110.224
+28800/69092	Loss: 109.102
+32000/69092	Loss: 110.978
+35200/69092	Loss: 111.166
+38400/69092	Loss: 109.473
+41600/69092	Loss: 110.275
+44800/69092	Loss: 109.078
+48000/69092	Loss: 109.106
+51200/69092	Loss: 109.655
+54400/69092	Loss: 109.283
+57600/69092	Loss: 110.331
+60800/69092	Loss: 109.908
+64000/69092	Loss: 109.906
+67200/69092	Loss: 109.922
+Training time 0:09:33.178170
+Epoch: 72 Average loss: 109.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1001)
+0/69092	Loss: 112.799
+3200/69092	Loss: 109.679
+6400/69092	Loss: 111.202
+9600/69092	Loss: 108.047
+12800/69092	Loss: 108.761
+16000/69092	Loss: 111.232
+19200/69092	Loss: 110.988
+22400/69092	Loss: 109.701
+25600/69092	Loss: 109.150
+28800/69092	Loss: 109.186
+32000/69092	Loss: 110.029
+35200/69092	Loss: 110.936
+38400/69092	Loss: 108.429
+41600/69092	Loss: 108.890
+44800/69092	Loss: 110.743
+48000/69092	Loss: 109.363
+51200/69092	Loss: 110.464
+54400/69092	Loss: 110.645
+57600/69092	Loss: 109.414
+60800/69092	Loss: 109.350
+64000/69092	Loss: 110.205
+67200/69092	Loss: 110.112
+Training time 0:09:20.325148
+Epoch: 73 Average loss: 109.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1002)
+0/69092	Loss: 109.049
+3200/69092	Loss: 109.315
+6400/69092	Loss: 111.125
+9600/69092	Loss: 110.308
+12800/69092	Loss: 109.195
+16000/69092	Loss: 108.440
+19200/69092	Loss: 109.414
+22400/69092	Loss: 109.457
+25600/69092	Loss: 110.249
+28800/69092	Loss: 110.902
+32000/69092	Loss: 110.676
+35200/69092	Loss: 108.934
+38400/69092	Loss: 109.641
+41600/69092	Loss: 109.850
+44800/69092	Loss: 109.003
+48000/69092	Loss: 108.910
+51200/69092	Loss: 110.933
+54400/69092	Loss: 109.379
+57600/69092	Loss: 111.217
+60800/69092	Loss: 110.566
+64000/69092	Loss: 111.083
+67200/69092	Loss: 110.147
+Training time 0:09:18.817060
+Epoch: 74 Average loss: 109.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1003)
+0/69092	Loss: 113.316
+3200/69092	Loss: 110.840
+6400/69092	Loss: 108.996
+9600/69092	Loss: 108.585
+12800/69092	Loss: 111.286
+16000/69092	Loss: 110.721
+19200/69092	Loss: 108.523
+22400/69092	Loss: 112.089
+25600/69092	Loss: 110.240
+28800/69092	Loss: 109.134
+32000/69092	Loss: 107.603
+35200/69092	Loss: 108.369
+38400/69092	Loss: 109.229
+41600/69092	Loss: 109.751
+44800/69092	Loss: 109.388
+48000/69092	Loss: 110.182
+51200/69092	Loss: 110.072
+54400/69092	Loss: 110.621
+57600/69092	Loss: 110.260
+60800/69092	Loss: 108.966
+64000/69092	Loss: 109.899
+67200/69092	Loss: 109.657
+Training time 0:09:41.876870
+Epoch: 75 Average loss: 109.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1004)
+0/69092	Loss: 108.545
+3200/69092	Loss: 110.364
+6400/69092	Loss: 109.358
+9600/69092	Loss: 109.338
+12800/69092	Loss: 110.788
+16000/69092	Loss: 109.715
+19200/69092	Loss: 111.973
+22400/69092	Loss: 111.157
+25600/69092	Loss: 110.285
+28800/69092	Loss: 108.790
+32000/69092	Loss: 108.647
+35200/69092	Loss: 108.882
+38400/69092	Loss: 109.661
+41600/69092	Loss: 108.815
+44800/69092	Loss: 110.043
+48000/69092	Loss: 109.152
+51200/69092	Loss: 111.668
+54400/69092	Loss: 109.826
+57600/69092	Loss: 110.999
+60800/69092	Loss: 108.021
+64000/69092	Loss: 108.862
+67200/69092	Loss: 110.181
+Training time 0:09:26.932766
+Epoch: 76 Average loss: 109.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1005)
+0/69092	Loss: 106.649
+3200/69092	Loss: 109.473
+6400/69092	Loss: 108.214
+9600/69092	Loss: 110.899
+12800/69092	Loss: 111.050
+16000/69092	Loss: 111.746
+19200/69092	Loss: 111.725
+22400/69092	Loss: 110.145
+25600/69092	Loss: 107.743
+28800/69092	Loss: 108.278
+32000/69092	Loss: 110.150
+35200/69092	Loss: 109.135
+38400/69092	Loss: 110.270
+41600/69092	Loss: 110.072
+44800/69092	Loss: 108.288
+48000/69092	Loss: 110.426
+51200/69092	Loss: 110.937
+54400/69092	Loss: 109.174
+57600/69092	Loss: 110.854
+60800/69092	Loss: 109.001
+64000/69092	Loss: 109.816
+67200/69092	Loss: 109.748
+Training time 0:09:14.815503
+Epoch: 77 Average loss: 109.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1006)
+0/69092	Loss: 107.577
+3200/69092	Loss: 110.283
+6400/69092	Loss: 108.870
+9600/69092	Loss: 109.450
+12800/69092	Loss: 110.048
+16000/69092	Loss: 110.088
+19200/69092	Loss: 109.829
+22400/69092	Loss: 109.619
+25600/69092	Loss: 112.136
+28800/69092	Loss: 109.176
+32000/69092	Loss: 109.680
+35200/69092	Loss: 110.338
+38400/69092	Loss: 110.421
+41600/69092	Loss: 108.396
+44800/69092	Loss: 110.617
+48000/69092	Loss: 110.619
+51200/69092	Loss: 108.490
+54400/69092	Loss: 109.445
+57600/69092	Loss: 108.722
+60800/69092	Loss: 110.096
+64000/69092	Loss: 110.280
+67200/69092	Loss: 109.206
+Training time 0:09:37.734441
+Epoch: 78 Average loss: 109.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1007)
+0/69092	Loss: 106.134
+3200/69092	Loss: 110.379
+6400/69092	Loss: 109.738
+9600/69092	Loss: 108.363
+12800/69092	Loss: 110.382
+16000/69092	Loss: 110.460
+19200/69092	Loss: 111.037
+22400/69092	Loss: 108.616
+25600/69092	Loss: 109.653
+28800/69092	Loss: 108.912
+32000/69092	Loss: 109.741
+35200/69092	Loss: 108.693
+38400/69092	Loss: 110.167
+41600/69092	Loss: 109.229
+44800/69092	Loss: 110.012
+48000/69092	Loss: 108.464
+51200/69092	Loss: 110.584
+54400/69092	Loss: 109.751
+57600/69092	Loss: 110.138
+60800/69092	Loss: 112.825
+64000/69092	Loss: 110.273
+67200/69092	Loss: 111.704
+Training time 0:09:17.415925
+Epoch: 79 Average loss: 109.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1008)
+0/69092	Loss: 107.784
+3200/69092	Loss: 110.692
+6400/69092	Loss: 108.668
+9600/69092	Loss: 109.345
+12800/69092	Loss: 109.792
+16000/69092	Loss: 109.298
+19200/69092	Loss: 109.330
+22400/69092	Loss: 108.473
+25600/69092	Loss: 110.827
+28800/69092	Loss: 109.936
+32000/69092	Loss: 110.759
+35200/69092	Loss: 108.405
+38400/69092	Loss: 109.995
+41600/69092	Loss: 109.992
+44800/69092	Loss: 111.133
+48000/69092	Loss: 110.078
+51200/69092	Loss: 109.861
+54400/69092	Loss: 110.582
+57600/69092	Loss: 109.082
+60800/69092	Loss: 110.692
+64000/69092	Loss: 109.924
+67200/69092	Loss: 107.730
+Training time 0:10:21.716419
+Epoch: 80 Average loss: 109.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1009)
+0/69092	Loss: 102.824
+3200/69092	Loss: 108.845
+6400/69092	Loss: 109.087
+9600/69092	Loss: 109.198
+12800/69092	Loss: 110.312
+16000/69092	Loss: 108.578
+19200/69092	Loss: 112.176
+22400/69092	Loss: 111.468
+25600/69092	Loss: 108.801
+28800/69092	Loss: 108.657
+32000/69092	Loss: 110.375
+35200/69092	Loss: 110.812
+38400/69092	Loss: 108.511
+41600/69092	Loss: 109.230
+44800/69092	Loss: 110.693
+48000/69092	Loss: 109.914
+51200/69092	Loss: 110.365
+54400/69092	Loss: 109.667
+57600/69092	Loss: 108.246
+60800/69092	Loss: 110.866
+64000/69092	Loss: 113.160
+67200/69092	Loss: 109.737
+Training time 0:09:36.204113
+Epoch: 81 Average loss: 109.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1010)
+0/69092	Loss: 125.301
+3200/69092	Loss: 109.201
+6400/69092	Loss: 110.707
+9600/69092	Loss: 111.091
+12800/69092	Loss: 110.658
+16000/69092	Loss: 109.300
+19200/69092	Loss: 109.023
+22400/69092	Loss: 110.111
+25600/69092	Loss: 110.461
+28800/69092	Loss: 109.384
+32000/69092	Loss: 109.576
+35200/69092	Loss: 108.763
+38400/69092	Loss: 109.176
+41600/69092	Loss: 109.793
+44800/69092	Loss: 109.589
+48000/69092	Loss: 109.708
+51200/69092	Loss: 110.607
+54400/69092	Loss: 109.024
+57600/69092	Loss: 109.359
+60800/69092	Loss: 110.638
+64000/69092	Loss: 108.729
+67200/69092	Loss: 109.922
+Training time 0:09:49.207324
+Epoch: 82 Average loss: 109.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1011)
+0/69092	Loss: 119.929
+3200/69092	Loss: 109.484
+6400/69092	Loss: 109.469
+9600/69092	Loss: 110.071
+12800/69092	Loss: 109.051
+16000/69092	Loss: 110.493
+19200/69092	Loss: 108.444
+22400/69092	Loss: 110.623
+25600/69092	Loss: 110.420
+28800/69092	Loss: 109.818
+32000/69092	Loss: 111.495
+35200/69092	Loss: 109.353
+38400/69092	Loss: 109.717
+41600/69092	Loss: 108.863
+44800/69092	Loss: 109.813
+48000/69092	Loss: 110.053
+51200/69092	Loss: 110.612
+54400/69092	Loss: 109.759
+57600/69092	Loss: 109.951
+60800/69092	Loss: 110.782
+64000/69092	Loss: 109.413
+67200/69092	Loss: 109.006
+Training time 0:09:39.852423
+Epoch: 83 Average loss: 109.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1012)
+0/69092	Loss: 111.588
+3200/69092	Loss: 109.416
+6400/69092	Loss: 109.620
+9600/69092	Loss: 109.188
+12800/69092	Loss: 111.654
+16000/69092	Loss: 110.292
+19200/69092	Loss: 109.607
+22400/69092	Loss: 108.442
+25600/69092	Loss: 110.933
+28800/69092	Loss: 109.703
+32000/69092	Loss: 110.197
+35200/69092	Loss: 109.987
+38400/69092	Loss: 110.169
+41600/69092	Loss: 108.781
+44800/69092	Loss: 110.324
+48000/69092	Loss: 110.599
+51200/69092	Loss: 109.695
+54400/69092	Loss: 110.062
+57600/69092	Loss: 109.701
+60800/69092	Loss: 109.461
+64000/69092	Loss: 110.054
+67200/69092	Loss: 107.681
+Training time 0:09:25.142762
+Epoch: 84 Average loss: 109.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1013)
+0/69092	Loss: 109.571
+3200/69092	Loss: 109.031
+6400/69092	Loss: 109.771
+9600/69092	Loss: 110.375
+12800/69092	Loss: 109.589
+16000/69092	Loss: 109.147
+19200/69092	Loss: 109.089
+22400/69092	Loss: 111.161
+25600/69092	Loss: 108.664
+28800/69092	Loss: 111.310
+32000/69092	Loss: 109.502
+35200/69092	Loss: 108.561
+38400/69092	Loss: 110.799
+41600/69092	Loss: 111.300
+44800/69092	Loss: 108.675
+48000/69092	Loss: 109.183
+51200/69092	Loss: 110.578
+54400/69092	Loss: 109.389
+57600/69092	Loss: 109.447
+60800/69092	Loss: 108.056
+64000/69092	Loss: 108.214
+67200/69092	Loss: 111.012
+Training time 0:10:13.994843
+Epoch: 85 Average loss: 109.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1014)
+0/69092	Loss: 112.780
+3200/69092	Loss: 108.574
+6400/69092	Loss: 109.885
+9600/69092	Loss: 109.547
+12800/69092	Loss: 110.769
+16000/69092	Loss: 108.954
+19200/69092	Loss: 108.015
+22400/69092	Loss: 109.133
+25600/69092	Loss: 109.829
+28800/69092	Loss: 110.320
+32000/69092	Loss: 110.155
+35200/69092	Loss: 111.465
+38400/69092	Loss: 109.558
+41600/69092	Loss: 109.142
+44800/69092	Loss: 109.076
+48000/69092	Loss: 111.051
+51200/69092	Loss: 110.121
+54400/69092	Loss: 110.278
+57600/69092	Loss: 110.320
+60800/69092	Loss: 109.872
+64000/69092	Loss: 109.726
+67200/69092	Loss: 109.058
+Training time 0:08:56.056529
+Epoch: 86 Average loss: 109.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1015)
+0/69092	Loss: 107.917
+3200/69092	Loss: 111.276
+6400/69092	Loss: 110.195
+9600/69092	Loss: 109.494
+12800/69092	Loss: 107.208
+16000/69092	Loss: 109.486
+19200/69092	Loss: 107.497
+22400/69092	Loss: 110.254
+25600/69092	Loss: 110.503
+28800/69092	Loss: 108.188
+32000/69092	Loss: 110.412
+35200/69092	Loss: 108.955
+38400/69092	Loss: 110.508
+41600/69092	Loss: 110.555
+44800/69092	Loss: 110.181
+48000/69092	Loss: 110.595
+51200/69092	Loss: 110.906
+54400/69092	Loss: 108.903
+57600/69092	Loss: 108.610
+60800/69092	Loss: 109.911
+64000/69092	Loss: 110.248
+67200/69092	Loss: 110.041
+Training time 0:09:23.242808
+Epoch: 87 Average loss: 109.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1016)
+0/69092	Loss: 113.882
+3200/69092	Loss: 110.454
+6400/69092	Loss: 108.562
+9600/69092	Loss: 108.108
+12800/69092	Loss: 108.810
+16000/69092	Loss: 108.466
+19200/69092	Loss: 112.169
+22400/69092	Loss: 111.085
+25600/69092	Loss: 106.935
+28800/69092	Loss: 108.740
+32000/69092	Loss: 110.504
+35200/69092	Loss: 111.105
+38400/69092	Loss: 110.368
+41600/69092	Loss: 108.585
+44800/69092	Loss: 111.216
+48000/69092	Loss: 108.775
+51200/69092	Loss: 110.337
+54400/69092	Loss: 109.398
+57600/69092	Loss: 111.386
+60800/69092	Loss: 111.226
+64000/69092	Loss: 109.934
+67200/69092	Loss: 109.880
+Training time 0:09:58.719186
+Epoch: 88 Average loss: 109.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1017)
+0/69092	Loss: 121.694
+3200/69092	Loss: 109.305
+6400/69092	Loss: 111.168
+9600/69092	Loss: 108.614
+12800/69092	Loss: 110.991
+16000/69092	Loss: 110.530
+19200/69092	Loss: 109.723
+22400/69092	Loss: 111.063
+25600/69092	Loss: 108.987
+28800/69092	Loss: 110.451
+32000/69092	Loss: 108.577
+35200/69092	Loss: 110.236
+38400/69092	Loss: 108.561
+41600/69092	Loss: 110.788
+44800/69092	Loss: 109.295
+48000/69092	Loss: 109.576
+51200/69092	Loss: 109.856
+54400/69092	Loss: 108.123
+57600/69092	Loss: 110.158
+60800/69092	Loss: 108.592
+64000/69092	Loss: 110.925
+67200/69092	Loss: 110.493
+Training time 0:09:10.414518
+Epoch: 89 Average loss: 109.87
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1018)
+0/69092	Loss: 107.933
+3200/69092	Loss: 109.628
+6400/69092	Loss: 109.562
+9600/69092	Loss: 110.016
+12800/69092	Loss: 109.599
+16000/69092	Loss: 109.338
+19200/69092	Loss: 109.610
+22400/69092	Loss: 108.740
+25600/69092	Loss: 109.552
+28800/69092	Loss: 111.177
+32000/69092	Loss: 111.473
+35200/69092	Loss: 109.037
+38400/69092	Loss: 109.630
+41600/69092	Loss: 110.823
+44800/69092	Loss: 109.891
+48000/69092	Loss: 108.577
+51200/69092	Loss: 109.156
+54400/69092	Loss: 110.907
+57600/69092	Loss: 109.350
+60800/69092	Loss: 109.721
+64000/69092	Loss: 109.935
+67200/69092	Loss: 109.383
+Training time 0:10:01.381803
+Epoch: 90 Average loss: 109.72
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1019)
+0/69092	Loss: 105.488
+3200/69092	Loss: 109.993
+6400/69092	Loss: 108.548
+9600/69092	Loss: 109.358
+12800/69092	Loss: 112.093
+16000/69092	Loss: 109.583
+19200/69092	Loss: 110.206
+22400/69092	Loss: 109.316
+25600/69092	Loss: 110.051
+28800/69092	Loss: 109.831
+32000/69092	Loss: 108.229
+35200/69092	Loss: 110.691
+38400/69092	Loss: 111.654
+41600/69092	Loss: 108.031
+44800/69092	Loss: 109.460
+48000/69092	Loss: 110.520
+51200/69092	Loss: 108.553
+54400/69092	Loss: 110.351
+57600/69092	Loss: 110.559
+60800/69092	Loss: 111.436
+64000/69092	Loss: 107.854
+67200/69092	Loss: 109.612
+Training time 0:09:38.697834
+Epoch: 91 Average loss: 109.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1020)
+0/69092	Loss: 110.511
+3200/69092	Loss: 109.530
+6400/69092	Loss: 109.689
+9600/69092	Loss: 110.565
+12800/69092	Loss: 110.365
+16000/69092	Loss: 108.153
+19200/69092	Loss: 109.011
+22400/69092	Loss: 108.555
+25600/69092	Loss: 110.814
+28800/69092	Loss: 111.417
+32000/69092	Loss: 110.948
+35200/69092	Loss: 110.538
+38400/69092	Loss: 111.402
+41600/69092	Loss: 109.518
+44800/69092	Loss: 110.361
+48000/69092	Loss: 107.544
+51200/69092	Loss: 110.728
+54400/69092	Loss: 108.568
+57600/69092	Loss: 110.643
+60800/69092	Loss: 109.953
+64000/69092	Loss: 109.409
+67200/69092	Loss: 109.593
+Training time 0:09:45.541864
+Epoch: 92 Average loss: 109.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1021)
+0/69092	Loss: 111.638
+3200/69092	Loss: 108.933
+6400/69092	Loss: 110.042
+9600/69092	Loss: 109.028
+12800/69092	Loss: 111.549
+16000/69092	Loss: 109.567
+19200/69092	Loss: 111.713
+22400/69092	Loss: 110.468
+25600/69092	Loss: 109.413
+28800/69092	Loss: 110.228
+32000/69092	Loss: 110.307
+35200/69092	Loss: 111.018
+38400/69092	Loss: 109.335
+41600/69092	Loss: 109.025
+44800/69092	Loss: 110.623
+48000/69092	Loss: 109.383
+51200/69092	Loss: 111.323
+54400/69092	Loss: 109.346
+57600/69092	Loss: 110.475
+60800/69092	Loss: 108.192
+64000/69092	Loss: 107.599
+67200/69092	Loss: 109.680
+Training time 0:10:07.670400
+Epoch: 93 Average loss: 109.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1022)
+0/69092	Loss: 105.201
+3200/69092	Loss: 109.837
+6400/69092	Loss: 109.129
+9600/69092	Loss: 108.476
+12800/69092	Loss: 110.047
+16000/69092	Loss: 109.114
+19200/69092	Loss: 109.524
+22400/69092	Loss: 109.852
+25600/69092	Loss: 109.728
+28800/69092	Loss: 110.078
+32000/69092	Loss: 109.304
+35200/69092	Loss: 111.493
+38400/69092	Loss: 110.204
+41600/69092	Loss: 110.542
+44800/69092	Loss: 109.919
+48000/69092	Loss: 109.889
+51200/69092	Loss: 110.826
+54400/69092	Loss: 110.454
+57600/69092	Loss: 108.770
+60800/69092	Loss: 110.116
+64000/69092	Loss: 109.556
+67200/69092	Loss: 109.362
+Training time 0:10:03.553217
+Epoch: 94 Average loss: 109.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1023)
+0/69092	Loss: 113.933
+3200/69092	Loss: 110.499
+6400/69092	Loss: 110.261
+9600/69092	Loss: 108.775
+12800/69092	Loss: 110.982
+16000/69092	Loss: 109.711
+19200/69092	Loss: 109.999
+22400/69092	Loss: 109.285
+25600/69092	Loss: 109.997
+28800/69092	Loss: 110.283
+32000/69092	Loss: 110.563
+35200/69092	Loss: 109.477
+38400/69092	Loss: 108.412
+41600/69092	Loss: 109.553
+44800/69092	Loss: 111.806
+48000/69092	Loss: 110.547
+51200/69092	Loss: 109.685
+54400/69092	Loss: 109.348
+57600/69092	Loss: 108.907
+60800/69092	Loss: 108.768
+64000/69092	Loss: 108.654
+67200/69092	Loss: 109.497
+Training time 0:09:23.514495
+Epoch: 95 Average loss: 109.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1024)
+0/69092	Loss: 114.984
+3200/69092	Loss: 110.199
+6400/69092	Loss: 108.950
+9600/69092	Loss: 110.214
+12800/69092	Loss: 109.753
+16000/69092	Loss: 110.906
+19200/69092	Loss: 111.099
+22400/69092	Loss: 109.504
+25600/69092	Loss: 109.017
+28800/69092	Loss: 109.199
+32000/69092	Loss: 107.374
+35200/69092	Loss: 109.379
+38400/69092	Loss: 111.726
+41600/69092	Loss: 109.420
+44800/69092	Loss: 109.260
+48000/69092	Loss: 109.609
+51200/69092	Loss: 111.393
+54400/69092	Loss: 111.157
+57600/69092	Loss: 109.533
+60800/69092	Loss: 109.482
+64000/69092	Loss: 108.666
+67200/69092	Loss: 109.959
+Training time 0:09:47.455945
+Epoch: 96 Average loss: 109.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1025)
+0/69092	Loss: 100.810
+3200/69092	Loss: 108.833
+6400/69092	Loss: 109.290
+9600/69092	Loss: 108.656
+12800/69092	Loss: 110.082
+16000/69092	Loss: 110.122
+19200/69092	Loss: 109.032
+22400/69092	Loss: 109.852
+25600/69092	Loss: 110.275
+28800/69092	Loss: 108.503
+32000/69092	Loss: 110.206
+35200/69092	Loss: 109.903
+38400/69092	Loss: 109.936
+41600/69092	Loss: 109.757
+44800/69092	Loss: 109.150
+48000/69092	Loss: 110.557
+51200/69092	Loss: 111.725
+54400/69092	Loss: 110.015
+57600/69092	Loss: 110.343
+60800/69092	Loss: 110.034
+64000/69092	Loss: 109.841
+67200/69092	Loss: 109.808
+Training time 0:09:51.370142
+Epoch: 97 Average loss: 109.72
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1026)
+0/69092	Loss: 106.962
+3200/69092	Loss: 112.222
+6400/69092	Loss: 109.474
+9600/69092	Loss: 107.872
+12800/69092	Loss: 109.205
+16000/69092	Loss: 108.734
+19200/69092	Loss: 108.021
+22400/69092	Loss: 109.550
+25600/69092	Loss: 109.325
+28800/69092	Loss: 111.843
+32000/69092	Loss: 109.816
+35200/69092	Loss: 108.455
+38400/69092	Loss: 109.788
+41600/69092	Loss: 112.646
+44800/69092	Loss: 108.881
+48000/69092	Loss: 109.577
+51200/69092	Loss: 108.902
+54400/69092	Loss: 110.166
+57600/69092	Loss: 111.115
+60800/69092	Loss: 108.981
+64000/69092	Loss: 108.492
+67200/69092	Loss: 109.356
+Training time 0:10:01.797407
+Epoch: 98 Average loss: 109.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1027)
+0/69092	Loss: 106.664
+3200/69092	Loss: 110.525
+6400/69092	Loss: 109.000
+9600/69092	Loss: 110.405
+12800/69092	Loss: 110.037
+16000/69092	Loss: 110.775
+19200/69092	Loss: 110.007
+22400/69092	Loss: 109.335
+25600/69092	Loss: 108.334
+28800/69092	Loss: 109.193
+32000/69092	Loss: 108.213
+35200/69092	Loss: 109.007
+38400/69092	Loss: 109.760
+41600/69092	Loss: 110.103
+44800/69092	Loss: 112.318
+48000/69092	Loss: 110.290
+51200/69092	Loss: 109.312
+54400/69092	Loss: 110.620
+57600/69092	Loss: 111.824
+60800/69092	Loss: 110.067
+64000/69092	Loss: 109.046
+67200/69092	Loss: 110.197
+Training time 0:09:11.988133
+Epoch: 99 Average loss: 109.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1028)
+0/69092	Loss: 117.303
+3200/69092	Loss: 109.878
+6400/69092	Loss: 108.761
+9600/69092	Loss: 109.519
+12800/69092	Loss: 110.341
+16000/69092	Loss: 107.917
+19200/69092	Loss: 109.564
+22400/69092	Loss: 109.096
+25600/69092	Loss: 109.063
+28800/69092	Loss: 109.506
+32000/69092	Loss: 111.093
+35200/69092	Loss: 110.374
+38400/69092	Loss: 109.616
+41600/69092	Loss: 110.997
+44800/69092	Loss: 110.396
+48000/69092	Loss: 110.758
+51200/69092	Loss: 108.895
+54400/69092	Loss: 110.528
+57600/69092	Loss: 109.830
+60800/69092	Loss: 108.950
+64000/69092	Loss: 108.205
+67200/69092	Loss: 111.540
+Training time 0:09:04.067008
+Epoch: 100 Average loss: 109.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1029)
+0/69092	Loss: 108.615
+3200/69092	Loss: 109.045
+6400/69092	Loss: 108.881
+9600/69092	Loss: 108.749
+12800/69092	Loss: 110.520
+16000/69092	Loss: 109.214
+19200/69092	Loss: 109.291
+22400/69092	Loss: 110.409
+25600/69092	Loss: 109.112
+28800/69092	Loss: 108.544
+32000/69092	Loss: 110.211
+35200/69092	Loss: 110.129
+38400/69092	Loss: 110.640
+41600/69092	Loss: 110.482
+44800/69092	Loss: 108.933
+48000/69092	Loss: 109.136
+51200/69092	Loss: 111.123
+54400/69092	Loss: 109.426
+57600/69092	Loss: 110.706
+60800/69092	Loss: 109.224
+64000/69092	Loss: 110.943
+67200/69092	Loss: 109.007
+Training time 0:09:22.234257
+Epoch: 101 Average loss: 109.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1030)
+0/69092	Loss: 105.161
+3200/69092	Loss: 108.770
+6400/69092	Loss: 112.311
+9600/69092	Loss: 109.034
+12800/69092	Loss: 110.434
+16000/69092	Loss: 108.568
+19200/69092	Loss: 111.517
+22400/69092	Loss: 109.773
+25600/69092	Loss: 109.253
+28800/69092	Loss: 109.825
+32000/69092	Loss: 108.991
+35200/69092	Loss: 109.242
+38400/69092	Loss: 110.725
+41600/69092	Loss: 110.419
+44800/69092	Loss: 109.508
+48000/69092	Loss: 109.679
+51200/69092	Loss: 111.504
+54400/69092	Loss: 110.605
+57600/69092	Loss: 110.122
+60800/69092	Loss: 108.274
+64000/69092	Loss: 108.751
+67200/69092	Loss: 109.882
+Training time 0:09:46.206172
+Epoch: 102 Average loss: 109.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1031)
+0/69092	Loss: 104.835
+3200/69092	Loss: 109.757
+6400/69092	Loss: 109.933
+9600/69092	Loss: 109.402
+12800/69092	Loss: 110.283
+16000/69092	Loss: 109.118
+19200/69092	Loss: 110.138
+22400/69092	Loss: 110.425
+25600/69092	Loss: 108.842
+28800/69092	Loss: 108.635
+32000/69092	Loss: 110.231
+35200/69092	Loss: 110.879
+38400/69092	Loss: 108.665
+41600/69092	Loss: 109.739
+44800/69092	Loss: 110.391
+48000/69092	Loss: 110.893
+51200/69092	Loss: 110.228
+54400/69092	Loss: 107.698
+57600/69092	Loss: 109.917
+60800/69092	Loss: 108.718
+64000/69092	Loss: 110.239
+67200/69092	Loss: 110.007
+Training time 0:09:29.587165
+Epoch: 103 Average loss: 109.69
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1032)
+0/69092	Loss: 97.211
+3200/69092	Loss: 108.747
+6400/69092	Loss: 109.319
+9600/69092	Loss: 108.982
+12800/69092	Loss: 109.917
+16000/69092	Loss: 109.414
+19200/69092	Loss: 109.216
+22400/69092	Loss: 109.124
+25600/69092	Loss: 111.577
+28800/69092	Loss: 111.311
+32000/69092	Loss: 109.564
+35200/69092	Loss: 109.876
+38400/69092	Loss: 108.511
+41600/69092	Loss: 111.396
+44800/69092	Loss: 109.346
+48000/69092	Loss: 108.568
+51200/69092	Loss: 110.430
+54400/69092	Loss: 109.548
+57600/69092	Loss: 109.721
+60800/69092	Loss: 110.285
+64000/69092	Loss: 109.206
+67200/69092	Loss: 110.824
+Training time 0:09:36.574227
+Epoch: 104 Average loss: 109.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1033)
+0/69092	Loss: 99.769
+3200/69092	Loss: 111.336
+6400/69092	Loss: 109.473
+9600/69092	Loss: 109.632
+12800/69092	Loss: 109.469
+16000/69092	Loss: 108.645
+19200/69092	Loss: 109.888
+22400/69092	Loss: 110.738
+25600/69092	Loss: 110.015
+28800/69092	Loss: 110.484
+32000/69092	Loss: 109.706
+35200/69092	Loss: 109.046
+38400/69092	Loss: 108.697
+41600/69092	Loss: 109.263
+44800/69092	Loss: 108.629
+48000/69092	Loss: 110.666
+51200/69092	Loss: 109.243
+54400/69092	Loss: 110.916
+57600/69092	Loss: 109.194
+60800/69092	Loss: 110.094
+64000/69092	Loss: 108.391
+67200/69092	Loss: 109.667
+Training time 0:09:19.203192
+Epoch: 105 Average loss: 109.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1034)
+0/69092	Loss: 100.673
+3200/69092	Loss: 110.440
+6400/69092	Loss: 109.714
+9600/69092	Loss: 108.809
+12800/69092	Loss: 109.203
+16000/69092	Loss: 108.550
+19200/69092	Loss: 109.205
+22400/69092	Loss: 109.854
+25600/69092	Loss: 110.670
+28800/69092	Loss: 109.514
+32000/69092	Loss: 109.174
+35200/69092	Loss: 107.817
+38400/69092	Loss: 109.425
+41600/69092	Loss: 109.788
+44800/69092	Loss: 111.551
+48000/69092	Loss: 108.902
+51200/69092	Loss: 109.202
+54400/69092	Loss: 111.008
+57600/69092	Loss: 111.398
+60800/69092	Loss: 108.660
+64000/69092	Loss: 110.533
+67200/69092	Loss: 111.801
+Training time 0:09:32.195764
+Epoch: 106 Average loss: 109.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1035)
+0/69092	Loss: 107.852
+3200/69092	Loss: 109.844
+6400/69092	Loss: 108.862
+9600/69092	Loss: 109.532
+12800/69092	Loss: 110.358
+16000/69092	Loss: 110.058
+19200/69092	Loss: 109.570
+22400/69092	Loss: 109.834
+25600/69092	Loss: 109.349
+28800/69092	Loss: 109.583
+32000/69092	Loss: 110.571
+35200/69092	Loss: 110.343
+38400/69092	Loss: 110.389
+41600/69092	Loss: 108.817
+44800/69092	Loss: 109.810
+48000/69092	Loss: 110.297
+51200/69092	Loss: 109.093
+54400/69092	Loss: 110.081
+57600/69092	Loss: 108.565
+60800/69092	Loss: 107.888
+64000/69092	Loss: 112.007
+67200/69092	Loss: 108.203
+Training time 0:09:48.049972
+Epoch: 107 Average loss: 109.71
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1036)
+0/69092	Loss: 108.961
+3200/69092	Loss: 109.847
+6400/69092	Loss: 107.595
+9600/69092	Loss: 108.948
+12800/69092	Loss: 109.602
+16000/69092	Loss: 109.808
+19200/69092	Loss: 110.749
+22400/69092	Loss: 107.729
+25600/69092	Loss: 111.367
+28800/69092	Loss: 109.831
+32000/69092	Loss: 110.410
+35200/69092	Loss: 111.335
+38400/69092	Loss: 108.909
+41600/69092	Loss: 110.873
+44800/69092	Loss: 109.005
+48000/69092	Loss: 109.924
+51200/69092	Loss: 108.385
+54400/69092	Loss: 109.272
+57600/69092	Loss: 108.737
+60800/69092	Loss: 110.283
+64000/69092	Loss: 110.197
+67200/69092	Loss: 109.082
+Training time 0:09:25.813362
+Epoch: 108 Average loss: 109.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1037)
+0/69092	Loss: 104.737
+3200/69092	Loss: 107.895
+6400/69092	Loss: 110.195
+9600/69092	Loss: 110.515
+12800/69092	Loss: 109.102
+16000/69092	Loss: 109.259
+19200/69092	Loss: 110.609
+22400/69092	Loss: 112.155
+25600/69092	Loss: 110.839
+28800/69092	Loss: 110.589
+32000/69092	Loss: 111.350
+35200/69092	Loss: 110.317
+38400/69092	Loss: 109.830
+41600/69092	Loss: 107.723
+44800/69092	Loss: 108.015
+48000/69092	Loss: 109.564
+51200/69092	Loss: 109.720
+54400/69092	Loss: 108.484
+57600/69092	Loss: 108.624
+60800/69092	Loss: 109.319
+64000/69092	Loss: 108.665
+67200/69092	Loss: 110.095
+Training time 0:09:13.768742
+Epoch: 109 Average loss: 109.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1038)
+0/69092	Loss: 118.631
+3200/69092	Loss: 110.008
+6400/69092	Loss: 108.389
+9600/69092	Loss: 108.378
+12800/69092	Loss: 109.866
+16000/69092	Loss: 108.258
+19200/69092	Loss: 110.421
+22400/69092	Loss: 110.000
+25600/69092	Loss: 110.764
+28800/69092	Loss: 107.693
+32000/69092	Loss: 110.977
+35200/69092	Loss: 110.708
+38400/69092	Loss: 109.320
+41600/69092	Loss: 110.031
+44800/69092	Loss: 108.891
+48000/69092	Loss: 110.133
+51200/69092	Loss: 109.764
+54400/69092	Loss: 110.949
+57600/69092	Loss: 108.944
+60800/69092	Loss: 109.427
+64000/69092	Loss: 108.573
+67200/69092	Loss: 111.784
+Training time 0:09:28.379127
+Epoch: 110 Average loss: 109.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1039)
+0/69092	Loss: 109.007
+3200/69092	Loss: 109.353
+6400/69092	Loss: 109.569
+9600/69092	Loss: 111.380
+12800/69092	Loss: 109.205
+16000/69092	Loss: 109.867
+19200/69092	Loss: 108.848
+22400/69092	Loss: 110.716
+25600/69092	Loss: 110.442
+28800/69092	Loss: 107.853
+32000/69092	Loss: 108.066
+35200/69092	Loss: 109.971
+38400/69092	Loss: 111.199
+41600/69092	Loss: 108.968
+44800/69092	Loss: 109.452
+48000/69092	Loss: 109.601
+51200/69092	Loss: 111.401
+54400/69092	Loss: 110.805
+57600/69092	Loss: 110.561
+60800/69092	Loss: 110.180
+64000/69092	Loss: 109.264
+67200/69092	Loss: 109.635
+Training time 0:09:14.259632
+Epoch: 111 Average loss: 109.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1040)
+0/69092	Loss: 107.270
+3200/69092	Loss: 110.267
+6400/69092	Loss: 108.279
+9600/69092	Loss: 109.548
+12800/69092	Loss: 110.586
+16000/69092	Loss: 111.115
+19200/69092	Loss: 110.434
+22400/69092	Loss: 109.173
+25600/69092	Loss: 109.930
+28800/69092	Loss: 109.796
+32000/69092	Loss: 109.011
+35200/69092	Loss: 109.599
+38400/69092	Loss: 109.210
+41600/69092	Loss: 109.517
+44800/69092	Loss: 108.401
+48000/69092	Loss: 109.338
+51200/69092	Loss: 108.944
+54400/69092	Loss: 110.206
+57600/69092	Loss: 108.580
+60800/69092	Loss: 110.788
+64000/69092	Loss: 110.492
+67200/69092	Loss: 109.671
+Training time 0:10:05.020596
+Epoch: 112 Average loss: 109.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1041)
+0/69092	Loss: 103.943
+3200/69092	Loss: 109.070
+6400/69092	Loss: 110.108
+9600/69092	Loss: 108.602
+12800/69092	Loss: 108.847
+16000/69092	Loss: 110.279
+19200/69092	Loss: 110.721
+22400/69092	Loss: 108.053
+25600/69092	Loss: 109.302
+28800/69092	Loss: 108.853
+32000/69092	Loss: 111.674
+35200/69092	Loss: 110.295
+38400/69092	Loss: 110.385
+41600/69092	Loss: 109.194
+44800/69092	Loss: 110.531
+48000/69092	Loss: 108.591
+51200/69092	Loss: 110.524
+54400/69092	Loss: 110.434
+57600/69092	Loss: 109.951
+60800/69092	Loss: 109.009
+64000/69092	Loss: 108.467
+67200/69092	Loss: 110.865
+Training time 0:10:05.144603
+Epoch: 113 Average loss: 109.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1042)
+0/69092	Loss: 117.786
+3200/69092	Loss: 109.952
+6400/69092	Loss: 109.887
+9600/69092	Loss: 108.840
+12800/69092	Loss: 110.730
+16000/69092	Loss: 110.473
+19200/69092	Loss: 108.216
+22400/69092	Loss: 110.246
+25600/69092	Loss: 109.362
+28800/69092	Loss: 109.157
+32000/69092	Loss: 110.033
+35200/69092	Loss: 109.544
+38400/69092	Loss: 111.425
+41600/69092	Loss: 110.305
+44800/69092	Loss: 108.535
+48000/69092	Loss: 109.595
+51200/69092	Loss: 110.140
+54400/69092	Loss: 108.731
+57600/69092	Loss: 108.746
+60800/69092	Loss: 109.777
+64000/69092	Loss: 109.522
+67200/69092	Loss: 110.459
+Training time 0:09:33.808219
+Epoch: 114 Average loss: 109.73
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1043)
+0/69092	Loss: 101.102
+3200/69092	Loss: 109.834
+6400/69092	Loss: 109.711
+9600/69092	Loss: 107.910
+12800/69092	Loss: 110.702
+16000/69092	Loss: 109.310
+19200/69092	Loss: 109.566
+22400/69092	Loss: 110.473
+25600/69092	Loss: 110.729
+28800/69092	Loss: 108.766
+32000/69092	Loss: 109.291
+35200/69092	Loss: 110.111
+38400/69092	Loss: 109.225
+41600/69092	Loss: 108.910
+44800/69092	Loss: 111.090
+48000/69092	Loss: 110.506
+51200/69092	Loss: 111.418
+54400/69092	Loss: 109.853
+57600/69092	Loss: 109.346
+60800/69092	Loss: 108.679
+64000/69092	Loss: 108.943
+67200/69092	Loss: 109.387
+Training time 0:09:36.025684
+Epoch: 115 Average loss: 109.70
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1044)
+0/69092	Loss: 109.994
+3200/69092	Loss: 111.022
+6400/69092	Loss: 111.936
+9600/69092	Loss: 109.127
+12800/69092	Loss: 108.844
+16000/69092	Loss: 110.885
+19200/69092	Loss: 108.063
+22400/69092	Loss: 108.094
+25600/69092	Loss: 109.222
+28800/69092	Loss: 109.290
+32000/69092	Loss: 110.895
+35200/69092	Loss: 108.503
+38400/69092	Loss: 109.722
+41600/69092	Loss: 109.713
+44800/69092	Loss: 107.675
+48000/69092	Loss: 109.993
+51200/69092	Loss: 110.508
+54400/69092	Loss: 109.303
+57600/69092	Loss: 110.280
+60800/69092	Loss: 109.654
+64000/69092	Loss: 109.710
+67200/69092	Loss: 111.324
+Training time 0:09:28.185711
+Epoch: 116 Average loss: 109.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1045)
+0/69092	Loss: 111.285
+3200/69092	Loss: 107.845
+6400/69092	Loss: 110.331
+9600/69092	Loss: 108.492
+12800/69092	Loss: 108.827
+16000/69092	Loss: 109.325
+19200/69092	Loss: 111.362
+22400/69092	Loss: 110.073
+25600/69092	Loss: 110.690
+28800/69092	Loss: 109.958
+32000/69092	Loss: 109.319
+35200/69092	Loss: 109.035
+38400/69092	Loss: 110.854
+41600/69092	Loss: 108.351
+44800/69092	Loss: 110.231
+48000/69092	Loss: 110.652
+51200/69092	Loss: 108.416
+54400/69092	Loss: 110.815
+57600/69092	Loss: 111.250
+60800/69092	Loss: 108.693
+64000/69092	Loss: 109.240
+67200/69092	Loss: 110.689
+Training time 0:09:52.619903
+Epoch: 117 Average loss: 109.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1046)
+0/69092	Loss: 122.277
+3200/69092	Loss: 108.935
+6400/69092	Loss: 110.610
+9600/69092	Loss: 109.581
+12800/69092	Loss: 109.249
+16000/69092	Loss: 110.880
+19200/69092	Loss: 107.687
+22400/69092	Loss: 109.419
+25600/69092	Loss: 108.148
+28800/69092	Loss: 109.469
+32000/69092	Loss: 111.104
+35200/69092	Loss: 109.794
+38400/69092	Loss: 110.430
+41600/69092	Loss: 109.881
+44800/69092	Loss: 111.100
+48000/69092	Loss: 109.124
+51200/69092	Loss: 109.265
+54400/69092	Loss: 110.166
+57600/69092	Loss: 109.763
+60800/69092	Loss: 110.624
+64000/69092	Loss: 110.479
+67200/69092	Loss: 110.636
+Training time 0:10:10.514988
+Epoch: 118 Average loss: 109.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1047)
+0/69092	Loss: 118.996
+3200/69092	Loss: 109.490
+6400/69092	Loss: 109.521
+9600/69092	Loss: 109.954
+12800/69092	Loss: 108.905
+16000/69092	Loss: 111.313
+19200/69092	Loss: 108.448
+22400/69092	Loss: 110.653
+25600/69092	Loss: 109.203
+28800/69092	Loss: 110.807
+32000/69092	Loss: 108.112
+35200/69092	Loss: 109.618
+38400/69092	Loss: 110.085
+41600/69092	Loss: 108.057
+44800/69092	Loss: 110.644
+48000/69092	Loss: 109.436
+51200/69092	Loss: 109.163
+54400/69092	Loss: 110.263
+57600/69092	Loss: 109.872
+60800/69092	Loss: 111.295
+64000/69092	Loss: 110.021
+67200/69092	Loss: 109.977
+Training time 0:09:47.798493
+Epoch: 119 Average loss: 109.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1048)
+0/69092	Loss: 97.597
+3200/69092	Loss: 110.587
+6400/69092	Loss: 108.317
+9600/69092	Loss: 108.556
+12800/69092	Loss: 110.277
+16000/69092	Loss: 111.070
+19200/69092	Loss: 109.211
+22400/69092	Loss: 110.353
+25600/69092	Loss: 108.452
+28800/69092	Loss: 108.820
+32000/69092	Loss: 110.477
+35200/69092	Loss: 111.591
+38400/69092	Loss: 108.414
+41600/69092	Loss: 110.235
+44800/69092	Loss: 109.828
+48000/69092	Loss: 109.331
+51200/69092	Loss: 109.440
+54400/69092	Loss: 108.387
+57600/69092	Loss: 111.328
+60800/69092	Loss: 108.748
+64000/69092	Loss: 111.560
+67200/69092	Loss: 111.450
+Training time 0:09:50.345036
+Epoch: 120 Average loss: 109.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1049)
+0/69092	Loss: 107.182
+3200/69092	Loss: 108.845
+6400/69092	Loss: 108.401
+9600/69092	Loss: 110.517
+12800/69092	Loss: 111.282
+16000/69092	Loss: 109.767
+19200/69092	Loss: 110.072
+22400/69092	Loss: 108.609
+25600/69092	Loss: 109.492
+28800/69092	Loss: 108.905
+32000/69092	Loss: 109.233
+35200/69092	Loss: 110.270
+38400/69092	Loss: 110.617
+41600/69092	Loss: 107.933
+44800/69092	Loss: 109.198
+48000/69092	Loss: 109.188
+51200/69092	Loss: 110.372
+54400/69092	Loss: 109.893
+57600/69092	Loss: 108.692
+60800/69092	Loss: 111.128
+64000/69092	Loss: 108.969
+67200/69092	Loss: 110.155
+Training time 0:09:33.383641
+Epoch: 121 Average loss: 109.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1050)
+0/69092	Loss: 107.561
+3200/69092	Loss: 109.063
+6400/69092	Loss: 108.674
+9600/69092	Loss: 111.323
+12800/69092	Loss: 111.997
+16000/69092	Loss: 108.568
+19200/69092	Loss: 110.808
+22400/69092	Loss: 109.206
+25600/69092	Loss: 110.102
+28800/69092	Loss: 110.955
+32000/69092	Loss: 109.058
+35200/69092	Loss: 110.528
+38400/69092	Loss: 110.501
+41600/69092	Loss: 108.741
+44800/69092	Loss: 111.336
+48000/69092	Loss: 109.881
+51200/69092	Loss: 109.347
+54400/69092	Loss: 110.004
+57600/69092	Loss: 107.737
+60800/69092	Loss: 108.618
+64000/69092	Loss: 111.482
+67200/69092	Loss: 109.229
+Training time 0:09:36.757163
+Epoch: 122 Average loss: 109.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1051)
+0/69092	Loss: 112.618
+3200/69092	Loss: 109.690
+6400/69092	Loss: 109.943
+9600/69092	Loss: 109.097
+12800/69092	Loss: 110.720
+16000/69092	Loss: 108.858
+19200/69092	Loss: 109.588
+22400/69092	Loss: 109.564
+25600/69092	Loss: 109.486
+28800/69092	Loss: 110.333
+32000/69092	Loss: 108.842
+35200/69092	Loss: 108.787
+38400/69092	Loss: 110.222
+41600/69092	Loss: 110.047
+44800/69092	Loss: 111.034
+48000/69092	Loss: 109.025
+51200/69092	Loss: 110.521
+54400/69092	Loss: 110.585
+57600/69092	Loss: 109.221
+60800/69092	Loss: 109.705
+64000/69092	Loss: 110.547
+67200/69092	Loss: 111.281
+Training time 0:08:54.410304
+Epoch: 123 Average loss: 109.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1052)
+0/69092	Loss: 105.133
+3200/69092	Loss: 109.048
+6400/69092	Loss: 109.221
+9600/69092	Loss: 108.922
+12800/69092	Loss: 109.301
+16000/69092	Loss: 110.753
+19200/69092	Loss: 109.936
+22400/69092	Loss: 108.969
+25600/69092	Loss: 110.502
+28800/69092	Loss: 109.627
+32000/69092	Loss: 108.977
+35200/69092	Loss: 109.344
+38400/69092	Loss: 109.291
+41600/69092	Loss: 109.545
+44800/69092	Loss: 110.059
+48000/69092	Loss: 110.288
+51200/69092	Loss: 109.768
+54400/69092	Loss: 109.012
+57600/69092	Loss: 110.516
+60800/69092	Loss: 110.924
+64000/69092	Loss: 110.367
+67200/69092	Loss: 108.457
+Training time 0:09:36.806168
+Epoch: 124 Average loss: 109.72
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1053)
+0/69092	Loss: 114.895
+3200/69092	Loss: 109.157
+6400/69092	Loss: 110.336
+9600/69092	Loss: 109.060
+12800/69092	Loss: 109.916
+16000/69092	Loss: 109.966
+19200/69092	Loss: 110.500
+22400/69092	Loss: 108.774
+25600/69092	Loss: 109.018
+28800/69092	Loss: 109.723
+32000/69092	Loss: 108.612
+35200/69092	Loss: 110.469
+38400/69092	Loss: 110.947
+41600/69092	Loss: 108.073
+44800/69092	Loss: 109.292
+48000/69092	Loss: 108.629
+51200/69092	Loss: 110.383
+54400/69092	Loss: 109.498
+57600/69092	Loss: 108.565
+60800/69092	Loss: 111.926
+64000/69092	Loss: 109.617
+67200/69092	Loss: 110.363
+Training time 0:09:38.875681
+Epoch: 125 Average loss: 109.71
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1054)
+0/69092	Loss: 106.338
+3200/69092	Loss: 109.310
+6400/69092	Loss: 111.285
+9600/69092	Loss: 110.067
+12800/69092	Loss: 108.286
+16000/69092	Loss: 109.110
+19200/69092	Loss: 108.005
+22400/69092	Loss: 109.809
+25600/69092	Loss: 108.997
+28800/69092	Loss: 110.646
+32000/69092	Loss: 108.205
+35200/69092	Loss: 108.792
+38400/69092	Loss: 109.460
+41600/69092	Loss: 111.838
+44800/69092	Loss: 109.803
+48000/69092	Loss: 110.221
+51200/69092	Loss: 110.843
+54400/69092	Loss: 109.890
+57600/69092	Loss: 110.155
+60800/69092	Loss: 110.504
+64000/69092	Loss: 108.333
+67200/69092	Loss: 108.294
+Training time 0:09:22.440934
+Epoch: 126 Average loss: 109.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1055)
+0/69092	Loss: 113.913
+3200/69092	Loss: 109.517
+6400/69092	Loss: 109.728
+9600/69092	Loss: 110.323
+12800/69092	Loss: 109.655
+16000/69092	Loss: 108.962
+19200/69092	Loss: 108.562
+22400/69092	Loss: 108.490
+25600/69092	Loss: 109.994
+28800/69092	Loss: 110.248
+32000/69092	Loss: 109.974
+35200/69092	Loss: 109.774
+38400/69092	Loss: 108.949
+41600/69092	Loss: 109.853
+44800/69092	Loss: 109.374
+48000/69092	Loss: 112.275
+51200/69092	Loss: 110.004
+54400/69092	Loss: 110.049
+57600/69092	Loss: 110.466
+60800/69092	Loss: 108.552
+64000/69092	Loss: 108.873
+67200/69092	Loss: 109.560
+Training time 0:09:37.063552
+Epoch: 127 Average loss: 109.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1056)
+0/69092	Loss: 117.734
+3200/69092	Loss: 109.726
+6400/69092	Loss: 109.372
+9600/69092	Loss: 109.028
+12800/69092	Loss: 111.126
+16000/69092	Loss: 109.814
+19200/69092	Loss: 109.864
+22400/69092	Loss: 109.095
+25600/69092	Loss: 110.321
+28800/69092	Loss: 109.822
+32000/69092	Loss: 108.665
+35200/69092	Loss: 110.830
+38400/69092	Loss: 108.969
+41600/69092	Loss: 109.819
+44800/69092	Loss: 110.208
+48000/69092	Loss: 107.401
+51200/69092	Loss: 108.834
+54400/69092	Loss: 111.112
+57600/69092	Loss: 111.229
+60800/69092	Loss: 110.035
+64000/69092	Loss: 109.469
+67200/69092	Loss: 109.512
+Training time 0:09:58.360008
+Epoch: 128 Average loss: 109.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1057)
+0/69092	Loss: 110.206
+3200/69092	Loss: 109.687
+6400/69092	Loss: 109.535
+9600/69092	Loss: 108.924
+12800/69092	Loss: 109.477
+16000/69092	Loss: 109.692
+19200/69092	Loss: 109.597
+22400/69092	Loss: 109.446
+25600/69092	Loss: 108.950
+28800/69092	Loss: 110.178
+32000/69092	Loss: 110.556
+35200/69092	Loss: 108.899
+38400/69092	Loss: 109.801
+41600/69092	Loss: 109.923
+44800/69092	Loss: 110.374
+48000/69092	Loss: 110.574
+51200/69092	Loss: 109.992
+54400/69092	Loss: 109.901
+57600/69092	Loss: 108.305
+60800/69092	Loss: 111.519
+64000/69092	Loss: 110.861
+67200/69092	Loss: 108.387
+Training time 0:09:27.109565
+Epoch: 129 Average loss: 109.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1058)
+0/69092	Loss: 115.793
+3200/69092	Loss: 109.019
+6400/69092	Loss: 109.807
+9600/69092	Loss: 108.722
+12800/69092	Loss: 109.212
+16000/69092	Loss: 111.998
+19200/69092	Loss: 108.485
+22400/69092	Loss: 110.602
+25600/69092	Loss: 110.121
+28800/69092	Loss: 108.439
+32000/69092	Loss: 109.692
+35200/69092	Loss: 109.507
+38400/69092	Loss: 109.034
+41600/69092	Loss: 111.004
+44800/69092	Loss: 110.019
+48000/69092	Loss: 107.646
+51200/69092	Loss: 108.868
+54400/69092	Loss: 110.308
+57600/69092	Loss: 109.209
+60800/69092	Loss: 110.329
+64000/69092	Loss: 110.542
+67200/69092	Loss: 109.214
+Training time 0:09:25.586374
+Epoch: 130 Average loss: 109.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1059)
+0/69092	Loss: 117.831
+3200/69092	Loss: 108.790
+6400/69092	Loss: 108.638
+9600/69092	Loss: 111.646
+12800/69092	Loss: 110.365
+16000/69092	Loss: 110.225
+19200/69092	Loss: 109.508
+22400/69092	Loss: 107.939
+25600/69092	Loss: 110.038
+28800/69092	Loss: 110.083
+32000/69092	Loss: 111.168
+35200/69092	Loss: 110.116
+38400/69092	Loss: 109.007
+41600/69092	Loss: 110.076
+44800/69092	Loss: 110.069
+48000/69092	Loss: 110.077
+51200/69092	Loss: 110.483
+54400/69092	Loss: 108.907
+57600/69092	Loss: 110.974
+60800/69092	Loss: 108.696
+64000/69092	Loss: 110.101
+67200/69092	Loss: 108.844
+Training time 0:09:43.523422
+Epoch: 131 Average loss: 109.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64/checkpoints/last' (iter 1060)
+0/69092	Loss: 105.153
+3200/69092	Loss: 110.586
+6400/69092	Loss: 108.532
+9600/69092	Loss: 109.132
+12800/69092	Loss: 107.735
+16000/69092	Loss: 108.301
+19200/69092	Loss: 108.845
+22400/69092	Loss: 108.643
+25600/69092	Loss: 109.032
+28800/69092	Loss: 110.030
+32000/69092	Loss: 108.722
+35200/69092	Loss: 108.866
diff --git a/OAR.2073649.stderr b/OAR.2073649.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..5dfa2d961718d9360fe6febaab7de3ccdf5b6ec3
--- /dev/null
+++ b/OAR.2073649.stderr
@@ -0,0 +1,3 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+## OAR [2020-07-06 17:10:05] Job 2073649 KILLED ##
diff --git a/OAR.2073649.stdout b/OAR.2073649.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..b9e80b1e04aa2c957542a9c11daf78f0dab1c606
--- /dev/null
+++ b/OAR.2073649.stdout
@@ -0,0 +1,3951 @@
+Namespace(batch_size=64, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='beta_VAE_bs_64_ls_15', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=15, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce GTX 1080 Ti
+GeForce GTX 1080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=30, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=15, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 769185
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last (iter 418)'
+0/69092	Loss: 143.183
+3200/69092	Loss: 147.618
+6400/69092	Loss: 147.473
+9600/69092	Loss: 148.717
+12800/69092	Loss: 147.245
+16000/69092	Loss: 148.120
+19200/69092	Loss: 147.159
+22400/69092	Loss: 148.509
+25600/69092	Loss: 148.512
+28800/69092	Loss: 149.219
+32000/69092	Loss: 149.731
+35200/69092	Loss: 148.253
+38400/69092	Loss: 148.995
+41600/69092	Loss: 146.679
+44800/69092	Loss: 148.135
+48000/69092	Loss: 145.226
+51200/69092	Loss: 148.689
+54400/69092	Loss: 149.348
+57600/69092	Loss: 147.100
+60800/69092	Loss: 149.646
+64000/69092	Loss: 148.485
+67200/69092	Loss: 148.533
+Training time 0:11:39.698038
+Epoch: 1 Average loss: 148.04
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 419)
+0/69092	Loss: 142.137
+3200/69092	Loss: 149.179
+6400/69092	Loss: 147.509
+9600/69092	Loss: 148.427
+12800/69092	Loss: 148.778
+16000/69092	Loss: 148.029
+19200/69092	Loss: 149.429
+22400/69092	Loss: 146.531
+25600/69092	Loss: 148.761
+28800/69092	Loss: 151.364
+32000/69092	Loss: 146.891
+35200/69092	Loss: 148.280
+38400/69092	Loss: 146.444
+41600/69092	Loss: 147.072
+44800/69092	Loss: 148.196
+48000/69092	Loss: 147.938
+51200/69092	Loss: 148.821
+54400/69092	Loss: 148.115
+57600/69092	Loss: 149.511
+60800/69092	Loss: 146.412
+64000/69092	Loss: 151.522
+67200/69092	Loss: 146.447
+Training time 0:07:54.532880
+Epoch: 2 Average loss: 148.24
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 420)
+0/69092	Loss: 151.972
+3200/69092	Loss: 147.955
+6400/69092	Loss: 148.205
+9600/69092	Loss: 150.636
+12800/69092	Loss: 148.021
+16000/69092	Loss: 149.129
+19200/69092	Loss: 146.083
+22400/69092	Loss: 148.885
+25600/69092	Loss: 149.544
+28800/69092	Loss: 149.156
+32000/69092	Loss: 146.294
+35200/69092	Loss: 147.960
+38400/69092	Loss: 146.559
+41600/69092	Loss: 147.397
+44800/69092	Loss: 148.683
+48000/69092	Loss: 150.809
+51200/69092	Loss: 150.111
+54400/69092	Loss: 147.976
+57600/69092	Loss: 145.551
+60800/69092	Loss: 149.531
+64000/69092	Loss: 150.106
+67200/69092	Loss: 147.041
+Training time 0:08:10.046653
+Epoch: 3 Average loss: 148.35
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 421)
+0/69092	Loss: 141.968
+3200/69092	Loss: 147.410
+6400/69092	Loss: 147.605
+9600/69092	Loss: 147.441
+12800/69092	Loss: 147.353
+16000/69092	Loss: 148.181
+19200/69092	Loss: 148.599
+22400/69092	Loss: 146.185
+25600/69092	Loss: 148.612
+28800/69092	Loss: 148.729
+32000/69092	Loss: 147.882
+35200/69092	Loss: 149.332
+38400/69092	Loss: 146.653
+41600/69092	Loss: 147.763
+44800/69092	Loss: 149.313
+48000/69092	Loss: 147.069
+51200/69092	Loss: 149.832
+54400/69092	Loss: 151.244
+57600/69092	Loss: 148.217
+60800/69092	Loss: 146.018
+64000/69092	Loss: 148.313
+67200/69092	Loss: 147.461
+Training time 0:07:55.915490
+Epoch: 4 Average loss: 148.13
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 422)
+0/69092	Loss: 128.724
+3200/69092	Loss: 148.896
+6400/69092	Loss: 148.732
+9600/69092	Loss: 146.904
+12800/69092	Loss: 148.209
+16000/69092	Loss: 148.359
+19200/69092	Loss: 151.128
+22400/69092	Loss: 150.880
+25600/69092	Loss: 146.344
+28800/69092	Loss: 145.558
+32000/69092	Loss: 149.491
+35200/69092	Loss: 147.168
+38400/69092	Loss: 148.340
+41600/69092	Loss: 149.432
+44800/69092	Loss: 148.780
+48000/69092	Loss: 149.556
+51200/69092	Loss: 148.414
+54400/69092	Loss: 149.195
+57600/69092	Loss: 148.268
+60800/69092	Loss: 149.315
+64000/69092	Loss: 146.709
+67200/69092	Loss: 148.883
+Training time 0:07:59.023014
+Epoch: 5 Average loss: 148.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 423)
+0/69092	Loss: 145.389
+3200/69092	Loss: 147.523
+6400/69092	Loss: 147.467
+9600/69092	Loss: 147.423
+12800/69092	Loss: 145.648
+16000/69092	Loss: 148.186
+19200/69092	Loss: 147.821
+22400/69092	Loss: 148.511
+25600/69092	Loss: 147.849
+28800/69092	Loss: 148.381
+32000/69092	Loss: 147.617
+35200/69092	Loss: 148.262
+38400/69092	Loss: 150.722
+41600/69092	Loss: 149.193
+44800/69092	Loss: 147.609
+48000/69092	Loss: 149.602
+51200/69092	Loss: 151.075
+54400/69092	Loss: 147.856
+57600/69092	Loss: 148.833
+60800/69092	Loss: 147.634
+64000/69092	Loss: 150.236
+67200/69092	Loss: 146.731
+Training time 0:08:05.637128
+Epoch: 6 Average loss: 148.36
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 424)
+0/69092	Loss: 156.154
+3200/69092	Loss: 147.157
+6400/69092	Loss: 148.065
+9600/69092	Loss: 148.416
+12800/69092	Loss: 149.543
+16000/69092	Loss: 150.355
+19200/69092	Loss: 148.574
+22400/69092	Loss: 148.524
+25600/69092	Loss: 148.022
+28800/69092	Loss: 146.403
+32000/69092	Loss: 151.165
+35200/69092	Loss: 146.379
+38400/69092	Loss: 148.845
+41600/69092	Loss: 148.021
+44800/69092	Loss: 145.643
+48000/69092	Loss: 146.532
+51200/69092	Loss: 147.306
+54400/69092	Loss: 148.737
+57600/69092	Loss: 147.937
+60800/69092	Loss: 147.891
+64000/69092	Loss: 148.591
+67200/69092	Loss: 149.620
+Training time 0:07:56.883112
+Epoch: 7 Average loss: 148.21
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 425)
+0/69092	Loss: 145.754
+3200/69092	Loss: 147.945
+6400/69092	Loss: 146.160
+9600/69092	Loss: 149.960
+12800/69092	Loss: 145.591
+16000/69092	Loss: 147.812
+19200/69092	Loss: 151.044
+22400/69092	Loss: 148.629
+25600/69092	Loss: 147.459
+28800/69092	Loss: 150.248
+32000/69092	Loss: 146.320
+35200/69092	Loss: 150.205
+38400/69092	Loss: 149.483
+41600/69092	Loss: 146.850
+44800/69092	Loss: 148.456
+48000/69092	Loss: 147.206
+51200/69092	Loss: 144.131
+54400/69092	Loss: 148.001
+57600/69092	Loss: 145.962
+60800/69092	Loss: 150.821
+64000/69092	Loss: 150.089
+67200/69092	Loss: 149.186
+Training time 0:08:14.918053
+Epoch: 8 Average loss: 148.12
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 426)
+0/69092	Loss: 146.375
+3200/69092	Loss: 146.793
+6400/69092	Loss: 147.296
+9600/69092	Loss: 149.391
+12800/69092	Loss: 148.266
+16000/69092	Loss: 146.895
+19200/69092	Loss: 148.269
+22400/69092	Loss: 144.834
+25600/69092	Loss: 146.757
+28800/69092	Loss: 149.730
+32000/69092	Loss: 147.362
+35200/69092	Loss: 151.049
+38400/69092	Loss: 148.387
+41600/69092	Loss: 146.074
+44800/69092	Loss: 150.241
+48000/69092	Loss: 151.275
+51200/69092	Loss: 148.801
+54400/69092	Loss: 147.876
+57600/69092	Loss: 148.990
+60800/69092	Loss: 148.252
+64000/69092	Loss: 149.032
+67200/69092	Loss: 146.944
+Training time 0:08:08.954540
+Epoch: 9 Average loss: 148.20
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 427)
+0/69092	Loss: 155.638
+3200/69092	Loss: 148.712
+6400/69092	Loss: 148.019
+9600/69092	Loss: 149.487
+12800/69092	Loss: 148.484
+16000/69092	Loss: 146.584
+19200/69092	Loss: 148.630
+22400/69092	Loss: 148.356
+25600/69092	Loss: 151.760
+28800/69092	Loss: 148.265
+32000/69092	Loss: 146.722
+35200/69092	Loss: 147.526
+38400/69092	Loss: 147.863
+41600/69092	Loss: 148.233
+44800/69092	Loss: 150.088
+48000/69092	Loss: 146.819
+51200/69092	Loss: 148.843
+54400/69092	Loss: 148.068
+57600/69092	Loss: 149.204
+60800/69092	Loss: 150.213
+64000/69092	Loss: 147.274
+67200/69092	Loss: 149.855
+Training time 0:07:56.412687
+Epoch: 10 Average loss: 148.38
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 428)
+0/69092	Loss: 156.538
+3200/69092	Loss: 148.370
+6400/69092	Loss: 148.031
+9600/69092	Loss: 150.001
+12800/69092	Loss: 149.847
+16000/69092	Loss: 148.283
+19200/69092	Loss: 148.921
+22400/69092	Loss: 146.693
+25600/69092	Loss: 147.832
+28800/69092	Loss: 148.380
+32000/69092	Loss: 148.320
+35200/69092	Loss: 150.534
+38400/69092	Loss: 149.614
+41600/69092	Loss: 147.369
+44800/69092	Loss: 147.269
+48000/69092	Loss: 148.624
+51200/69092	Loss: 146.261
+54400/69092	Loss: 148.377
+57600/69092	Loss: 149.715
+60800/69092	Loss: 150.184
+64000/69092	Loss: 146.827
+67200/69092	Loss: 146.942
+Training time 0:08:17.455823
+Epoch: 11 Average loss: 148.40
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 429)
+0/69092	Loss: 135.437
+3200/69092	Loss: 145.795
+6400/69092	Loss: 149.987
+9600/69092	Loss: 147.563
+12800/69092	Loss: 147.523
+16000/69092	Loss: 149.619
+19200/69092	Loss: 143.788
+22400/69092	Loss: 148.897
+25600/69092	Loss: 151.577
+28800/69092	Loss: 149.206
+32000/69092	Loss: 147.418
+35200/69092	Loss: 146.874
+38400/69092	Loss: 146.673
+41600/69092	Loss: 148.630
+44800/69092	Loss: 146.626
+48000/69092	Loss: 151.496
+51200/69092	Loss: 149.410
+54400/69092	Loss: 147.152
+57600/69092	Loss: 149.060
+60800/69092	Loss: 149.144
+64000/69092	Loss: 144.658
+67200/69092	Loss: 150.248
+Training time 0:08:14.879181
+Epoch: 12 Average loss: 148.21
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 430)
+0/69092	Loss: 140.867
+3200/69092	Loss: 148.903
+6400/69092	Loss: 148.330
+9600/69092	Loss: 149.084
+12800/69092	Loss: 149.345
+16000/69092	Loss: 146.931
+19200/69092	Loss: 148.202
+22400/69092	Loss: 148.223
+25600/69092	Loss: 149.430
+28800/69092	Loss: 146.027
+32000/69092	Loss: 150.377
+35200/69092	Loss: 146.120
+38400/69092	Loss: 147.849
+41600/69092	Loss: 148.908
+44800/69092	Loss: 148.744
+48000/69092	Loss: 147.663
+51200/69092	Loss: 149.876
+54400/69092	Loss: 150.930
+57600/69092	Loss: 147.989
+60800/69092	Loss: 146.148
+64000/69092	Loss: 150.220
+67200/69092	Loss: 145.671
+Training time 0:07:54.587141
+Epoch: 13 Average loss: 148.35
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 431)
+0/69092	Loss: 173.080
+3200/69092	Loss: 148.688
+6400/69092	Loss: 147.209
+9600/69092	Loss: 148.451
+12800/69092	Loss: 147.353
+16000/69092	Loss: 145.839
+19200/69092	Loss: 146.161
+22400/69092	Loss: 149.156
+25600/69092	Loss: 148.625
+28800/69092	Loss: 146.879
+32000/69092	Loss: 149.375
+35200/69092	Loss: 148.484
+38400/69092	Loss: 150.579
+41600/69092	Loss: 149.484
+44800/69092	Loss: 149.941
+48000/69092	Loss: 149.240
+51200/69092	Loss: 147.528
+54400/69092	Loss: 148.218
+57600/69092	Loss: 144.949
+60800/69092	Loss: 148.823
+64000/69092	Loss: 147.993
+67200/69092	Loss: 148.369
+Training time 0:08:15.532555
+Epoch: 14 Average loss: 148.24
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 432)
+0/69092	Loss: 157.533
+3200/69092	Loss: 148.672
+6400/69092	Loss: 148.216
+9600/69092	Loss: 151.031
+12800/69092	Loss: 147.606
+16000/69092	Loss: 148.248
+19200/69092	Loss: 144.587
+22400/69092	Loss: 146.560
+25600/69092	Loss: 147.953
+28800/69092	Loss: 150.668
+32000/69092	Loss: 147.917
+35200/69092	Loss: 148.531
+38400/69092	Loss: 148.173
+41600/69092	Loss: 148.771
+44800/69092	Loss: 148.117
+48000/69092	Loss: 147.374
+51200/69092	Loss: 148.461
+54400/69092	Loss: 147.842
+57600/69092	Loss: 147.981
+60800/69092	Loss: 148.616
+64000/69092	Loss: 148.052
+67200/69092	Loss: 147.393
+Training time 0:08:13.360769
+Epoch: 15 Average loss: 148.28
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 433)
+0/69092	Loss: 143.217
+3200/69092	Loss: 147.051
+6400/69092	Loss: 148.431
+9600/69092	Loss: 148.788
+12800/69092	Loss: 147.885
+16000/69092	Loss: 149.630
+19200/69092	Loss: 146.780
+22400/69092	Loss: 149.477
+25600/69092	Loss: 146.637
+28800/69092	Loss: 146.005
+32000/69092	Loss: 148.121
+35200/69092	Loss: 149.538
+38400/69092	Loss: 148.992
+41600/69092	Loss: 146.767
+44800/69092	Loss: 146.575
+48000/69092	Loss: 148.247
+51200/69092	Loss: 147.566
+54400/69092	Loss: 148.181
+57600/69092	Loss: 149.464
+60800/69092	Loss: 147.129
+64000/69092	Loss: 149.189
+67200/69092	Loss: 151.608
+Training time 0:08:01.282106
+Epoch: 16 Average loss: 148.27
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 434)
+0/69092	Loss: 141.424
+3200/69092	Loss: 148.376
+6400/69092	Loss: 149.043
+9600/69092	Loss: 147.739
+12800/69092	Loss: 148.168
+16000/69092	Loss: 147.035
+19200/69092	Loss: 147.584
+22400/69092	Loss: 147.715
+25600/69092	Loss: 147.867
+28800/69092	Loss: 148.391
+32000/69092	Loss: 150.060
+35200/69092	Loss: 148.538
+38400/69092	Loss: 147.262
+41600/69092	Loss: 146.985
+44800/69092	Loss: 146.733
+48000/69092	Loss: 147.953
+51200/69092	Loss: 150.002
+54400/69092	Loss: 144.197
+57600/69092	Loss: 147.031
+60800/69092	Loss: 149.365
+64000/69092	Loss: 146.765
+67200/69092	Loss: 151.156
+Training time 0:08:09.618079
+Epoch: 17 Average loss: 147.95
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 435)
+0/69092	Loss: 148.481
+3200/69092	Loss: 147.458
+6400/69092	Loss: 147.018
+9600/69092	Loss: 148.193
+12800/69092	Loss: 150.312
+16000/69092	Loss: 146.336
+19200/69092	Loss: 151.199
+22400/69092	Loss: 149.720
+25600/69092	Loss: 148.621
+28800/69092	Loss: 146.475
+32000/69092	Loss: 147.064
+35200/69092	Loss: 145.493
+38400/69092	Loss: 148.069
+41600/69092	Loss: 147.616
+44800/69092	Loss: 149.106
+48000/69092	Loss: 147.316
+51200/69092	Loss: 147.639
+54400/69092	Loss: 146.997
+57600/69092	Loss: 147.944
+60800/69092	Loss: 148.630
+64000/69092	Loss: 145.983
+67200/69092	Loss: 151.094
+Training time 0:08:10.071948
+Epoch: 18 Average loss: 148.02
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 436)
+0/69092	Loss: 148.115
+3200/69092	Loss: 149.206
+6400/69092	Loss: 143.855
+9600/69092	Loss: 143.719
+12800/69092	Loss: 148.447
+16000/69092	Loss: 147.355
+19200/69092	Loss: 150.515
+22400/69092	Loss: 148.988
+25600/69092	Loss: 148.082
+28800/69092	Loss: 146.642
+32000/69092	Loss: 150.371
+35200/69092	Loss: 148.081
+38400/69092	Loss: 149.873
+41600/69092	Loss: 147.399
+44800/69092	Loss: 147.447
+48000/69092	Loss: 148.191
+51200/69092	Loss: 150.706
+54400/69092	Loss: 150.777
+57600/69092	Loss: 147.912
+60800/69092	Loss: 146.146
+64000/69092	Loss: 147.305
+67200/69092	Loss: 146.441
+Training time 0:07:59.220278
+Epoch: 19 Average loss: 147.97
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 437)
+0/69092	Loss: 131.021
+3200/69092	Loss: 146.446
+6400/69092	Loss: 146.946
+9600/69092	Loss: 148.588
+12800/69092	Loss: 149.286
+16000/69092	Loss: 150.007
+19200/69092	Loss: 150.473
+22400/69092	Loss: 149.020
+25600/69092	Loss: 147.899
+28800/69092	Loss: 147.834
+32000/69092	Loss: 145.860
+35200/69092	Loss: 149.508
+38400/69092	Loss: 149.057
+41600/69092	Loss: 146.578
+44800/69092	Loss: 150.041
+48000/69092	Loss: 148.928
+51200/69092	Loss: 147.288
+54400/69092	Loss: 148.036
+57600/69092	Loss: 147.716
+60800/69092	Loss: 147.762
+64000/69092	Loss: 144.956
+67200/69092	Loss: 147.061
+Training time 0:08:12.216152
+Epoch: 20 Average loss: 148.13
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 438)
+0/69092	Loss: 150.240
+3200/69092	Loss: 149.712
+6400/69092	Loss: 149.016
+9600/69092	Loss: 148.304
+12800/69092	Loss: 146.313
+16000/69092	Loss: 148.699
+19200/69092	Loss: 145.658
+22400/69092	Loss: 145.821
+25600/69092	Loss: 148.022
+28800/69092	Loss: 148.880
+32000/69092	Loss: 148.422
+35200/69092	Loss: 146.137
+38400/69092	Loss: 149.069
+41600/69092	Loss: 151.531
+44800/69092	Loss: 149.311
+48000/69092	Loss: 147.249
+51200/69092	Loss: 147.168
+54400/69092	Loss: 148.229
+57600/69092	Loss: 146.840
+60800/69092	Loss: 146.514
+64000/69092	Loss: 148.016
+67200/69092	Loss: 146.485
+Training time 0:08:09.801460
+Epoch: 21 Average loss: 147.86
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 439)
+0/69092	Loss: 162.247
+3200/69092	Loss: 148.213
+6400/69092	Loss: 150.657
+9600/69092	Loss: 147.509
+12800/69092	Loss: 148.421
+16000/69092	Loss: 147.295
+19200/69092	Loss: 147.616
+22400/69092	Loss: 147.921
+25600/69092	Loss: 146.332
+28800/69092	Loss: 149.402
+32000/69092	Loss: 148.166
+35200/69092	Loss: 148.783
+38400/69092	Loss: 146.822
+41600/69092	Loss: 148.938
+44800/69092	Loss: 148.111
+48000/69092	Loss: 150.963
+51200/69092	Loss: 148.606
+54400/69092	Loss: 148.309
+57600/69092	Loss: 147.807
+60800/69092	Loss: 147.408
+64000/69092	Loss: 146.878
+67200/69092	Loss: 148.016
+Training time 0:07:55.938343
+Epoch: 22 Average loss: 148.26
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 440)
+0/69092	Loss: 155.706
+3200/69092	Loss: 148.599
+6400/69092	Loss: 146.513
+9600/69092	Loss: 145.756
+12800/69092	Loss: 149.388
+16000/69092	Loss: 148.574
+19200/69092	Loss: 146.949
+22400/69092	Loss: 147.869
+25600/69092	Loss: 145.385
+28800/69092	Loss: 146.625
+32000/69092	Loss: 151.839
+35200/69092	Loss: 147.076
+38400/69092	Loss: 147.623
+41600/69092	Loss: 150.296
+44800/69092	Loss: 148.547
+48000/69092	Loss: 146.676
+51200/69092	Loss: 148.324
+54400/69092	Loss: 145.567
+57600/69092	Loss: 148.300
+60800/69092	Loss: 151.457
+64000/69092	Loss: 147.204
+67200/69092	Loss: 148.512
+Training time 0:08:07.568188
+Epoch: 23 Average loss: 148.08
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 441)
+0/69092	Loss: 156.300
+3200/69092	Loss: 147.409
+6400/69092	Loss: 148.853
+9600/69092	Loss: 151.547
+12800/69092	Loss: 147.351
+16000/69092	Loss: 147.707
+19200/69092	Loss: 147.603
+22400/69092	Loss: 149.792
+25600/69092	Loss: 145.896
+28800/69092	Loss: 151.087
+32000/69092	Loss: 148.622
+35200/69092	Loss: 148.990
+38400/69092	Loss: 147.862
+41600/69092	Loss: 148.976
+44800/69092	Loss: 148.330
+48000/69092	Loss: 145.300
+51200/69092	Loss: 147.794
+54400/69092	Loss: 146.840
+57600/69092	Loss: 147.746
+60800/69092	Loss: 147.394
+64000/69092	Loss: 147.259
+67200/69092	Loss: 148.705
+Training time 0:08:10.596763
+Epoch: 24 Average loss: 148.23
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 442)
+0/69092	Loss: 164.702
+3200/69092	Loss: 148.065
+6400/69092	Loss: 147.172
+9600/69092	Loss: 149.072
+12800/69092	Loss: 148.064
+16000/69092	Loss: 148.151
+19200/69092	Loss: 148.973
+22400/69092	Loss: 148.406
+25600/69092	Loss: 148.134
+28800/69092	Loss: 148.082
+32000/69092	Loss: 147.130
+35200/69092	Loss: 146.779
+38400/69092	Loss: 149.002
+41600/69092	Loss: 148.293
+44800/69092	Loss: 147.374
+48000/69092	Loss: 150.518
+51200/69092	Loss: 148.212
+54400/69092	Loss: 149.365
+57600/69092	Loss: 150.856
+60800/69092	Loss: 146.766
+64000/69092	Loss: 148.604
+67200/69092	Loss: 146.261
+Training time 0:08:04.134514
+Epoch: 25 Average loss: 148.21
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 443)
+0/69092	Loss: 139.293
+3200/69092	Loss: 149.153
+6400/69092	Loss: 147.671
+9600/69092	Loss: 146.209
+12800/69092	Loss: 145.942
+16000/69092	Loss: 147.053
+19200/69092	Loss: 148.615
+22400/69092	Loss: 150.480
+25600/69092	Loss: 148.883
+28800/69092	Loss: 150.828
+32000/69092	Loss: 147.771
+35200/69092	Loss: 150.045
+38400/69092	Loss: 147.675
+41600/69092	Loss: 147.483
+44800/69092	Loss: 148.487
+48000/69092	Loss: 149.847
+51200/69092	Loss: 145.931
+54400/69092	Loss: 150.154
+57600/69092	Loss: 145.836
+60800/69092	Loss: 147.828
+64000/69092	Loss: 148.121
+67200/69092	Loss: 146.828
+Training time 0:08:11.302526
+Epoch: 26 Average loss: 148.11
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 444)
+0/69092	Loss: 145.546
+3200/69092	Loss: 146.655
+6400/69092	Loss: 148.614
+9600/69092	Loss: 148.423
+12800/69092	Loss: 148.222
+16000/69092	Loss: 148.028
+19200/69092	Loss: 146.499
+22400/69092	Loss: 148.356
+25600/69092	Loss: 150.092
+28800/69092	Loss: 148.466
+32000/69092	Loss: 148.952
+35200/69092	Loss: 149.688
+38400/69092	Loss: 147.727
+41600/69092	Loss: 148.294
+44800/69092	Loss: 147.270
+48000/69092	Loss: 148.046
+51200/69092	Loss: 146.498
+54400/69092	Loss: 147.327
+57600/69092	Loss: 147.433
+60800/69092	Loss: 147.472
+64000/69092	Loss: 151.523
+67200/69092	Loss: 146.017
+Training time 0:08:03.606979
+Epoch: 27 Average loss: 148.05
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 445)
+0/69092	Loss: 146.829
+3200/69092	Loss: 150.099
+6400/69092	Loss: 149.186
+9600/69092	Loss: 149.600
+12800/69092	Loss: 146.362
+16000/69092	Loss: 150.737
+19200/69092	Loss: 149.330
+22400/69092	Loss: 148.516
+25600/69092	Loss: 148.261
+28800/69092	Loss: 149.302
+32000/69092	Loss: 147.198
+35200/69092	Loss: 147.400
+38400/69092	Loss: 146.582
+41600/69092	Loss: 148.072
+44800/69092	Loss: 143.896
+48000/69092	Loss: 147.628
+51200/69092	Loss: 147.017
+54400/69092	Loss: 150.601
+57600/69092	Loss: 147.691
+60800/69092	Loss: 147.907
+64000/69092	Loss: 146.175
+67200/69092	Loss: 146.997
+Training time 0:08:02.229186
+Epoch: 28 Average loss: 148.04
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 446)
+0/69092	Loss: 141.041
+3200/69092	Loss: 145.905
+6400/69092	Loss: 147.013
+9600/69092	Loss: 149.193
+12800/69092	Loss: 149.434
+16000/69092	Loss: 147.402
+19200/69092	Loss: 148.860
+22400/69092	Loss: 149.273
+25600/69092	Loss: 148.087
+28800/69092	Loss: 146.363
+32000/69092	Loss: 147.747
+35200/69092	Loss: 149.471
+38400/69092	Loss: 148.715
+41600/69092	Loss: 148.992
+44800/69092	Loss: 144.856
+48000/69092	Loss: 148.000
+51200/69092	Loss: 150.016
+54400/69092	Loss: 146.175
+57600/69092	Loss: 149.239
+60800/69092	Loss: 148.430
+64000/69092	Loss: 148.121
+67200/69092	Loss: 146.915
+Training time 0:08:06.193518
+Epoch: 29 Average loss: 148.02
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 447)
+0/69092	Loss: 153.961
+3200/69092	Loss: 145.624
+6400/69092	Loss: 149.661
+9600/69092	Loss: 150.121
+12800/69092	Loss: 148.938
+16000/69092	Loss: 148.346
+19200/69092	Loss: 147.282
+22400/69092	Loss: 145.541
+25600/69092	Loss: 147.446
+28800/69092	Loss: 149.718
+32000/69092	Loss: 145.130
+35200/69092	Loss: 146.380
+38400/69092	Loss: 149.341
+41600/69092	Loss: 147.638
+44800/69092	Loss: 146.055
+48000/69092	Loss: 148.953
+51200/69092	Loss: 147.412
+54400/69092	Loss: 148.449
+57600/69092	Loss: 149.200
+60800/69092	Loss: 145.262
+64000/69092	Loss: 149.707
+67200/69092	Loss: 146.116
+Training time 0:07:56.714020
+Epoch: 30 Average loss: 147.76
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 448)
+0/69092	Loss: 147.208
+3200/69092	Loss: 147.898
+6400/69092	Loss: 148.379
+9600/69092	Loss: 148.956
+12800/69092	Loss: 147.439
+16000/69092	Loss: 149.625
+19200/69092	Loss: 146.804
+22400/69092	Loss: 148.697
+25600/69092	Loss: 144.557
+28800/69092	Loss: 150.664
+32000/69092	Loss: 148.874
+35200/69092	Loss: 148.875
+38400/69092	Loss: 147.146
+41600/69092	Loss: 146.803
+44800/69092	Loss: 147.706
+48000/69092	Loss: 147.382
+51200/69092	Loss: 148.540
+54400/69092	Loss: 146.964
+57600/69092	Loss: 146.207
+60800/69092	Loss: 147.512
+64000/69092	Loss: 147.036
+67200/69092	Loss: 149.246
+Training time 0:08:08.049636
+Epoch: 31 Average loss: 147.95
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 449)
+0/69092	Loss: 154.486
+3200/69092	Loss: 146.538
+6400/69092	Loss: 147.309
+9600/69092	Loss: 147.183
+12800/69092	Loss: 147.674
+16000/69092	Loss: 146.870
+19200/69092	Loss: 146.350
+22400/69092	Loss: 146.527
+25600/69092	Loss: 149.160
+28800/69092	Loss: 148.780
+32000/69092	Loss: 146.034
+35200/69092	Loss: 147.837
+38400/69092	Loss: 150.295
+41600/69092	Loss: 149.436
+44800/69092	Loss: 147.406
+48000/69092	Loss: 148.187
+51200/69092	Loss: 148.190
+54400/69092	Loss: 147.674
+57600/69092	Loss: 148.366
+60800/69092	Loss: 146.110
+64000/69092	Loss: 147.097
+67200/69092	Loss: 148.212
+Training time 0:08:08.612121
+Epoch: 32 Average loss: 147.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 450)
+0/69092	Loss: 157.820
+3200/69092	Loss: 147.279
+6400/69092	Loss: 146.476
+9600/69092	Loss: 146.643
+12800/69092	Loss: 149.833
+16000/69092	Loss: 148.621
+19200/69092	Loss: 145.554
+22400/69092	Loss: 147.437
+25600/69092	Loss: 149.238
+28800/69092	Loss: 148.816
+32000/69092	Loss: 148.049
+35200/69092	Loss: 144.955
+38400/69092	Loss: 151.129
+41600/69092	Loss: 146.837
+44800/69092	Loss: 148.611
+48000/69092	Loss: 148.916
+51200/69092	Loss: 147.479
+54400/69092	Loss: 147.995
+57600/69092	Loss: 150.899
+60800/69092	Loss: 148.429
+64000/69092	Loss: 145.854
+67200/69092	Loss: 148.767
+Training time 0:08:00.133266
+Epoch: 33 Average loss: 148.01
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 451)
+0/69092	Loss: 146.987
+3200/69092	Loss: 148.967
+6400/69092	Loss: 149.877
+9600/69092	Loss: 149.288
+12800/69092	Loss: 147.283
+16000/69092	Loss: 149.386
+19200/69092	Loss: 147.005
+22400/69092	Loss: 145.841
+25600/69092	Loss: 149.361
+28800/69092	Loss: 148.619
+32000/69092	Loss: 148.246
+35200/69092	Loss: 147.190
+38400/69092	Loss: 148.138
+41600/69092	Loss: 147.676
+44800/69092	Loss: 149.170
+48000/69092	Loss: 149.179
+51200/69092	Loss: 144.251
+54400/69092	Loss: 147.534
+57600/69092	Loss: 148.770
+60800/69092	Loss: 149.348
+64000/69092	Loss: 149.214
+67200/69092	Loss: 146.594
+Training time 0:08:10.495989
+Epoch: 34 Average loss: 148.10
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 452)
+0/69092	Loss: 154.872
+3200/69092	Loss: 150.102
+6400/69092	Loss: 148.049
+9600/69092	Loss: 146.893
+12800/69092	Loss: 149.331
+16000/69092	Loss: 146.750
+19200/69092	Loss: 148.587
+22400/69092	Loss: 144.538
+25600/69092	Loss: 147.891
+28800/69092	Loss: 147.443
+32000/69092	Loss: 148.261
+35200/69092	Loss: 147.756
+38400/69092	Loss: 148.438
+41600/69092	Loss: 149.877
+44800/69092	Loss: 145.629
+48000/69092	Loss: 147.936
+51200/69092	Loss: 148.292
+54400/69092	Loss: 149.120
+57600/69092	Loss: 146.668
+60800/69092	Loss: 148.293
+64000/69092	Loss: 146.584
+67200/69092	Loss: 149.138
+Training time 0:08:08.066059
+Epoch: 35 Average loss: 147.92
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 453)
+0/69092	Loss: 144.107
+3200/69092	Loss: 147.263
+6400/69092	Loss: 148.721
+9600/69092	Loss: 146.997
+12800/69092	Loss: 148.728
+16000/69092	Loss: 146.582
+19200/69092	Loss: 146.552
+22400/69092	Loss: 147.329
+25600/69092	Loss: 148.620
+28800/69092	Loss: 146.287
+32000/69092	Loss: 147.103
+35200/69092	Loss: 148.038
+38400/69092	Loss: 145.561
+41600/69092	Loss: 147.841
+44800/69092	Loss: 146.746
+48000/69092	Loss: 149.432
+51200/69092	Loss: 151.244
+54400/69092	Loss: 147.422
+57600/69092	Loss: 148.779
+60800/69092	Loss: 149.898
+64000/69092	Loss: 150.070
+67200/69092	Loss: 145.500
+Training time 0:08:01.168977
+Epoch: 36 Average loss: 147.88
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 454)
+0/69092	Loss: 158.654
+3200/69092	Loss: 149.694
+6400/69092	Loss: 148.231
+9600/69092	Loss: 148.486
+12800/69092	Loss: 145.361
+16000/69092	Loss: 149.350
+19200/69092	Loss: 147.505
+22400/69092	Loss: 147.571
+25600/69092	Loss: 148.206
+28800/69092	Loss: 142.649
+32000/69092	Loss: 147.909
+35200/69092	Loss: 149.097
+38400/69092	Loss: 149.508
+41600/69092	Loss: 148.885
+44800/69092	Loss: 147.852
+48000/69092	Loss: 148.087
+51200/69092	Loss: 150.050
+54400/69092	Loss: 147.069
+57600/69092	Loss: 150.538
+60800/69092	Loss: 148.262
+64000/69092	Loss: 147.661
+67200/69092	Loss: 146.824
+Training time 0:08:17.519137
+Epoch: 37 Average loss: 148.14
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 455)
+0/69092	Loss: 149.688
+3200/69092	Loss: 146.304
+6400/69092	Loss: 147.775
+9600/69092	Loss: 146.869
+12800/69092	Loss: 148.176
+16000/69092	Loss: 148.856
+19200/69092	Loss: 149.063
+22400/69092	Loss: 147.659
+25600/69092	Loss: 146.572
+28800/69092	Loss: 147.572
+32000/69092	Loss: 148.656
+35200/69092	Loss: 150.193
+38400/69092	Loss: 147.900
+41600/69092	Loss: 151.263
+44800/69092	Loss: 147.189
+48000/69092	Loss: 147.041
+51200/69092	Loss: 146.532
+54400/69092	Loss: 148.287
+57600/69092	Loss: 145.252
+60800/69092	Loss: 148.043
+64000/69092	Loss: 147.553
+67200/69092	Loss: 146.769
+Training time 0:08:06.081523
+Epoch: 38 Average loss: 147.82
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 456)
+0/69092	Loss: 150.797
+3200/69092	Loss: 147.095
+6400/69092	Loss: 145.967
+9600/69092	Loss: 148.106
+12800/69092	Loss: 149.112
+16000/69092	Loss: 149.403
+19200/69092	Loss: 148.268
+22400/69092	Loss: 145.286
+25600/69092	Loss: 147.793
+28800/69092	Loss: 149.574
+32000/69092	Loss: 147.595
+35200/69092	Loss: 148.577
+38400/69092	Loss: 149.670
+41600/69092	Loss: 147.611
+44800/69092	Loss: 149.895
+48000/69092	Loss: 146.503
+51200/69092	Loss: 147.977
+54400/69092	Loss: 145.945
+57600/69092	Loss: 147.262
+60800/69092	Loss: 146.957
+64000/69092	Loss: 146.696
+67200/69092	Loss: 149.292
+Training time 0:07:53.634117
+Epoch: 39 Average loss: 147.85
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 457)
+0/69092	Loss: 137.992
+3200/69092	Loss: 149.550
+6400/69092	Loss: 147.822
+9600/69092	Loss: 149.553
+12800/69092	Loss: 148.779
+16000/69092	Loss: 150.581
+19200/69092	Loss: 145.373
+22400/69092	Loss: 146.937
+25600/69092	Loss: 146.867
+28800/69092	Loss: 146.965
+32000/69092	Loss: 147.773
+35200/69092	Loss: 146.226
+38400/69092	Loss: 149.469
+41600/69092	Loss: 146.900
+44800/69092	Loss: 148.533
+48000/69092	Loss: 146.440
+51200/69092	Loss: 146.106
+54400/69092	Loss: 146.527
+57600/69092	Loss: 147.226
+60800/69092	Loss: 146.908
+64000/69092	Loss: 151.346
+67200/69092	Loss: 147.449
+Training time 0:08:11.125053
+Epoch: 40 Average loss: 147.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 458)
+0/69092	Loss: 151.597
+3200/69092	Loss: 148.039
+6400/69092	Loss: 146.658
+9600/69092	Loss: 149.576
+12800/69092	Loss: 147.667
+16000/69092	Loss: 146.826
+19200/69092	Loss: 149.286
+22400/69092	Loss: 148.785
+25600/69092	Loss: 148.059
+28800/69092	Loss: 145.862
+32000/69092	Loss: 147.839
+35200/69092	Loss: 146.473
+38400/69092	Loss: 148.723
+41600/69092	Loss: 146.382
+44800/69092	Loss: 148.383
+48000/69092	Loss: 146.915
+51200/69092	Loss: 151.326
+54400/69092	Loss: 146.806
+57600/69092	Loss: 146.054
+60800/69092	Loss: 148.095
+64000/69092	Loss: 147.353
+67200/69092	Loss: 147.817
+Training time 0:08:05.367305
+Epoch: 41 Average loss: 147.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 459)
+0/69092	Loss: 137.070
+3200/69092	Loss: 149.880
+6400/69092	Loss: 144.188
+9600/69092	Loss: 146.220
+12800/69092	Loss: 147.654
+16000/69092	Loss: 149.157
+19200/69092	Loss: 147.671
+22400/69092	Loss: 150.200
+25600/69092	Loss: 148.826
+28800/69092	Loss: 150.492
+32000/69092	Loss: 146.492
+35200/69092	Loss: 148.099
+38400/69092	Loss: 146.570
+41600/69092	Loss: 147.864
+44800/69092	Loss: 145.999
+48000/69092	Loss: 146.403
+51200/69092	Loss: 148.065
+54400/69092	Loss: 150.361
+57600/69092	Loss: 149.461
+60800/69092	Loss: 146.866
+64000/69092	Loss: 147.946
+67200/69092	Loss: 147.057
+Training time 0:07:59.299594
+Epoch: 42 Average loss: 147.86
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 460)
+0/69092	Loss: 156.091
+3200/69092	Loss: 146.357
+6400/69092	Loss: 147.889
+9600/69092	Loss: 147.301
+12800/69092	Loss: 149.765
+16000/69092	Loss: 147.479
+19200/69092	Loss: 146.767
+22400/69092	Loss: 148.197
+25600/69092	Loss: 148.841
+28800/69092	Loss: 150.382
+32000/69092	Loss: 147.229
+35200/69092	Loss: 146.671
+38400/69092	Loss: 149.988
+41600/69092	Loss: 147.914
+44800/69092	Loss: 148.624
+48000/69092	Loss: 146.680
+51200/69092	Loss: 148.477
+54400/69092	Loss: 149.339
+57600/69092	Loss: 148.026
+60800/69092	Loss: 148.727
+64000/69092	Loss: 147.142
+67200/69092	Loss: 148.418
+Training time 0:08:13.834192
+Epoch: 43 Average loss: 148.09
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 461)
+0/69092	Loss: 145.296
+3200/69092	Loss: 149.456
+6400/69092	Loss: 149.430
+9600/69092	Loss: 149.795
+12800/69092	Loss: 147.863
+16000/69092	Loss: 146.812
+19200/69092	Loss: 147.363
+22400/69092	Loss: 148.909
+25600/69092	Loss: 149.190
+28800/69092	Loss: 147.190
+32000/69092	Loss: 148.826
+35200/69092	Loss: 147.786
+38400/69092	Loss: 148.715
+41600/69092	Loss: 145.456
+44800/69092	Loss: 149.306
+48000/69092	Loss: 147.830
+51200/69092	Loss: 143.954
+54400/69092	Loss: 147.292
+57600/69092	Loss: 144.963
+60800/69092	Loss: 150.076
+64000/69092	Loss: 147.673
+67200/69092	Loss: 148.857
+Training time 0:08:08.137736
+Epoch: 44 Average loss: 147.90
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 462)
+0/69092	Loss: 135.402
+3200/69092	Loss: 145.745
+6400/69092	Loss: 147.940
+9600/69092	Loss: 147.087
+12800/69092	Loss: 146.681
+16000/69092	Loss: 147.194
+19200/69092	Loss: 148.038
+22400/69092	Loss: 148.515
+25600/69092	Loss: 150.095
+28800/69092	Loss: 146.330
+32000/69092	Loss: 145.407
+35200/69092	Loss: 149.563
+38400/69092	Loss: 150.124
+41600/69092	Loss: 149.799
+44800/69092	Loss: 149.942
+48000/69092	Loss: 148.292
+51200/69092	Loss: 148.653
+54400/69092	Loss: 147.412
+57600/69092	Loss: 146.634
+60800/69092	Loss: 146.140
+64000/69092	Loss: 148.629
+67200/69092	Loss: 146.649
+Training time 0:08:04.533059
+Epoch: 45 Average loss: 147.84
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 463)
+0/69092	Loss: 134.291
+3200/69092	Loss: 149.769
+6400/69092	Loss: 150.208
+9600/69092	Loss: 148.465
+12800/69092	Loss: 145.368
+16000/69092	Loss: 145.483
+19200/69092	Loss: 146.001
+22400/69092	Loss: 149.066
+25600/69092	Loss: 147.709
+28800/69092	Loss: 148.044
+32000/69092	Loss: 147.961
+35200/69092	Loss: 147.483
+38400/69092	Loss: 149.518
+41600/69092	Loss: 146.165
+44800/69092	Loss: 146.633
+48000/69092	Loss: 148.310
+51200/69092	Loss: 148.504
+54400/69092	Loss: 146.682
+57600/69092	Loss: 152.826
+60800/69092	Loss: 149.200
+64000/69092	Loss: 149.433
+67200/69092	Loss: 146.115
+Training time 0:08:20.033304
+Epoch: 46 Average loss: 147.99
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 464)
+0/69092	Loss: 142.656
+3200/69092	Loss: 146.437
+6400/69092	Loss: 147.613
+9600/69092	Loss: 146.981
+12800/69092	Loss: 149.262
+16000/69092	Loss: 147.658
+19200/69092	Loss: 147.653
+22400/69092	Loss: 147.737
+25600/69092	Loss: 150.158
+28800/69092	Loss: 147.674
+32000/69092	Loss: 147.185
+35200/69092	Loss: 146.266
+38400/69092	Loss: 148.152
+41600/69092	Loss: 148.771
+44800/69092	Loss: 148.195
+48000/69092	Loss: 146.765
+51200/69092	Loss: 148.167
+54400/69092	Loss: 149.248
+57600/69092	Loss: 146.866
+60800/69092	Loss: 148.037
+64000/69092	Loss: 149.821
+67200/69092	Loss: 149.010
+Training time 0:08:08.210877
+Epoch: 47 Average loss: 148.02
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 465)
+0/69092	Loss: 141.979
+3200/69092	Loss: 146.551
+6400/69092	Loss: 144.719
+9600/69092	Loss: 147.675
+12800/69092	Loss: 149.406
+16000/69092	Loss: 149.955
+19200/69092	Loss: 149.545
+22400/69092	Loss: 148.148
+25600/69092	Loss: 147.784
+28800/69092	Loss: 143.561
+32000/69092	Loss: 146.728
+35200/69092	Loss: 148.039
+38400/69092	Loss: 149.162
+41600/69092	Loss: 145.788
+44800/69092	Loss: 148.363
+48000/69092	Loss: 147.782
+51200/69092	Loss: 147.930
+54400/69092	Loss: 148.442
+57600/69092	Loss: 149.321
+60800/69092	Loss: 149.428
+64000/69092	Loss: 146.285
+67200/69092	Loss: 147.884
+Training time 0:07:59.799955
+Epoch: 48 Average loss: 147.81
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 466)
+0/69092	Loss: 172.191
+3200/69092	Loss: 146.721
+6400/69092	Loss: 142.361
+9600/69092	Loss: 148.484
+12800/69092	Loss: 149.466
+16000/69092	Loss: 147.471
+19200/69092	Loss: 149.073
+22400/69092	Loss: 148.399
+25600/69092	Loss: 148.828
+28800/69092	Loss: 147.570
+32000/69092	Loss: 147.190
+35200/69092	Loss: 146.663
+38400/69092	Loss: 148.451
+41600/69092	Loss: 147.317
+44800/69092	Loss: 148.366
+48000/69092	Loss: 149.674
+51200/69092	Loss: 146.408
+54400/69092	Loss: 148.305
+57600/69092	Loss: 148.341
+60800/69092	Loss: 147.900
+64000/69092	Loss: 148.286
+67200/69092	Loss: 146.068
+Training time 0:08:16.050488
+Epoch: 49 Average loss: 147.75
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 467)
+0/69092	Loss: 142.790
+3200/69092	Loss: 146.814
+6400/69092	Loss: 148.383
+9600/69092	Loss: 144.958
+12800/69092	Loss: 149.076
+16000/69092	Loss: 147.434
+19200/69092	Loss: 150.512
+22400/69092	Loss: 148.685
+25600/69092	Loss: 148.754
+28800/69092	Loss: 145.935
+32000/69092	Loss: 146.291
+35200/69092	Loss: 148.561
+38400/69092	Loss: 150.090
+41600/69092	Loss: 148.168
+44800/69092	Loss: 146.254
+48000/69092	Loss: 149.541
+51200/69092	Loss: 146.826
+54400/69092	Loss: 147.428
+57600/69092	Loss: 147.312
+60800/69092	Loss: 146.237
+64000/69092	Loss: 147.917
+67200/69092	Loss: 147.982
+Training time 0:07:59.060184
+Epoch: 50 Average loss: 147.81
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 468)
+0/69092	Loss: 138.113
+3200/69092	Loss: 147.075
+6400/69092	Loss: 147.436
+9600/69092	Loss: 147.216
+12800/69092	Loss: 151.128
+16000/69092	Loss: 147.135
+19200/69092	Loss: 149.678
+22400/69092	Loss: 150.715
+25600/69092	Loss: 147.066
+28800/69092	Loss: 145.876
+32000/69092	Loss: 148.671
+35200/69092	Loss: 149.096
+38400/69092	Loss: 147.086
+41600/69092	Loss: 146.227
+44800/69092	Loss: 146.770
+48000/69092	Loss: 148.102
+51200/69092	Loss: 147.864
+54400/69092	Loss: 146.793
+57600/69092	Loss: 148.213
+60800/69092	Loss: 147.481
+64000/69092	Loss: 148.723
+67200/69092	Loss: 145.572
+Training time 0:08:05.098546
+Epoch: 51 Average loss: 147.78
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 469)
+0/69092	Loss: 138.135
+3200/69092	Loss: 145.227
+6400/69092	Loss: 148.162
+9600/69092	Loss: 150.537
+12800/69092	Loss: 147.951
+16000/69092	Loss: 146.280
+19200/69092	Loss: 149.030
+22400/69092	Loss: 149.056
+25600/69092	Loss: 144.649
+28800/69092	Loss: 147.771
+32000/69092	Loss: 146.186
+35200/69092	Loss: 146.767
+38400/69092	Loss: 149.182
+41600/69092	Loss: 147.523
+44800/69092	Loss: 149.208
+48000/69092	Loss: 149.837
+51200/69092	Loss: 144.433
+54400/69092	Loss: 146.990
+57600/69092	Loss: 148.214
+60800/69092	Loss: 151.211
+64000/69092	Loss: 147.203
+67200/69092	Loss: 149.614
+Training time 0:08:05.860257
+Epoch: 52 Average loss: 147.86
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 470)
+0/69092	Loss: 134.241
+3200/69092	Loss: 147.406
+6400/69092	Loss: 148.054
+9600/69092	Loss: 147.130
+12800/69092	Loss: 146.299
+16000/69092	Loss: 147.966
+19200/69092	Loss: 145.672
+22400/69092	Loss: 147.195
+25600/69092	Loss: 149.086
+28800/69092	Loss: 147.373
+32000/69092	Loss: 146.088
+35200/69092	Loss: 146.685
+38400/69092	Loss: 149.995
+41600/69092	Loss: 147.336
+44800/69092	Loss: 147.009
+48000/69092	Loss: 147.086
+51200/69092	Loss: 147.297
+54400/69092	Loss: 147.429
+57600/69092	Loss: 149.985
+60800/69092	Loss: 145.981
+64000/69092	Loss: 148.734
+67200/69092	Loss: 148.410
+Training time 0:08:01.590198
+Epoch: 53 Average loss: 147.56
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 471)
+0/69092	Loss: 155.960
+3200/69092	Loss: 148.155
+6400/69092	Loss: 148.295
+9600/69092	Loss: 144.030
+12800/69092	Loss: 147.189
+16000/69092	Loss: 148.088
+19200/69092	Loss: 147.126
+22400/69092	Loss: 148.164
+25600/69092	Loss: 148.587
+28800/69092	Loss: 147.496
+32000/69092	Loss: 145.704
+35200/69092	Loss: 148.467
+38400/69092	Loss: 146.380
+41600/69092	Loss: 150.873
+44800/69092	Loss: 144.490
+48000/69092	Loss: 148.206
+51200/69092	Loss: 146.042
+54400/69092	Loss: 150.670
+57600/69092	Loss: 147.252
+60800/69092	Loss: 151.639
+64000/69092	Loss: 146.631
+67200/69092	Loss: 149.878
+Training time 0:08:01.247998
+Epoch: 54 Average loss: 147.86
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 472)
+0/69092	Loss: 149.394
+3200/69092	Loss: 150.620
+6400/69092	Loss: 149.638
+9600/69092	Loss: 146.113
+12800/69092	Loss: 147.130
+16000/69092	Loss: 148.149
+19200/69092	Loss: 148.539
+22400/69092	Loss: 148.260
+25600/69092	Loss: 145.291
+28800/69092	Loss: 146.523
+32000/69092	Loss: 148.225
+35200/69092	Loss: 147.852
+38400/69092	Loss: 148.826
+41600/69092	Loss: 148.099
+44800/69092	Loss: 145.906
+48000/69092	Loss: 147.891
+51200/69092	Loss: 147.586
+54400/69092	Loss: 148.273
+57600/69092	Loss: 147.848
+60800/69092	Loss: 147.545
+64000/69092	Loss: 146.404
+67200/69092	Loss: 147.911
+Training time 0:08:07.731624
+Epoch: 55 Average loss: 147.75
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 473)
+0/69092	Loss: 145.554
+3200/69092	Loss: 148.096
+6400/69092	Loss: 146.533
+9600/69092	Loss: 144.554
+12800/69092	Loss: 145.518
+16000/69092	Loss: 148.028
+19200/69092	Loss: 148.519
+22400/69092	Loss: 147.132
+25600/69092	Loss: 147.399
+28800/69092	Loss: 148.102
+32000/69092	Loss: 147.398
+35200/69092	Loss: 149.871
+38400/69092	Loss: 148.646
+41600/69092	Loss: 149.078
+44800/69092	Loss: 147.635
+48000/69092	Loss: 147.394
+51200/69092	Loss: 148.157
+54400/69092	Loss: 146.131
+57600/69092	Loss: 149.055
+60800/69092	Loss: 149.161
+64000/69092	Loss: 148.470
+67200/69092	Loss: 148.216
+Training time 0:07:59.311078
+Epoch: 56 Average loss: 147.79
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 474)
+0/69092	Loss: 146.526
+3200/69092	Loss: 146.871
+6400/69092	Loss: 147.454
+9600/69092	Loss: 148.470
+12800/69092	Loss: 146.253
+16000/69092	Loss: 149.347
+19200/69092	Loss: 148.875
+22400/69092	Loss: 148.004
+25600/69092	Loss: 147.982
+28800/69092	Loss: 148.783
+32000/69092	Loss: 149.006
+35200/69092	Loss: 149.213
+38400/69092	Loss: 148.202
+41600/69092	Loss: 144.362
+44800/69092	Loss: 147.079
+48000/69092	Loss: 146.207
+51200/69092	Loss: 145.895
+54400/69092	Loss: 149.871
+57600/69092	Loss: 148.416
+60800/69092	Loss: 150.377
+64000/69092	Loss: 146.150
+67200/69092	Loss: 147.322
+Training time 0:08:08.323224
+Epoch: 57 Average loss: 147.77
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 475)
+0/69092	Loss: 156.756
+3200/69092	Loss: 147.819
+6400/69092	Loss: 146.791
+9600/69092	Loss: 146.817
+12800/69092	Loss: 146.121
+16000/69092	Loss: 149.812
+19200/69092	Loss: 145.045
+22400/69092	Loss: 147.587
+25600/69092	Loss: 149.517
+28800/69092	Loss: 149.582
+32000/69092	Loss: 149.649
+35200/69092	Loss: 149.031
+38400/69092	Loss: 148.733
+41600/69092	Loss: 148.798
+44800/69092	Loss: 148.223
+48000/69092	Loss: 147.306
+51200/69092	Loss: 149.765
+54400/69092	Loss: 147.611
+57600/69092	Loss: 148.472
+60800/69092	Loss: 144.799
+64000/69092	Loss: 146.900
+67200/69092	Loss: 146.943
+Training time 0:08:16.767151
+Epoch: 58 Average loss: 147.88
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 476)
+0/69092	Loss: 166.062
+3200/69092	Loss: 146.490
+6400/69092	Loss: 150.273
+9600/69092	Loss: 146.619
+12800/69092	Loss: 147.692
+16000/69092	Loss: 145.404
+19200/69092	Loss: 150.362
+22400/69092	Loss: 149.257
+25600/69092	Loss: 148.728
+28800/69092	Loss: 148.697
+32000/69092	Loss: 146.319
+35200/69092	Loss: 146.263
+38400/69092	Loss: 146.905
+41600/69092	Loss: 148.212
+44800/69092	Loss: 146.479
+48000/69092	Loss: 146.932
+51200/69092	Loss: 149.571
+54400/69092	Loss: 148.682
+57600/69092	Loss: 147.077
+60800/69092	Loss: 146.838
+64000/69092	Loss: 148.488
+67200/69092	Loss: 149.977
+Training time 0:08:06.254737
+Epoch: 59 Average loss: 147.87
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 477)
+0/69092	Loss: 164.949
+3200/69092	Loss: 149.320
+6400/69092	Loss: 150.263
+9600/69092	Loss: 146.362
+12800/69092	Loss: 144.981
+16000/69092	Loss: 147.118
+19200/69092	Loss: 146.999
+22400/69092	Loss: 146.674
+25600/69092	Loss: 148.998
+28800/69092	Loss: 148.602
+32000/69092	Loss: 147.459
+35200/69092	Loss: 148.472
+38400/69092	Loss: 149.124
+41600/69092	Loss: 149.270
+44800/69092	Loss: 148.242
+48000/69092	Loss: 149.437
+51200/69092	Loss: 146.726
+54400/69092	Loss: 145.715
+57600/69092	Loss: 147.939
+60800/69092	Loss: 147.379
+64000/69092	Loss: 148.864
+67200/69092	Loss: 147.665
+Training time 0:08:11.309099
+Epoch: 60 Average loss: 147.85
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 478)
+0/69092	Loss: 150.170
+3200/69092	Loss: 146.303
+6400/69092	Loss: 149.527
+9600/69092	Loss: 146.989
+12800/69092	Loss: 148.267
+16000/69092	Loss: 148.765
+19200/69092	Loss: 148.736
+22400/69092	Loss: 148.196
+25600/69092	Loss: 146.703
+28800/69092	Loss: 146.208
+32000/69092	Loss: 148.105
+35200/69092	Loss: 149.833
+38400/69092	Loss: 146.248
+41600/69092	Loss: 148.791
+44800/69092	Loss: 146.799
+48000/69092	Loss: 147.169
+51200/69092	Loss: 147.322
+54400/69092	Loss: 147.924
+57600/69092	Loss: 147.948
+60800/69092	Loss: 147.565
+64000/69092	Loss: 148.086
+67200/69092	Loss: 148.707
+Training time 0:08:12.296952
+Epoch: 61 Average loss: 147.76
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 479)
+0/69092	Loss: 161.114
+3200/69092	Loss: 146.314
+6400/69092	Loss: 148.966
+9600/69092	Loss: 149.766
+12800/69092	Loss: 148.643
+16000/69092	Loss: 147.866
+19200/69092	Loss: 147.891
+22400/69092	Loss: 147.430
+25600/69092	Loss: 147.493
+28800/69092	Loss: 146.280
+32000/69092	Loss: 147.055
+35200/69092	Loss: 148.138
+38400/69092	Loss: 147.175
+41600/69092	Loss: 147.260
+44800/69092	Loss: 147.012
+48000/69092	Loss: 147.416
+51200/69092	Loss: 148.775
+54400/69092	Loss: 150.922
+57600/69092	Loss: 147.944
+60800/69092	Loss: 145.582
+64000/69092	Loss: 149.088
+67200/69092	Loss: 146.646
+Training time 0:08:02.683893
+Epoch: 62 Average loss: 147.87
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 480)
+0/69092	Loss: 132.742
+3200/69092	Loss: 149.377
+6400/69092	Loss: 147.588
+9600/69092	Loss: 146.643
+12800/69092	Loss: 145.527
+16000/69092	Loss: 146.099
+19200/69092	Loss: 148.547
+22400/69092	Loss: 148.333
+25600/69092	Loss: 148.210
+28800/69092	Loss: 148.356
+32000/69092	Loss: 147.654
+35200/69092	Loss: 148.502
+38400/69092	Loss: 148.352
+41600/69092	Loss: 148.618
+44800/69092	Loss: 147.938
+48000/69092	Loss: 144.796
+51200/69092	Loss: 149.221
+54400/69092	Loss: 147.302
+57600/69092	Loss: 148.802
+60800/69092	Loss: 148.363
+64000/69092	Loss: 145.717
+67200/69092	Loss: 146.996
+Training time 0:08:03.994530
+Epoch: 63 Average loss: 147.79
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 481)
+0/69092	Loss: 158.100
+3200/69092	Loss: 148.050
+6400/69092	Loss: 146.655
+9600/69092	Loss: 148.858
+12800/69092	Loss: 145.539
+16000/69092	Loss: 146.745
+19200/69092	Loss: 150.005
+22400/69092	Loss: 150.585
+25600/69092	Loss: 147.427
+28800/69092	Loss: 146.490
+32000/69092	Loss: 146.466
+35200/69092	Loss: 147.380
+38400/69092	Loss: 146.968
+41600/69092	Loss: 148.550
+44800/69092	Loss: 151.894
+48000/69092	Loss: 145.848
+51200/69092	Loss: 146.153
+54400/69092	Loss: 149.692
+57600/69092	Loss: 147.893
+60800/69092	Loss: 146.377
+64000/69092	Loss: 146.444
+67200/69092	Loss: 148.846
+Training time 0:08:20.347860
+Epoch: 64 Average loss: 147.78
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 482)
+0/69092	Loss: 156.470
+3200/69092	Loss: 147.868
+6400/69092	Loss: 147.238
+9600/69092	Loss: 147.330
+12800/69092	Loss: 143.805
+16000/69092	Loss: 148.650
+19200/69092	Loss: 148.664
+22400/69092	Loss: 148.092
+25600/69092	Loss: 148.626
+28800/69092	Loss: 147.226
+32000/69092	Loss: 144.805
+35200/69092	Loss: 148.884
+38400/69092	Loss: 146.363
+41600/69092	Loss: 148.717
+44800/69092	Loss: 148.801
+48000/69092	Loss: 146.797
+51200/69092	Loss: 147.627
+54400/69092	Loss: 149.043
+57600/69092	Loss: 149.468
+60800/69092	Loss: 148.037
+64000/69092	Loss: 147.522
+67200/69092	Loss: 148.540
+Training time 0:08:00.876787
+Epoch: 65 Average loss: 147.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 483)
+0/69092	Loss: 149.686
+3200/69092	Loss: 145.144
+6400/69092	Loss: 147.802
+9600/69092	Loss: 144.740
+12800/69092	Loss: 148.536
+16000/69092	Loss: 148.564
+19200/69092	Loss: 147.007
+22400/69092	Loss: 149.423
+25600/69092	Loss: 148.068
+28800/69092	Loss: 145.189
+32000/69092	Loss: 147.339
+35200/69092	Loss: 148.305
+38400/69092	Loss: 146.814
+41600/69092	Loss: 145.674
+44800/69092	Loss: 148.672
+48000/69092	Loss: 147.767
+51200/69092	Loss: 148.660
+54400/69092	Loss: 148.286
+57600/69092	Loss: 150.484
+60800/69092	Loss: 151.237
+64000/69092	Loss: 149.309
+67200/69092	Loss: 147.670
+Training time 0:08:01.836567
+Epoch: 66 Average loss: 147.93
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 484)
+0/69092	Loss: 134.220
+3200/69092	Loss: 147.559
+6400/69092	Loss: 148.264
+9600/69092	Loss: 148.192
+12800/69092	Loss: 147.086
+16000/69092	Loss: 150.275
+19200/69092	Loss: 145.772
+22400/69092	Loss: 147.116
+25600/69092	Loss: 148.544
+28800/69092	Loss: 145.792
+32000/69092	Loss: 149.287
+35200/69092	Loss: 147.223
+38400/69092	Loss: 148.293
+41600/69092	Loss: 147.027
+44800/69092	Loss: 148.958
+48000/69092	Loss: 148.512
+51200/69092	Loss: 148.366
+54400/69092	Loss: 147.952
+57600/69092	Loss: 147.857
+60800/69092	Loss: 146.250
+64000/69092	Loss: 148.176
+67200/69092	Loss: 146.308
+Training time 0:08:10.463024
+Epoch: 67 Average loss: 147.80
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 485)
+0/69092	Loss: 150.623
+3200/69092	Loss: 147.072
+6400/69092	Loss: 148.225
+9600/69092	Loss: 148.183
+12800/69092	Loss: 147.470
+16000/69092	Loss: 145.792
+19200/69092	Loss: 147.714
+22400/69092	Loss: 146.061
+25600/69092	Loss: 146.760
+28800/69092	Loss: 146.819
+32000/69092	Loss: 148.986
+35200/69092	Loss: 147.071
+38400/69092	Loss: 149.131
+41600/69092	Loss: 150.407
+44800/69092	Loss: 146.936
+48000/69092	Loss: 148.496
+51200/69092	Loss: 147.860
+54400/69092	Loss: 148.570
+57600/69092	Loss: 146.489
+60800/69092	Loss: 149.126
+64000/69092	Loss: 148.316
+67200/69092	Loss: 146.348
+Training time 0:07:54.026186
+Epoch: 68 Average loss: 147.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 486)
+0/69092	Loss: 159.239
+3200/69092	Loss: 148.075
+6400/69092	Loss: 147.400
+9600/69092	Loss: 149.850
+12800/69092	Loss: 146.572
+16000/69092	Loss: 148.331
+19200/69092	Loss: 146.869
+22400/69092	Loss: 147.211
+25600/69092	Loss: 147.775
+28800/69092	Loss: 147.969
+32000/69092	Loss: 147.285
+35200/69092	Loss: 147.255
+38400/69092	Loss: 148.382
+41600/69092	Loss: 146.525
+44800/69092	Loss: 146.984
+48000/69092	Loss: 147.473
+51200/69092	Loss: 147.320
+54400/69092	Loss: 147.303
+57600/69092	Loss: 148.118
+60800/69092	Loss: 150.639
+64000/69092	Loss: 146.166
+67200/69092	Loss: 148.848
+Training time 0:08:07.657566
+Epoch: 69 Average loss: 147.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 487)
+0/69092	Loss: 152.437
+3200/69092	Loss: 146.726
+6400/69092	Loss: 145.381
+9600/69092	Loss: 146.292
+12800/69092	Loss: 147.554
+16000/69092	Loss: 147.518
+19200/69092	Loss: 147.292
+22400/69092	Loss: 147.597
+25600/69092	Loss: 146.593
+28800/69092	Loss: 148.970
+32000/69092	Loss: 146.340
+35200/69092	Loss: 150.680
+38400/69092	Loss: 150.258
+41600/69092	Loss: 147.113
+44800/69092	Loss: 146.031
+48000/69092	Loss: 148.553
+51200/69092	Loss: 148.968
+54400/69092	Loss: 149.680
+57600/69092	Loss: 149.045
+60800/69092	Loss: 147.915
+64000/69092	Loss: 148.425
+67200/69092	Loss: 149.528
+Training time 0:08:12.730213
+Epoch: 70 Average loss: 147.92
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 488)
+0/69092	Loss: 150.596
+3200/69092	Loss: 147.031
+6400/69092	Loss: 147.127
+9600/69092	Loss: 148.107
+12800/69092	Loss: 144.678
+16000/69092	Loss: 149.595
+19200/69092	Loss: 146.229
+22400/69092	Loss: 149.459
+25600/69092	Loss: 146.053
+28800/69092	Loss: 147.049
+32000/69092	Loss: 149.130
+35200/69092	Loss: 149.700
+38400/69092	Loss: 147.908
+41600/69092	Loss: 146.448
+44800/69092	Loss: 148.774
+48000/69092	Loss: 146.317
+51200/69092	Loss: 147.227
+54400/69092	Loss: 147.296
+57600/69092	Loss: 145.805
+60800/69092	Loss: 147.846
+64000/69092	Loss: 148.879
+67200/69092	Loss: 147.286
+Training time 0:08:00.545413
+Epoch: 71 Average loss: 147.56
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 489)
+0/69092	Loss: 153.573
+3200/69092	Loss: 150.779
+6400/69092	Loss: 148.933
+9600/69092	Loss: 148.347
+12800/69092	Loss: 149.494
+16000/69092	Loss: 146.201
+19200/69092	Loss: 148.578
+22400/69092	Loss: 147.148
+25600/69092	Loss: 148.903
+28800/69092	Loss: 149.757
+32000/69092	Loss: 144.795
+35200/69092	Loss: 146.287
+38400/69092	Loss: 146.238
+41600/69092	Loss: 150.254
+44800/69092	Loss: 146.729
+48000/69092	Loss: 148.038
+51200/69092	Loss: 146.533
+54400/69092	Loss: 149.126
+57600/69092	Loss: 147.769
+60800/69092	Loss: 144.744
+64000/69092	Loss: 146.757
+67200/69092	Loss: 147.329
+Training time 0:08:05.859777
+Epoch: 72 Average loss: 147.72
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 490)
+0/69092	Loss: 142.988
+3200/69092	Loss: 149.538
+6400/69092	Loss: 148.085
+9600/69092	Loss: 144.918
+12800/69092	Loss: 149.324
+16000/69092	Loss: 146.290
+19200/69092	Loss: 148.996
+22400/69092	Loss: 147.449
+25600/69092	Loss: 148.123
+28800/69092	Loss: 147.910
+32000/69092	Loss: 146.773
+35200/69092	Loss: 147.690
+38400/69092	Loss: 149.474
+41600/69092	Loss: 147.384
+44800/69092	Loss: 146.233
+48000/69092	Loss: 147.615
+51200/69092	Loss: 148.699
+54400/69092	Loss: 147.564
+57600/69092	Loss: 146.802
+60800/69092	Loss: 146.808
+64000/69092	Loss: 148.041
+67200/69092	Loss: 147.266
+Training time 0:08:12.850143
+Epoch: 73 Average loss: 147.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 491)
+0/69092	Loss: 160.430
+3200/69092	Loss: 146.395
+6400/69092	Loss: 147.341
+9600/69092	Loss: 149.192
+12800/69092	Loss: 144.175
+16000/69092	Loss: 147.611
+19200/69092	Loss: 146.300
+22400/69092	Loss: 146.721
+25600/69092	Loss: 146.007
+28800/69092	Loss: 147.536
+32000/69092	Loss: 146.327
+35200/69092	Loss: 148.050
+38400/69092	Loss: 149.947
+41600/69092	Loss: 146.226
+44800/69092	Loss: 149.838
+48000/69092	Loss: 149.326
+51200/69092	Loss: 146.998
+54400/69092	Loss: 148.815
+57600/69092	Loss: 149.600
+60800/69092	Loss: 148.327
+64000/69092	Loss: 149.284
+67200/69092	Loss: 145.096
+Training time 0:07:54.301976
+Epoch: 74 Average loss: 147.63
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 492)
+0/69092	Loss: 118.721
+3200/69092	Loss: 146.334
+6400/69092	Loss: 145.412
+9600/69092	Loss: 147.852
+12800/69092	Loss: 147.854
+16000/69092	Loss: 147.607
+19200/69092	Loss: 146.192
+22400/69092	Loss: 149.040
+25600/69092	Loss: 145.435
+28800/69092	Loss: 148.128
+32000/69092	Loss: 147.518
+35200/69092	Loss: 149.242
+38400/69092	Loss: 148.009
+41600/69092	Loss: 151.082
+44800/69092	Loss: 148.590
+48000/69092	Loss: 145.866
+51200/69092	Loss: 147.532
+54400/69092	Loss: 148.850
+57600/69092	Loss: 149.558
+60800/69092	Loss: 147.745
+64000/69092	Loss: 148.991
+67200/69092	Loss: 148.642
+Training time 0:08:07.135607
+Epoch: 75 Average loss: 147.93
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 493)
+0/69092	Loss: 162.003
+3200/69092	Loss: 146.595
+6400/69092	Loss: 145.067
+9600/69092	Loss: 147.766
+12800/69092	Loss: 145.111
+16000/69092	Loss: 147.810
+19200/69092	Loss: 147.221
+22400/69092	Loss: 147.677
+25600/69092	Loss: 149.013
+28800/69092	Loss: 148.079
+32000/69092	Loss: 147.279
+35200/69092	Loss: 149.759
+38400/69092	Loss: 147.905
+41600/69092	Loss: 148.204
+44800/69092	Loss: 147.397
+48000/69092	Loss: 149.801
+51200/69092	Loss: 146.389
+54400/69092	Loss: 148.871
+57600/69092	Loss: 148.890
+60800/69092	Loss: 148.565
+64000/69092	Loss: 147.958
+67200/69092	Loss: 146.508
+Training time 0:08:15.098624
+Epoch: 76 Average loss: 147.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 494)
+0/69092	Loss: 156.167
+3200/69092	Loss: 147.619
+6400/69092	Loss: 147.630
+9600/69092	Loss: 148.685
+12800/69092	Loss: 146.421
+16000/69092	Loss: 148.485
+19200/69092	Loss: 147.908
+22400/69092	Loss: 146.355
+25600/69092	Loss: 148.664
+28800/69092	Loss: 148.097
+32000/69092	Loss: 149.818
+35200/69092	Loss: 146.800
+38400/69092	Loss: 146.318
+41600/69092	Loss: 148.177
+44800/69092	Loss: 147.624
+48000/69092	Loss: 147.742
+51200/69092	Loss: 150.796
+54400/69092	Loss: 146.732
+57600/69092	Loss: 147.670
+60800/69092	Loss: 148.511
+64000/69092	Loss: 146.433
+67200/69092	Loss: 146.693
+Training time 0:08:02.243860
+Epoch: 77 Average loss: 147.79
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 495)
+0/69092	Loss: 155.573
+3200/69092	Loss: 149.174
+6400/69092	Loss: 147.261
+9600/69092	Loss: 148.125
+12800/69092	Loss: 146.556
+16000/69092	Loss: 147.495
+19200/69092	Loss: 149.037
+22400/69092	Loss: 148.689
+25600/69092	Loss: 145.319
+28800/69092	Loss: 147.632
+32000/69092	Loss: 146.534
+35200/69092	Loss: 145.337
+38400/69092	Loss: 149.021
+41600/69092	Loss: 147.914
+44800/69092	Loss: 150.437
+48000/69092	Loss: 146.795
+51200/69092	Loss: 147.591
+54400/69092	Loss: 148.298
+57600/69092	Loss: 148.966
+60800/69092	Loss: 147.551
+64000/69092	Loss: 146.674
+67200/69092	Loss: 144.583
+Training time 0:08:09.306475
+Epoch: 78 Average loss: 147.56
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 496)
+0/69092	Loss: 134.958
+3200/69092	Loss: 150.737
+6400/69092	Loss: 147.099
+9600/69092	Loss: 145.468
+12800/69092	Loss: 149.608
+16000/69092	Loss: 147.893
+19200/69092	Loss: 148.544
+22400/69092	Loss: 147.294
+25600/69092	Loss: 147.239
+28800/69092	Loss: 145.701
+32000/69092	Loss: 148.572
+35200/69092	Loss: 147.888
+38400/69092	Loss: 145.297
+41600/69092	Loss: 146.695
+44800/69092	Loss: 148.117
+48000/69092	Loss: 148.865
+51200/69092	Loss: 149.021
+54400/69092	Loss: 146.633
+57600/69092	Loss: 146.149
+60800/69092	Loss: 147.611
+64000/69092	Loss: 148.343
+67200/69092	Loss: 149.154
+Training time 0:08:17.476480
+Epoch: 79 Average loss: 147.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 497)
+0/69092	Loss: 137.519
+3200/69092	Loss: 146.366
+6400/69092	Loss: 150.280
+9600/69092	Loss: 149.294
+12800/69092	Loss: 146.915
+16000/69092	Loss: 146.916
+19200/69092	Loss: 145.042
+22400/69092	Loss: 147.667
+25600/69092	Loss: 147.308
+28800/69092	Loss: 147.992
+32000/69092	Loss: 151.514
+35200/69092	Loss: 145.262
+38400/69092	Loss: 147.613
+41600/69092	Loss: 148.685
+44800/69092	Loss: 147.722
+48000/69092	Loss: 145.971
+51200/69092	Loss: 146.321
+54400/69092	Loss: 148.260
+57600/69092	Loss: 147.512
+60800/69092	Loss: 149.371
+64000/69092	Loss: 146.708
+67200/69092	Loss: 149.506
+Training time 0:08:04.414892
+Epoch: 80 Average loss: 147.73
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 498)
+0/69092	Loss: 154.737
+3200/69092	Loss: 147.845
+6400/69092	Loss: 147.557
+9600/69092	Loss: 144.314
+12800/69092	Loss: 148.370
+16000/69092	Loss: 147.748
+19200/69092	Loss: 145.924
+22400/69092	Loss: 149.566
+25600/69092	Loss: 146.930
+28800/69092	Loss: 147.473
+32000/69092	Loss: 147.248
+35200/69092	Loss: 148.774
+38400/69092	Loss: 148.108
+41600/69092	Loss: 145.911
+44800/69092	Loss: 147.717
+48000/69092	Loss: 147.603
+51200/69092	Loss: 150.033
+54400/69092	Loss: 148.107
+57600/69092	Loss: 147.870
+60800/69092	Loss: 149.684
+64000/69092	Loss: 147.125
+67200/69092	Loss: 146.929
+Training time 0:08:07.579532
+Epoch: 81 Average loss: 147.68
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 499)
+0/69092	Loss: 135.185
+3200/69092	Loss: 146.080
+6400/69092	Loss: 150.029
+9600/69092	Loss: 148.247
+12800/69092	Loss: 148.878
+16000/69092	Loss: 146.841
+19200/69092	Loss: 148.527
+22400/69092	Loss: 147.904
+25600/69092	Loss: 145.949
+28800/69092	Loss: 147.557
+32000/69092	Loss: 147.416
+35200/69092	Loss: 147.015
+38400/69092	Loss: 147.752
+41600/69092	Loss: 147.364
+44800/69092	Loss: 145.552
+48000/69092	Loss: 148.077
+51200/69092	Loss: 146.565
+54400/69092	Loss: 147.934
+57600/69092	Loss: 148.519
+60800/69092	Loss: 149.135
+64000/69092	Loss: 147.331
+67200/69092	Loss: 147.317
+Training time 0:08:12.978166
+Epoch: 82 Average loss: 147.61
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 500)
+0/69092	Loss: 136.819
+3200/69092	Loss: 145.044
+6400/69092	Loss: 147.238
+9600/69092	Loss: 146.320
+12800/69092	Loss: 147.935
+16000/69092	Loss: 146.883
+19200/69092	Loss: 146.125
+22400/69092	Loss: 147.902
+25600/69092	Loss: 145.536
+28800/69092	Loss: 149.641
+32000/69092	Loss: 143.462
+35200/69092	Loss: 147.313
+38400/69092	Loss: 148.904
+41600/69092	Loss: 147.050
+44800/69092	Loss: 149.485
+48000/69092	Loss: 147.878
+51200/69092	Loss: 148.114
+54400/69092	Loss: 149.537
+57600/69092	Loss: 147.324
+60800/69092	Loss: 148.123
+64000/69092	Loss: 148.448
+67200/69092	Loss: 148.748
+Training time 0:07:54.036569
+Epoch: 83 Average loss: 147.47
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 501)
+0/69092	Loss: 135.650
+3200/69092	Loss: 146.067
+6400/69092	Loss: 147.043
+9600/69092	Loss: 147.076
+12800/69092	Loss: 146.580
+16000/69092	Loss: 148.806
+19200/69092	Loss: 144.973
+22400/69092	Loss: 150.626
+25600/69092	Loss: 149.575
+28800/69092	Loss: 146.888
+32000/69092	Loss: 148.025
+35200/69092	Loss: 148.847
+38400/69092	Loss: 148.982
+41600/69092	Loss: 146.736
+44800/69092	Loss: 148.138
+48000/69092	Loss: 147.213
+51200/69092	Loss: 147.875
+54400/69092	Loss: 146.184
+57600/69092	Loss: 146.093
+60800/69092	Loss: 149.322
+64000/69092	Loss: 148.082
+67200/69092	Loss: 148.149
+Training time 0:08:23.560828
+Epoch: 84 Average loss: 147.75
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 502)
+0/69092	Loss: 155.349
+3200/69092	Loss: 147.661
+6400/69092	Loss: 145.798
+9600/69092	Loss: 148.066
+12800/69092	Loss: 146.832
+16000/69092	Loss: 146.631
+19200/69092	Loss: 147.877
+22400/69092	Loss: 148.664
+25600/69092	Loss: 146.001
+28800/69092	Loss: 147.571
+32000/69092	Loss: 148.930
+35200/69092	Loss: 146.671
+38400/69092	Loss: 146.147
+41600/69092	Loss: 147.096
+44800/69092	Loss: 152.366
+48000/69092	Loss: 147.906
+51200/69092	Loss: 146.929
+54400/69092	Loss: 146.356
+57600/69092	Loss: 148.891
+60800/69092	Loss: 146.702
+64000/69092	Loss: 147.325
+67200/69092	Loss: 146.521
+Training time 0:08:17.577059
+Epoch: 85 Average loss: 147.49
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 503)
+0/69092	Loss: 163.972
+3200/69092	Loss: 146.746
+6400/69092	Loss: 148.067
+9600/69092	Loss: 147.307
+12800/69092	Loss: 147.552
+16000/69092	Loss: 147.474
+19200/69092	Loss: 148.758
+22400/69092	Loss: 147.979
+25600/69092	Loss: 147.099
+28800/69092	Loss: 147.179
+32000/69092	Loss: 147.097
+35200/69092	Loss: 149.327
+38400/69092	Loss: 146.647
+41600/69092	Loss: 147.902
+44800/69092	Loss: 146.341
+48000/69092	Loss: 148.940
+51200/69092	Loss: 147.932
+54400/69092	Loss: 147.762
+57600/69092	Loss: 147.697
+60800/69092	Loss: 148.365
+64000/69092	Loss: 148.080
+67200/69092	Loss: 147.055
+Training time 0:07:58.455668
+Epoch: 86 Average loss: 147.73
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 504)
+0/69092	Loss: 147.318
+3200/69092	Loss: 150.924
+6400/69092	Loss: 147.242
+9600/69092	Loss: 147.379
+12800/69092	Loss: 148.316
+16000/69092	Loss: 146.900
+19200/69092	Loss: 146.470
+22400/69092	Loss: 146.816
+25600/69092	Loss: 146.232
+28800/69092	Loss: 148.870
+32000/69092	Loss: 148.522
+35200/69092	Loss: 146.695
+38400/69092	Loss: 148.517
+41600/69092	Loss: 147.169
+44800/69092	Loss: 149.679
+48000/69092	Loss: 149.307
+51200/69092	Loss: 146.480
+54400/69092	Loss: 147.332
+57600/69092	Loss: 146.588
+60800/69092	Loss: 149.258
+64000/69092	Loss: 148.278
+67200/69092	Loss: 147.715
+Training time 0:08:10.216719
+Epoch: 87 Average loss: 147.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 505)
+0/69092	Loss: 140.944
+3200/69092	Loss: 147.757
+6400/69092	Loss: 147.884
+9600/69092	Loss: 144.680
+12800/69092	Loss: 146.142
+16000/69092	Loss: 148.803
+19200/69092	Loss: 145.198
+22400/69092	Loss: 149.061
+25600/69092	Loss: 148.217
+28800/69092	Loss: 149.004
+32000/69092	Loss: 148.815
+35200/69092	Loss: 148.192
+38400/69092	Loss: 149.235
+41600/69092	Loss: 146.242
+44800/69092	Loss: 145.157
+48000/69092	Loss: 148.070
+51200/69092	Loss: 150.627
+54400/69092	Loss: 146.369
+57600/69092	Loss: 146.079
+60800/69092	Loss: 147.702
+64000/69092	Loss: 144.910
+67200/69092	Loss: 149.907
+Training time 0:08:12.385406
+Epoch: 88 Average loss: 147.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 506)
+0/69092	Loss: 152.500
+3200/69092	Loss: 148.537
+6400/69092	Loss: 148.159
+9600/69092	Loss: 145.010
+12800/69092	Loss: 148.960
+16000/69092	Loss: 147.353
+19200/69092	Loss: 146.021
+22400/69092	Loss: 148.964
+25600/69092	Loss: 149.490
+28800/69092	Loss: 146.247
+32000/69092	Loss: 148.036
+35200/69092	Loss: 149.508
+38400/69092	Loss: 147.327
+41600/69092	Loss: 147.604
+44800/69092	Loss: 144.935
+48000/69092	Loss: 148.282
+51200/69092	Loss: 145.934
+54400/69092	Loss: 146.569
+57600/69092	Loss: 147.644
+60800/69092	Loss: 147.019
+64000/69092	Loss: 148.032
+67200/69092	Loss: 147.709
+Training time 0:07:55.828928
+Epoch: 89 Average loss: 147.61
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 507)
+0/69092	Loss: 140.336
+3200/69092	Loss: 148.462
+6400/69092	Loss: 149.642
+9600/69092	Loss: 148.141
+12800/69092	Loss: 147.736
+16000/69092	Loss: 148.605
+19200/69092	Loss: 149.172
+22400/69092	Loss: 146.730
+25600/69092	Loss: 146.967
+28800/69092	Loss: 148.742
+32000/69092	Loss: 145.618
+35200/69092	Loss: 148.630
+38400/69092	Loss: 146.286
+41600/69092	Loss: 146.504
+44800/69092	Loss: 147.819
+48000/69092	Loss: 148.904
+51200/69092	Loss: 148.692
+54400/69092	Loss: 147.058
+57600/69092	Loss: 147.391
+60800/69092	Loss: 146.200
+64000/69092	Loss: 147.115
+67200/69092	Loss: 147.220
+Training time 0:08:12.233386
+Epoch: 90 Average loss: 147.76
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 508)
+0/69092	Loss: 163.084
+3200/69092	Loss: 147.225
+6400/69092	Loss: 149.745
+9600/69092	Loss: 148.163
+12800/69092	Loss: 145.341
+16000/69092	Loss: 147.504
+19200/69092	Loss: 147.433
+22400/69092	Loss: 148.004
+25600/69092	Loss: 146.638
+28800/69092	Loss: 148.799
+32000/69092	Loss: 146.636
+35200/69092	Loss: 145.366
+38400/69092	Loss: 148.274
+41600/69092	Loss: 146.978
+44800/69092	Loss: 148.799
+48000/69092	Loss: 147.228
+51200/69092	Loss: 148.699
+54400/69092	Loss: 148.522
+57600/69092	Loss: 147.266
+60800/69092	Loss: 146.425
+64000/69092	Loss: 146.838
+67200/69092	Loss: 148.239
+Training time 0:08:05.861440
+Epoch: 91 Average loss: 147.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 509)
+0/69092	Loss: 161.314
+3200/69092	Loss: 147.510
+6400/69092	Loss: 147.959
+9600/69092	Loss: 146.308
+12800/69092	Loss: 147.346
+16000/69092	Loss: 149.496
+19200/69092	Loss: 145.616
+22400/69092	Loss: 148.794
+25600/69092	Loss: 146.330
+28800/69092	Loss: 148.777
+32000/69092	Loss: 145.517
+35200/69092	Loss: 146.641
+38400/69092	Loss: 147.547
+41600/69092	Loss: 149.627
+44800/69092	Loss: 147.428
+48000/69092	Loss: 147.202
+51200/69092	Loss: 148.737
+54400/69092	Loss: 147.726
+57600/69092	Loss: 146.789
+60800/69092	Loss: 149.622
+64000/69092	Loss: 146.021
+67200/69092	Loss: 148.590
+Training time 0:07:57.001161
+Epoch: 92 Average loss: 147.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 510)
+0/69092	Loss: 134.804
+3200/69092	Loss: 147.918
+6400/69092	Loss: 147.887
+9600/69092	Loss: 147.149
+12800/69092	Loss: 148.444
+16000/69092	Loss: 148.305
+19200/69092	Loss: 147.981
+22400/69092	Loss: 148.457
+25600/69092	Loss: 147.454
+28800/69092	Loss: 147.559
+32000/69092	Loss: 147.965
+35200/69092	Loss: 146.426
+38400/69092	Loss: 149.440
+41600/69092	Loss: 149.855
+44800/69092	Loss: 145.485
+48000/69092	Loss: 147.974
+51200/69092	Loss: 148.486
+54400/69092	Loss: 147.198
+57600/69092	Loss: 146.138
+60800/69092	Loss: 146.566
+64000/69092	Loss: 148.464
+67200/69092	Loss: 146.112
+Training time 0:08:11.052943
+Epoch: 93 Average loss: 147.62
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 511)
+0/69092	Loss: 162.450
+3200/69092	Loss: 146.729
+6400/69092	Loss: 146.884
+9600/69092	Loss: 146.767
+12800/69092	Loss: 146.424
+16000/69092	Loss: 145.226
+19200/69092	Loss: 147.174
+22400/69092	Loss: 148.910
+25600/69092	Loss: 147.281
+28800/69092	Loss: 148.277
+32000/69092	Loss: 150.619
+35200/69092	Loss: 148.943
+38400/69092	Loss: 146.155
+41600/69092	Loss: 149.078
+44800/69092	Loss: 146.909
+48000/69092	Loss: 149.739
+51200/69092	Loss: 148.480
+54400/69092	Loss: 148.257
+57600/69092	Loss: 146.433
+60800/69092	Loss: 146.926
+64000/69092	Loss: 146.405
+67200/69092	Loss: 147.375
+Training time 0:08:14.260243
+Epoch: 94 Average loss: 147.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 512)
+0/69092	Loss: 148.071
+3200/69092	Loss: 148.283
+6400/69092	Loss: 148.561
+9600/69092	Loss: 149.444
+12800/69092	Loss: 146.401
+16000/69092	Loss: 146.077
+19200/69092	Loss: 148.641
+22400/69092	Loss: 149.240
+25600/69092	Loss: 146.069
+28800/69092	Loss: 147.599
+32000/69092	Loss: 147.274
+35200/69092	Loss: 146.148
+38400/69092	Loss: 146.235
+41600/69092	Loss: 148.912
+44800/69092	Loss: 147.283
+48000/69092	Loss: 147.811
+51200/69092	Loss: 145.115
+54400/69092	Loss: 148.596
+57600/69092	Loss: 148.462
+60800/69092	Loss: 150.560
+64000/69092	Loss: 145.737
+67200/69092	Loss: 148.026
+Training time 0:08:00.072262
+Epoch: 95 Average loss: 147.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 513)
+0/69092	Loss: 142.155
+3200/69092	Loss: 146.731
+6400/69092	Loss: 147.541
+9600/69092	Loss: 146.518
+12800/69092	Loss: 148.861
+16000/69092	Loss: 147.425
+19200/69092	Loss: 148.138
+22400/69092	Loss: 148.554
+25600/69092	Loss: 148.874
+28800/69092	Loss: 147.928
+32000/69092	Loss: 147.873
+35200/69092	Loss: 147.112
+38400/69092	Loss: 148.005
+41600/69092	Loss: 146.327
+44800/69092	Loss: 146.952
+48000/69092	Loss: 146.966
+51200/69092	Loss: 148.605
+54400/69092	Loss: 150.269
+57600/69092	Loss: 146.599
+60800/69092	Loss: 146.306
+64000/69092	Loss: 145.989
+67200/69092	Loss: 146.062
+Training time 0:08:15.707317
+Epoch: 96 Average loss: 147.56
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 514)
+0/69092	Loss: 152.896
+3200/69092	Loss: 145.565
+6400/69092	Loss: 147.373
+9600/69092	Loss: 144.888
+12800/69092	Loss: 146.331
+16000/69092	Loss: 146.029
+19200/69092	Loss: 148.672
+22400/69092	Loss: 147.382
+25600/69092	Loss: 146.595
+28800/69092	Loss: 149.114
+32000/69092	Loss: 148.268
+35200/69092	Loss: 144.069
+38400/69092	Loss: 147.740
+41600/69092	Loss: 146.003
+44800/69092	Loss: 146.959
+48000/69092	Loss: 148.516
+51200/69092	Loss: 149.198
+54400/69092	Loss: 146.288
+57600/69092	Loss: 147.963
+60800/69092	Loss: 148.418
+64000/69092	Loss: 151.847
+67200/69092	Loss: 147.474
+Training time 0:08:18.100296
+Epoch: 97 Average loss: 147.42
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 515)
+0/69092	Loss: 146.202
+3200/69092	Loss: 145.613
+6400/69092	Loss: 146.668
+9600/69092	Loss: 146.731
+12800/69092	Loss: 145.234
+16000/69092	Loss: 146.444
+19200/69092	Loss: 149.336
+22400/69092	Loss: 147.294
+25600/69092	Loss: 148.730
+28800/69092	Loss: 148.962
+32000/69092	Loss: 147.806
+35200/69092	Loss: 149.632
+38400/69092	Loss: 148.029
+41600/69092	Loss: 145.635
+44800/69092	Loss: 148.433
+48000/69092	Loss: 148.164
+51200/69092	Loss: 147.554
+54400/69092	Loss: 147.824
+57600/69092	Loss: 147.327
+60800/69092	Loss: 147.750
+64000/69092	Loss: 146.468
+67200/69092	Loss: 148.670
+Training time 0:07:55.536206
+Epoch: 98 Average loss: 147.56
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 516)
+0/69092	Loss: 129.299
+3200/69092	Loss: 147.476
+6400/69092	Loss: 147.209
+9600/69092	Loss: 146.903
+12800/69092	Loss: 149.666
+16000/69092	Loss: 147.846
+19200/69092	Loss: 148.262
+22400/69092	Loss: 148.026
+25600/69092	Loss: 146.662
+28800/69092	Loss: 145.144
+32000/69092	Loss: 146.433
+35200/69092	Loss: 146.580
+38400/69092	Loss: 146.032
+41600/69092	Loss: 146.448
+44800/69092	Loss: 146.491
+48000/69092	Loss: 148.486
+51200/69092	Loss: 148.369
+54400/69092	Loss: 148.601
+57600/69092	Loss: 147.551
+60800/69092	Loss: 149.184
+64000/69092	Loss: 147.858
+67200/69092	Loss: 148.645
+Training time 0:08:15.924963
+Epoch: 99 Average loss: 147.54
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 517)
+0/69092	Loss: 140.958
+3200/69092	Loss: 147.424
+6400/69092	Loss: 148.779
+9600/69092	Loss: 147.866
+12800/69092	Loss: 149.118
+16000/69092	Loss: 147.473
+19200/69092	Loss: 149.822
+22400/69092	Loss: 147.037
+25600/69092	Loss: 146.054
+28800/69092	Loss: 148.704
+32000/69092	Loss: 146.316
+35200/69092	Loss: 146.097
+38400/69092	Loss: 148.950
+41600/69092	Loss: 147.435
+44800/69092	Loss: 149.595
+48000/69092	Loss: 145.107
+51200/69092	Loss: 148.559
+54400/69092	Loss: 147.290
+57600/69092	Loss: 148.233
+60800/69092	Loss: 147.083
+64000/69092	Loss: 145.557
+67200/69092	Loss: 148.468
+Training time 0:08:14.569202
+Epoch: 100 Average loss: 147.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 518)
+0/69092	Loss: 145.551
+3200/69092	Loss: 149.179
+6400/69092	Loss: 145.650
+9600/69092	Loss: 145.334
+12800/69092	Loss: 146.776
+16000/69092	Loss: 145.474
+19200/69092	Loss: 146.642
+22400/69092	Loss: 147.965
+25600/69092	Loss: 147.585
+28800/69092	Loss: 147.092
+32000/69092	Loss: 148.408
+35200/69092	Loss: 148.777
+38400/69092	Loss: 146.952
+41600/69092	Loss: 147.564
+44800/69092	Loss: 147.728
+48000/69092	Loss: 146.030
+51200/69092	Loss: 149.226
+54400/69092	Loss: 148.627
+57600/69092	Loss: 148.533
+60800/69092	Loss: 147.407
+64000/69092	Loss: 150.093
+67200/69092	Loss: 147.888
+Training time 0:07:56.109121
+Epoch: 101 Average loss: 147.52
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 519)
+0/69092	Loss: 160.292
+3200/69092	Loss: 149.533
+6400/69092	Loss: 146.530
+9600/69092	Loss: 149.473
+12800/69092	Loss: 145.931
+16000/69092	Loss: 146.320
+19200/69092	Loss: 146.926
+22400/69092	Loss: 145.928
+25600/69092	Loss: 147.875
+28800/69092	Loss: 148.001
+32000/69092	Loss: 145.241
+35200/69092	Loss: 146.594
+38400/69092	Loss: 148.955
+41600/69092	Loss: 152.342
+44800/69092	Loss: 148.385
+48000/69092	Loss: 146.921
+51200/69092	Loss: 145.987
+54400/69092	Loss: 146.966
+57600/69092	Loss: 145.693
+60800/69092	Loss: 149.795
+64000/69092	Loss: 148.175
+67200/69092	Loss: 147.622
+Training time 0:08:05.008511
+Epoch: 102 Average loss: 147.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 520)
+0/69092	Loss: 148.057
+3200/69092	Loss: 146.475
+6400/69092	Loss: 148.238
+9600/69092	Loss: 147.985
+12800/69092	Loss: 148.074
+16000/69092	Loss: 148.332
+19200/69092	Loss: 147.114
+22400/69092	Loss: 146.694
+25600/69092	Loss: 148.469
+28800/69092	Loss: 147.798
+32000/69092	Loss: 147.778
+35200/69092	Loss: 147.148
+38400/69092	Loss: 149.829
+41600/69092	Loss: 145.903
+44800/69092	Loss: 144.400
+48000/69092	Loss: 147.282
+51200/69092	Loss: 151.700
+54400/69092	Loss: 146.351
+57600/69092	Loss: 148.215
+60800/69092	Loss: 149.661
+64000/69092	Loss: 145.294
+67200/69092	Loss: 147.886
+Training time 0:08:10.060694
+Epoch: 103 Average loss: 147.63
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 521)
+0/69092	Loss: 136.738
+3200/69092	Loss: 148.736
+6400/69092	Loss: 145.925
+9600/69092	Loss: 148.449
+12800/69092	Loss: 148.286
+16000/69092	Loss: 150.222
+19200/69092	Loss: 146.531
+22400/69092	Loss: 146.262
+25600/69092	Loss: 146.841
+28800/69092	Loss: 148.632
+32000/69092	Loss: 147.031
+35200/69092	Loss: 147.599
+38400/69092	Loss: 147.164
+41600/69092	Loss: 147.928
+44800/69092	Loss: 145.883
+48000/69092	Loss: 148.497
+51200/69092	Loss: 150.466
+54400/69092	Loss: 146.723
+57600/69092	Loss: 147.582
+60800/69092	Loss: 145.117
+64000/69092	Loss: 144.893
+67200/69092	Loss: 149.262
+Training time 0:08:05.079702
+Epoch: 104 Average loss: 147.58
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 522)
+0/69092	Loss: 149.773
+3200/69092	Loss: 144.630
+6400/69092	Loss: 146.729
+9600/69092	Loss: 149.109
+12800/69092	Loss: 147.683
+16000/69092	Loss: 146.872
+19200/69092	Loss: 147.522
+22400/69092	Loss: 145.183
+25600/69092	Loss: 148.903
+28800/69092	Loss: 147.712
+32000/69092	Loss: 148.348
+35200/69092	Loss: 148.851
+38400/69092	Loss: 147.985
+41600/69092	Loss: 150.745
+44800/69092	Loss: 147.507
+48000/69092	Loss: 146.582
+51200/69092	Loss: 148.033
+54400/69092	Loss: 146.095
+57600/69092	Loss: 145.749
+60800/69092	Loss: 146.536
+64000/69092	Loss: 146.788
+67200/69092	Loss: 148.825
+Training time 0:08:06.408761
+Epoch: 105 Average loss: 147.39
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 523)
+0/69092	Loss: 145.118
+3200/69092	Loss: 148.173
+6400/69092	Loss: 148.325
+9600/69092	Loss: 147.924
+12800/69092	Loss: 149.131
+16000/69092	Loss: 147.525
+19200/69092	Loss: 146.508
+22400/69092	Loss: 146.059
+25600/69092	Loss: 144.840
+28800/69092	Loss: 146.562
+32000/69092	Loss: 146.584
+35200/69092	Loss: 146.812
+38400/69092	Loss: 145.653
+41600/69092	Loss: 146.580
+44800/69092	Loss: 150.697
+48000/69092	Loss: 147.812
+51200/69092	Loss: 147.550
+54400/69092	Loss: 145.244
+57600/69092	Loss: 146.819
+60800/69092	Loss: 146.409
+64000/69092	Loss: 148.653
+67200/69092	Loss: 149.149
+Training time 0:08:10.038232
+Epoch: 106 Average loss: 147.36
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 524)
+0/69092	Loss: 151.083
+3200/69092	Loss: 148.231
+6400/69092	Loss: 149.923
+9600/69092	Loss: 145.992
+12800/69092	Loss: 147.813
+16000/69092	Loss: 147.781
+19200/69092	Loss: 148.138
+22400/69092	Loss: 148.577
+25600/69092	Loss: 147.331
+28800/69092	Loss: 147.888
+32000/69092	Loss: 148.076
+35200/69092	Loss: 147.255
+38400/69092	Loss: 146.204
+41600/69092	Loss: 148.343
+44800/69092	Loss: 148.550
+48000/69092	Loss: 146.231
+51200/69092	Loss: 146.592
+54400/69092	Loss: 149.095
+57600/69092	Loss: 146.762
+60800/69092	Loss: 148.242
+64000/69092	Loss: 145.483
+67200/69092	Loss: 148.491
+Training time 0:08:01.060046
+Epoch: 107 Average loss: 147.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 525)
+0/69092	Loss: 159.302
+3200/69092	Loss: 146.271
+6400/69092	Loss: 148.401
+9600/69092	Loss: 148.905
+12800/69092	Loss: 145.988
+16000/69092	Loss: 146.825
+19200/69092	Loss: 148.741
+22400/69092	Loss: 145.509
+25600/69092	Loss: 147.826
+28800/69092	Loss: 144.333
+32000/69092	Loss: 150.294
+35200/69092	Loss: 146.781
+38400/69092	Loss: 147.857
+41600/69092	Loss: 148.922
+44800/69092	Loss: 149.093
+48000/69092	Loss: 146.189
+51200/69092	Loss: 146.758
+54400/69092	Loss: 150.542
+57600/69092	Loss: 146.531
+60800/69092	Loss: 146.979
+64000/69092	Loss: 147.766
+67200/69092	Loss: 147.279
+Training time 0:08:21.107097
+Epoch: 108 Average loss: 147.59
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 526)
+0/69092	Loss: 166.670
+3200/69092	Loss: 150.091
+6400/69092	Loss: 146.647
+9600/69092	Loss: 148.459
+12800/69092	Loss: 148.485
+16000/69092	Loss: 145.739
+19200/69092	Loss: 150.105
+22400/69092	Loss: 149.956
+25600/69092	Loss: 147.548
+28800/69092	Loss: 146.998
+32000/69092	Loss: 149.395
+35200/69092	Loss: 146.746
+38400/69092	Loss: 148.088
+41600/69092	Loss: 147.727
+44800/69092	Loss: 149.681
+48000/69092	Loss: 145.742
+51200/69092	Loss: 146.390
+54400/69092	Loss: 147.955
+57600/69092	Loss: 147.966
+60800/69092	Loss: 147.038
+64000/69092	Loss: 147.214
+67200/69092	Loss: 147.317
+Training time 0:08:12.813550
+Epoch: 109 Average loss: 147.92
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 527)
+0/69092	Loss: 142.467
+3200/69092	Loss: 145.671
+6400/69092	Loss: 145.747
+9600/69092	Loss: 147.597
+12800/69092	Loss: 145.084
+16000/69092	Loss: 149.997
+19200/69092	Loss: 145.442
+22400/69092	Loss: 149.166
+25600/69092	Loss: 148.598
+28800/69092	Loss: 146.938
+32000/69092	Loss: 147.460
+35200/69092	Loss: 147.701
+38400/69092	Loss: 148.551
+41600/69092	Loss: 147.959
+44800/69092	Loss: 147.409
+48000/69092	Loss: 148.133
+51200/69092	Loss: 148.010
+54400/69092	Loss: 149.896
+57600/69092	Loss: 146.633
+60800/69092	Loss: 145.686
+64000/69092	Loss: 150.277
+67200/69092	Loss: 146.427
+Training time 0:08:01.131396
+Epoch: 110 Average loss: 147.54
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 528)
+0/69092	Loss: 149.691
+3200/69092	Loss: 146.897
+6400/69092	Loss: 148.604
+9600/69092	Loss: 146.684
+12800/69092	Loss: 148.613
+16000/69092	Loss: 147.791
+19200/69092	Loss: 147.025
+22400/69092	Loss: 147.596
+25600/69092	Loss: 147.919
+28800/69092	Loss: 149.502
+32000/69092	Loss: 146.143
+35200/69092	Loss: 147.450
+38400/69092	Loss: 146.729
+41600/69092	Loss: 148.392
+44800/69092	Loss: 145.983
+48000/69092	Loss: 149.527
+51200/69092	Loss: 147.957
+54400/69092	Loss: 146.620
+57600/69092	Loss: 147.728
+60800/69092	Loss: 148.002
+64000/69092	Loss: 145.630
+67200/69092	Loss: 147.906
+Training time 0:08:07.185914
+Epoch: 111 Average loss: 147.58
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 529)
+0/69092	Loss: 160.350
+3200/69092	Loss: 147.683
+6400/69092	Loss: 147.527
+9600/69092	Loss: 149.726
+12800/69092	Loss: 150.507
+16000/69092	Loss: 145.917
+19200/69092	Loss: 147.107
+22400/69092	Loss: 148.405
+25600/69092	Loss: 149.008
+28800/69092	Loss: 146.652
+32000/69092	Loss: 148.998
+35200/69092	Loss: 147.370
+38400/69092	Loss: 146.146
+41600/69092	Loss: 145.483
+44800/69092	Loss: 146.394
+48000/69092	Loss: 147.461
+51200/69092	Loss: 147.053
+54400/69092	Loss: 149.007
+57600/69092	Loss: 149.327
+60800/69092	Loss: 146.428
+64000/69092	Loss: 148.075
+67200/69092	Loss: 147.085
+Training time 0:08:15.738968
+Epoch: 112 Average loss: 147.73
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 530)
+0/69092	Loss: 152.454
+3200/69092	Loss: 147.156
+6400/69092	Loss: 146.305
+9600/69092	Loss: 145.165
+12800/69092	Loss: 146.405
+16000/69092	Loss: 147.580
+19200/69092	Loss: 147.711
+22400/69092	Loss: 147.206
+25600/69092	Loss: 145.634
+28800/69092	Loss: 145.832
+32000/69092	Loss: 149.233
+35200/69092	Loss: 148.879
+38400/69092	Loss: 147.525
+41600/69092	Loss: 148.223
+44800/69092	Loss: 149.008
+48000/69092	Loss: 149.579
+51200/69092	Loss: 148.423
+54400/69092	Loss: 147.668
+57600/69092	Loss: 146.085
+60800/69092	Loss: 146.043
+64000/69092	Loss: 147.029
+67200/69092	Loss: 149.432
+Training time 0:08:01.205496
+Epoch: 113 Average loss: 147.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 531)
+0/69092	Loss: 161.051
+3200/69092	Loss: 150.524
+6400/69092	Loss: 148.156
+9600/69092	Loss: 145.730
+12800/69092	Loss: 148.912
+16000/69092	Loss: 146.919
+19200/69092	Loss: 148.927
+22400/69092	Loss: 146.552
+25600/69092	Loss: 150.537
+28800/69092	Loss: 147.477
+32000/69092	Loss: 145.482
+35200/69092	Loss: 149.337
+38400/69092	Loss: 148.177
+41600/69092	Loss: 147.276
+44800/69092	Loss: 146.537
+48000/69092	Loss: 145.323
+51200/69092	Loss: 145.134
+54400/69092	Loss: 147.545
+57600/69092	Loss: 144.988
+60800/69092	Loss: 147.304
+64000/69092	Loss: 146.970
+67200/69092	Loss: 146.491
+Training time 0:08:10.818199
+Epoch: 114 Average loss: 147.43
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 532)
+0/69092	Loss: 139.090
+3200/69092	Loss: 146.309
+6400/69092	Loss: 147.047
+9600/69092	Loss: 147.101
+12800/69092	Loss: 145.913
+16000/69092	Loss: 147.181
+19200/69092	Loss: 145.638
+22400/69092	Loss: 148.865
+25600/69092	Loss: 147.394
+28800/69092	Loss: 147.110
+32000/69092	Loss: 148.380
+35200/69092	Loss: 147.768
+38400/69092	Loss: 146.963
+41600/69092	Loss: 146.760
+44800/69092	Loss: 146.915
+48000/69092	Loss: 149.674
+51200/69092	Loss: 143.686
+54400/69092	Loss: 148.340
+57600/69092	Loss: 148.897
+60800/69092	Loss: 150.137
+64000/69092	Loss: 147.660
+67200/69092	Loss: 148.278
+Training time 0:08:17.305804
+Epoch: 115 Average loss: 147.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 533)
+0/69092	Loss: 168.487
+3200/69092	Loss: 148.369
+6400/69092	Loss: 148.275
+9600/69092	Loss: 150.465
+12800/69092	Loss: 146.279
+16000/69092	Loss: 150.053
+19200/69092	Loss: 147.836
+22400/69092	Loss: 148.895
+25600/69092	Loss: 146.658
+28800/69092	Loss: 144.695
+32000/69092	Loss: 147.762
+35200/69092	Loss: 146.311
+38400/69092	Loss: 146.574
+41600/69092	Loss: 145.270
+44800/69092	Loss: 148.973
+48000/69092	Loss: 145.952
+51200/69092	Loss: 146.232
+54400/69092	Loss: 149.366
+57600/69092	Loss: 147.644
+60800/69092	Loss: 147.552
+64000/69092	Loss: 145.241
+67200/69092	Loss: 148.423
+Training time 0:07:55.130128
+Epoch: 116 Average loss: 147.46
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 534)
+0/69092	Loss: 158.945
+3200/69092	Loss: 146.989
+6400/69092	Loss: 146.338
+9600/69092	Loss: 147.853
+12800/69092	Loss: 150.202
+16000/69092	Loss: 147.990
+19200/69092	Loss: 146.240
+22400/69092	Loss: 148.249
+25600/69092	Loss: 148.402
+28800/69092	Loss: 149.935
+32000/69092	Loss: 148.400
+35200/69092	Loss: 144.883
+38400/69092	Loss: 149.779
+41600/69092	Loss: 145.199
+44800/69092	Loss: 148.300
+48000/69092	Loss: 146.905
+51200/69092	Loss: 147.159
+54400/69092	Loss: 146.000
+57600/69092	Loss: 148.086
+60800/69092	Loss: 146.103
+64000/69092	Loss: 148.067
+67200/69092	Loss: 144.166
+Training time 0:08:03.987456
+Epoch: 117 Average loss: 147.46
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 535)
+0/69092	Loss: 141.966
+3200/69092	Loss: 148.568
+6400/69092	Loss: 149.284
+9600/69092	Loss: 148.073
+12800/69092	Loss: 146.455
+16000/69092	Loss: 149.468
+19200/69092	Loss: 147.936
+22400/69092	Loss: 147.576
+25600/69092	Loss: 146.253
+28800/69092	Loss: 145.205
+32000/69092	Loss: 145.820
+35200/69092	Loss: 148.744
+38400/69092	Loss: 145.711
+41600/69092	Loss: 149.104
+44800/69092	Loss: 146.777
+48000/69092	Loss: 146.779
+51200/69092	Loss: 147.031
+54400/69092	Loss: 148.005
+57600/69092	Loss: 147.228
+60800/69092	Loss: 150.324
+64000/69092	Loss: 145.341
+67200/69092	Loss: 146.204
+Training time 0:08:09.574476
+Epoch: 118 Average loss: 147.36
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 536)
+0/69092	Loss: 144.354
+3200/69092	Loss: 146.886
+6400/69092	Loss: 152.442
+9600/69092	Loss: 149.404
+12800/69092	Loss: 145.389
+16000/69092	Loss: 146.080
+19200/69092	Loss: 148.041
+22400/69092	Loss: 148.131
+25600/69092	Loss: 147.823
+28800/69092	Loss: 148.095
+32000/69092	Loss: 147.581
+35200/69092	Loss: 147.602
+38400/69092	Loss: 146.330
+41600/69092	Loss: 148.689
+44800/69092	Loss: 147.656
+48000/69092	Loss: 146.543
+51200/69092	Loss: 146.352
+54400/69092	Loss: 147.308
+57600/69092	Loss: 143.988
+60800/69092	Loss: 145.653
+64000/69092	Loss: 148.626
+67200/69092	Loss: 147.035
+Training time 0:07:57.078689
+Epoch: 119 Average loss: 147.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 537)
+0/69092	Loss: 151.588
+3200/69092	Loss: 146.803
+6400/69092	Loss: 149.077
+9600/69092	Loss: 147.033
+12800/69092	Loss: 148.103
+16000/69092	Loss: 146.288
+19200/69092	Loss: 149.896
+22400/69092	Loss: 146.481
+25600/69092	Loss: 148.949
+28800/69092	Loss: 148.946
+32000/69092	Loss: 149.971
+35200/69092	Loss: 148.363
+38400/69092	Loss: 147.742
+41600/69092	Loss: 150.030
+44800/69092	Loss: 146.451
+48000/69092	Loss: 149.914
+51200/69092	Loss: 146.593
+54400/69092	Loss: 143.870
+57600/69092	Loss: 146.620
+60800/69092	Loss: 148.666
+64000/69092	Loss: 147.897
+67200/69092	Loss: 145.023
+Training time 0:08:15.246061
+Epoch: 120 Average loss: 147.79
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 538)
+0/69092	Loss: 152.920
+3200/69092	Loss: 144.815
+6400/69092	Loss: 147.639
+9600/69092	Loss: 146.946
+12800/69092	Loss: 149.872
+16000/69092	Loss: 146.020
+19200/69092	Loss: 147.146
+22400/69092	Loss: 146.844
+25600/69092	Loss: 148.834
+28800/69092	Loss: 147.639
+32000/69092	Loss: 145.993
+35200/69092	Loss: 146.130
+38400/69092	Loss: 147.786
+41600/69092	Loss: 147.516
+44800/69092	Loss: 147.006
+48000/69092	Loss: 148.924
+51200/69092	Loss: 147.979
+54400/69092	Loss: 147.544
+57600/69092	Loss: 148.029
+60800/69092	Loss: 147.669
+64000/69092	Loss: 147.253
+67200/69092	Loss: 148.900
+Training time 0:08:09.342244
+Epoch: 121 Average loss: 147.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 539)
+0/69092	Loss: 151.948
+3200/69092	Loss: 145.662
+6400/69092	Loss: 149.176
+9600/69092	Loss: 146.233
+12800/69092	Loss: 147.181
+16000/69092	Loss: 147.305
+19200/69092	Loss: 148.629
+22400/69092	Loss: 147.639
+25600/69092	Loss: 148.447
+28800/69092	Loss: 146.908
+32000/69092	Loss: 149.289
+35200/69092	Loss: 147.695
+38400/69092	Loss: 145.855
+41600/69092	Loss: 147.471
+44800/69092	Loss: 147.665
+48000/69092	Loss: 147.344
+51200/69092	Loss: 147.826
+54400/69092	Loss: 146.256
+57600/69092	Loss: 147.767
+60800/69092	Loss: 146.763
+64000/69092	Loss: 147.085
+67200/69092	Loss: 147.189
+Training time 0:07:57.461286
+Epoch: 122 Average loss: 147.40
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 540)
+0/69092	Loss: 151.962
+3200/69092	Loss: 145.114
+6400/69092	Loss: 147.746
+9600/69092	Loss: 146.342
+12800/69092	Loss: 148.232
+16000/69092	Loss: 147.960
+19200/69092	Loss: 149.212
+22400/69092	Loss: 148.888
+25600/69092	Loss: 146.312
+28800/69092	Loss: 147.355
+32000/69092	Loss: 148.328
+35200/69092	Loss: 147.972
+38400/69092	Loss: 146.040
+41600/69092	Loss: 145.291
+44800/69092	Loss: 146.460
+48000/69092	Loss: 146.681
+51200/69092	Loss: 148.134
+54400/69092	Loss: 146.123
+57600/69092	Loss: 147.561
+60800/69092	Loss: 147.775
+64000/69092	Loss: 147.625
+67200/69092	Loss: 145.857
+Training time 0:08:07.404815
+Epoch: 123 Average loss: 147.30
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 541)
+0/69092	Loss: 152.717
+3200/69092	Loss: 145.806
+6400/69092	Loss: 147.693
+9600/69092	Loss: 147.025
+12800/69092	Loss: 149.400
+16000/69092	Loss: 146.482
+19200/69092	Loss: 146.437
+22400/69092	Loss: 147.060
+25600/69092	Loss: 148.020
+28800/69092	Loss: 147.830
+32000/69092	Loss: 147.630
+35200/69092	Loss: 147.215
+38400/69092	Loss: 147.355
+41600/69092	Loss: 148.222
+44800/69092	Loss: 149.177
+48000/69092	Loss: 146.179
+51200/69092	Loss: 149.570
+54400/69092	Loss: 147.375
+57600/69092	Loss: 147.435
+60800/69092	Loss: 149.018
+64000/69092	Loss: 146.493
+67200/69092	Loss: 147.510
+Training time 0:08:04.794687
+Epoch: 124 Average loss: 147.52
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 542)
+0/69092	Loss: 170.132
+3200/69092	Loss: 147.135
+6400/69092	Loss: 146.621
+9600/69092	Loss: 146.015
+12800/69092	Loss: 147.906
+16000/69092	Loss: 149.700
+19200/69092	Loss: 149.005
+22400/69092	Loss: 148.115
+25600/69092	Loss: 146.691
+28800/69092	Loss: 147.986
+32000/69092	Loss: 146.489
+35200/69092	Loss: 149.301
+38400/69092	Loss: 148.275
+41600/69092	Loss: 146.862
+44800/69092	Loss: 144.979
+48000/69092	Loss: 146.003
+51200/69092	Loss: 147.676
+54400/69092	Loss: 146.996
+57600/69092	Loss: 143.947
+60800/69092	Loss: 148.326
+64000/69092	Loss: 147.689
+67200/69092	Loss: 149.267
+Training time 0:07:50.549805
+Epoch: 125 Average loss: 147.39
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 543)
+0/69092	Loss: 165.316
+3200/69092	Loss: 146.985
+6400/69092	Loss: 146.590
+9600/69092	Loss: 147.091
+12800/69092	Loss: 149.088
+16000/69092	Loss: 147.641
+19200/69092	Loss: 147.147
+22400/69092	Loss: 147.452
+25600/69092	Loss: 147.438
+28800/69092	Loss: 147.815
+32000/69092	Loss: 145.122
+35200/69092	Loss: 147.243
+38400/69092	Loss: 146.451
+41600/69092	Loss: 147.378
+44800/69092	Loss: 148.379
+48000/69092	Loss: 146.824
+51200/69092	Loss: 148.175
+54400/69092	Loss: 149.874
+57600/69092	Loss: 147.951
+60800/69092	Loss: 146.629
+64000/69092	Loss: 147.688
+67200/69092	Loss: 147.375
+Training time 0:08:08.270873
+Epoch: 126 Average loss: 147.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 544)
+0/69092	Loss: 148.949
+3200/69092	Loss: 147.543
+6400/69092	Loss: 149.402
+9600/69092	Loss: 149.680
+12800/69092	Loss: 146.733
+16000/69092	Loss: 144.827
+19200/69092	Loss: 144.892
+22400/69092	Loss: 149.029
+25600/69092	Loss: 147.039
+28800/69092	Loss: 149.478
+32000/69092	Loss: 146.511
+35200/69092	Loss: 147.992
+38400/69092	Loss: 147.671
+41600/69092	Loss: 145.764
+44800/69092	Loss: 146.266
+48000/69092	Loss: 149.204
+51200/69092	Loss: 149.231
+54400/69092	Loss: 147.095
+57600/69092	Loss: 146.810
+60800/69092	Loss: 145.939
+64000/69092	Loss: 150.034
+67200/69092	Loss: 146.821
+Training time 0:08:13.346742
+Epoch: 127 Average loss: 147.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 545)
+0/69092	Loss: 138.288
+3200/69092	Loss: 145.850
+6400/69092	Loss: 148.308
+9600/69092	Loss: 147.834
+12800/69092	Loss: 144.476
+16000/69092	Loss: 147.858
+19200/69092	Loss: 146.749
+22400/69092	Loss: 146.655
+25600/69092	Loss: 149.386
+28800/69092	Loss: 148.407
+32000/69092	Loss: 147.363
+35200/69092	Loss: 148.665
+38400/69092	Loss: 145.892
+41600/69092	Loss: 147.257
+44800/69092	Loss: 148.445
+48000/69092	Loss: 148.779
+51200/69092	Loss: 147.671
+54400/69092	Loss: 147.750
+57600/69092	Loss: 147.413
+60800/69092	Loss: 148.905
+64000/69092	Loss: 145.074
+67200/69092	Loss: 146.179
+Training time 0:07:59.000302
+Epoch: 128 Average loss: 147.42
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 546)
+0/69092	Loss: 152.609
+3200/69092	Loss: 148.827
+6400/69092	Loss: 149.909
+9600/69092	Loss: 147.004
+12800/69092	Loss: 147.111
+16000/69092	Loss: 144.803
+19200/69092	Loss: 148.799
+22400/69092	Loss: 150.989
+25600/69092	Loss: 146.997
+28800/69092	Loss: 147.658
+32000/69092	Loss: 145.647
+35200/69092	Loss: 149.345
+38400/69092	Loss: 148.063
+41600/69092	Loss: 146.276
+44800/69092	Loss: 146.095
+48000/69092	Loss: 147.454
+51200/69092	Loss: 147.728
+54400/69092	Loss: 146.567
+57600/69092	Loss: 146.449
+60800/69092	Loss: 146.527
+64000/69092	Loss: 148.803
+67200/69092	Loss: 144.118
+Training time 0:08:12.911462
+Epoch: 129 Average loss: 147.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 547)
+0/69092	Loss: 146.925
+3200/69092	Loss: 147.856
+6400/69092	Loss: 147.443
+9600/69092	Loss: 147.255
+12800/69092	Loss: 148.931
+16000/69092	Loss: 147.518
+19200/69092	Loss: 148.060
+22400/69092	Loss: 147.788
+25600/69092	Loss: 149.779
+28800/69092	Loss: 147.333
+32000/69092	Loss: 148.796
+35200/69092	Loss: 147.501
+38400/69092	Loss: 146.472
+41600/69092	Loss: 146.156
+44800/69092	Loss: 148.704
+48000/69092	Loss: 144.879
+51200/69092	Loss: 149.971
+54400/69092	Loss: 147.289
+57600/69092	Loss: 145.771
+60800/69092	Loss: 147.910
+64000/69092	Loss: 148.098
+67200/69092	Loss: 146.290
+Training time 0:08:13.558156
+Epoch: 130 Average loss: 147.54
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 548)
+0/69092	Loss: 149.508
+3200/69092	Loss: 147.696
+6400/69092	Loss: 148.856
+9600/69092	Loss: 147.725
+12800/69092	Loss: 146.567
+16000/69092	Loss: 149.474
+19200/69092	Loss: 149.224
+22400/69092	Loss: 147.491
+25600/69092	Loss: 150.212
+28800/69092	Loss: 146.108
+32000/69092	Loss: 146.547
+35200/69092	Loss: 144.104
+38400/69092	Loss: 147.899
+41600/69092	Loss: 147.223
+44800/69092	Loss: 148.601
+48000/69092	Loss: 148.724
+51200/69092	Loss: 147.372
+54400/69092	Loss: 146.775
+57600/69092	Loss: 145.695
+60800/69092	Loss: 145.900
+64000/69092	Loss: 145.089
+67200/69092	Loss: 146.736
+Training time 0:07:51.320967
+Epoch: 131 Average loss: 147.38
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 549)
+0/69092	Loss: 141.001
+3200/69092	Loss: 149.148
+6400/69092	Loss: 147.794
+9600/69092	Loss: 147.679
+12800/69092	Loss: 146.907
+16000/69092	Loss: 145.313
+19200/69092	Loss: 148.850
+22400/69092	Loss: 148.830
+25600/69092	Loss: 146.937
+28800/69092	Loss: 147.875
+32000/69092	Loss: 147.571
+35200/69092	Loss: 146.423
+38400/69092	Loss: 147.562
+41600/69092	Loss: 148.850
+44800/69092	Loss: 146.919
+48000/69092	Loss: 148.755
+51200/69092	Loss: 146.945
+54400/69092	Loss: 148.743
+57600/69092	Loss: 146.731
+60800/69092	Loss: 146.545
+64000/69092	Loss: 146.132
+67200/69092	Loss: 150.567
+Training time 0:08:10.009287
+Epoch: 132 Average loss: 147.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 550)
+0/69092	Loss: 152.756
+3200/69092	Loss: 146.223
+6400/69092	Loss: 148.479
+9600/69092	Loss: 148.050
+12800/69092	Loss: 145.997
+16000/69092	Loss: 147.631
+19200/69092	Loss: 146.452
+22400/69092	Loss: 146.036
+25600/69092	Loss: 147.272
+28800/69092	Loss: 146.291
+32000/69092	Loss: 147.560
+35200/69092	Loss: 148.799
+38400/69092	Loss: 147.844
+41600/69092	Loss: 148.385
+44800/69092	Loss: 146.596
+48000/69092	Loss: 148.314
+51200/69092	Loss: 148.889
+54400/69092	Loss: 147.303
+57600/69092	Loss: 149.438
+60800/69092	Loss: 146.217
+64000/69092	Loss: 145.970
+67200/69092	Loss: 146.731
+Training time 0:08:13.614751
+Epoch: 133 Average loss: 147.36
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 551)
+0/69092	Loss: 147.097
+3200/69092	Loss: 149.939
+6400/69092	Loss: 145.717
+9600/69092	Loss: 148.853
+12800/69092	Loss: 147.567
+16000/69092	Loss: 145.807
+19200/69092	Loss: 148.500
+22400/69092	Loss: 147.097
+25600/69092	Loss: 148.303
+28800/69092	Loss: 146.412
+32000/69092	Loss: 148.049
+35200/69092	Loss: 147.622
+38400/69092	Loss: 143.306
+41600/69092	Loss: 148.530
+44800/69092	Loss: 146.442
+48000/69092	Loss: 146.443
+51200/69092	Loss: 148.110
+54400/69092	Loss: 146.320
+57600/69092	Loss: 146.567
+60800/69092	Loss: 147.958
+64000/69092	Loss: 149.559
+67200/69092	Loss: 148.704
+Training time 0:07:57.950908
+Epoch: 134 Average loss: 147.41
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 552)
+0/69092	Loss: 144.213
+3200/69092	Loss: 148.146
+6400/69092	Loss: 145.956
+9600/69092	Loss: 148.158
+12800/69092	Loss: 145.836
+16000/69092	Loss: 145.665
+19200/69092	Loss: 147.205
+22400/69092	Loss: 146.121
+25600/69092	Loss: 148.371
+28800/69092	Loss: 146.314
+32000/69092	Loss: 147.920
+35200/69092	Loss: 147.553
+38400/69092	Loss: 150.762
+41600/69092	Loss: 150.620
+44800/69092	Loss: 149.081
+48000/69092	Loss: 145.399
+51200/69092	Loss: 146.686
+54400/69092	Loss: 146.642
+57600/69092	Loss: 149.188
+60800/69092	Loss: 146.796
+64000/69092	Loss: 147.291
+67200/69092	Loss: 149.267
+Training time 0:08:06.854811
+Epoch: 135 Average loss: 147.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 553)
+0/69092	Loss: 130.863
+3200/69092	Loss: 146.169
+6400/69092	Loss: 147.892
+9600/69092	Loss: 146.109
+12800/69092	Loss: 148.935
+16000/69092	Loss: 147.303
+19200/69092	Loss: 149.477
+22400/69092	Loss: 147.083
+25600/69092	Loss: 146.878
+28800/69092	Loss: 144.482
+32000/69092	Loss: 148.034
+35200/69092	Loss: 146.969
+38400/69092	Loss: 148.132
+41600/69092	Loss: 147.810
+44800/69092	Loss: 148.127
+48000/69092	Loss: 148.731
+51200/69092	Loss: 147.875
+54400/69092	Loss: 147.381
+57600/69092	Loss: 149.727
+60800/69092	Loss: 144.134
+64000/69092	Loss: 147.235
+67200/69092	Loss: 148.247
+Training time 0:08:26.751803
+Epoch: 136 Average loss: 147.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 554)
+0/69092	Loss: 141.173
+3200/69092	Loss: 148.024
+6400/69092	Loss: 146.600
+9600/69092	Loss: 146.682
+12800/69092	Loss: 147.187
+16000/69092	Loss: 145.813
+19200/69092	Loss: 145.991
+22400/69092	Loss: 146.792
+25600/69092	Loss: 146.281
+28800/69092	Loss: 148.965
+32000/69092	Loss: 147.063
+35200/69092	Loss: 148.140
+38400/69092	Loss: 147.617
+41600/69092	Loss: 148.269
+44800/69092	Loss: 148.357
+48000/69092	Loss: 150.111
+51200/69092	Loss: 147.012
+54400/69092	Loss: 144.853
+57600/69092	Loss: 150.206
+60800/69092	Loss: 146.126
+64000/69092	Loss: 145.905
+67200/69092	Loss: 148.163
+Training time 0:07:55.368098
+Epoch: 137 Average loss: 147.22
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 555)
+0/69092	Loss: 148.608
+3200/69092	Loss: 148.326
+6400/69092	Loss: 146.898
+9600/69092	Loss: 150.176
+12800/69092	Loss: 148.185
+16000/69092	Loss: 145.446
+19200/69092	Loss: 149.077
+22400/69092	Loss: 146.385
+25600/69092	Loss: 148.332
+28800/69092	Loss: 146.333
+32000/69092	Loss: 149.204
+35200/69092	Loss: 146.366
+38400/69092	Loss: 149.394
+41600/69092	Loss: 147.970
+44800/69092	Loss: 145.831
+48000/69092	Loss: 146.894
+51200/69092	Loss: 145.432
+54400/69092	Loss: 148.743
+57600/69092	Loss: 145.576
+60800/69092	Loss: 147.274
+64000/69092	Loss: 146.176
+67200/69092	Loss: 149.620
+Training time 0:08:10.197081
+Epoch: 138 Average loss: 147.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 556)
+0/69092	Loss: 134.684
+3200/69092	Loss: 148.582
+6400/69092	Loss: 146.947
+9600/69092	Loss: 146.362
+12800/69092	Loss: 146.738
+16000/69092	Loss: 149.528
+19200/69092	Loss: 147.867
+22400/69092	Loss: 146.849
+25600/69092	Loss: 147.079
+28800/69092	Loss: 148.170
+32000/69092	Loss: 146.702
+35200/69092	Loss: 146.809
+38400/69092	Loss: 149.344
+41600/69092	Loss: 148.242
+44800/69092	Loss: 147.575
+48000/69092	Loss: 148.723
+51200/69092	Loss: 148.396
+54400/69092	Loss: 145.200
+57600/69092	Loss: 146.916
+60800/69092	Loss: 144.552
+64000/69092	Loss: 146.248
+67200/69092	Loss: 149.941
+Training time 0:08:02.915528
+Epoch: 139 Average loss: 147.45
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 557)
+0/69092	Loss: 166.295
+3200/69092	Loss: 148.723
+6400/69092	Loss: 147.220
+9600/69092	Loss: 144.637
+12800/69092	Loss: 147.887
+16000/69092	Loss: 148.894
+19200/69092	Loss: 147.247
+22400/69092	Loss: 148.885
+25600/69092	Loss: 146.589
+28800/69092	Loss: 145.854
+32000/69092	Loss: 147.788
+35200/69092	Loss: 146.078
+38400/69092	Loss: 149.950
+41600/69092	Loss: 147.224
+44800/69092	Loss: 147.910
+48000/69092	Loss: 146.259
+51200/69092	Loss: 147.717
+54400/69092	Loss: 147.671
+57600/69092	Loss: 146.417
+60800/69092	Loss: 147.124
+64000/69092	Loss: 147.495
+67200/69092	Loss: 148.547
+Training time 0:08:01.500627
+Epoch: 140 Average loss: 147.44
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 558)
+0/69092	Loss: 150.415
+3200/69092	Loss: 147.755
+6400/69092	Loss: 148.786
+9600/69092	Loss: 145.049
+12800/69092	Loss: 148.315
+16000/69092	Loss: 146.712
+19200/69092	Loss: 149.528
+22400/69092	Loss: 147.612
+25600/69092	Loss: 148.713
+28800/69092	Loss: 147.505
+32000/69092	Loss: 148.213
+35200/69092	Loss: 147.243
+38400/69092	Loss: 144.729
+41600/69092	Loss: 148.828
+44800/69092	Loss: 146.919
+48000/69092	Loss: 147.031
+51200/69092	Loss: 145.458
+54400/69092	Loss: 145.426
+57600/69092	Loss: 149.812
+60800/69092	Loss: 148.419
+64000/69092	Loss: 148.254
+67200/69092	Loss: 146.173
+Training time 0:08:08.570936
+Epoch: 141 Average loss: 147.35
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 559)
+0/69092	Loss: 157.977
+3200/69092	Loss: 144.659
+6400/69092	Loss: 146.196
+9600/69092	Loss: 147.784
+12800/69092	Loss: 149.669
+16000/69092	Loss: 145.861
+19200/69092	Loss: 147.748
+22400/69092	Loss: 148.604
+25600/69092	Loss: 147.250
+28800/69092	Loss: 146.363
+32000/69092	Loss: 145.803
+35200/69092	Loss: 145.224
+38400/69092	Loss: 146.404
+41600/69092	Loss: 148.886
+44800/69092	Loss: 149.378
+48000/69092	Loss: 149.546
+51200/69092	Loss: 148.315
+54400/69092	Loss: 149.531
+57600/69092	Loss: 145.622
+60800/69092	Loss: 148.121
+64000/69092	Loss: 147.169
+67200/69092	Loss: 148.191
+Training time 0:08:22.773814
+Epoch: 142 Average loss: 147.46
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 560)
+0/69092	Loss: 130.874
+3200/69092	Loss: 146.979
+6400/69092	Loss: 147.386
+9600/69092	Loss: 146.650
+12800/69092	Loss: 147.119
+16000/69092	Loss: 145.112
+19200/69092	Loss: 148.646
+22400/69092	Loss: 146.642
+25600/69092	Loss: 148.992
+28800/69092	Loss: 146.060
+32000/69092	Loss: 148.406
+35200/69092	Loss: 145.636
+38400/69092	Loss: 144.372
+41600/69092	Loss: 146.853
+44800/69092	Loss: 151.247
+48000/69092	Loss: 148.157
+51200/69092	Loss: 144.789
+54400/69092	Loss: 147.969
+57600/69092	Loss: 147.084
+60800/69092	Loss: 146.353
+64000/69092	Loss: 146.482
+67200/69092	Loss: 150.983
+Training time 0:07:57.892779
+Epoch: 143 Average loss: 147.25
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 561)
+0/69092	Loss: 136.492
+3200/69092	Loss: 146.379
+6400/69092	Loss: 146.394
+9600/69092	Loss: 147.678
+12800/69092	Loss: 149.821
+16000/69092	Loss: 144.392
+19200/69092	Loss: 147.237
+22400/69092	Loss: 146.966
+25600/69092	Loss: 145.617
+28800/69092	Loss: 147.089
+32000/69092	Loss: 147.727
+35200/69092	Loss: 144.910
+38400/69092	Loss: 145.244
+41600/69092	Loss: 144.676
+44800/69092	Loss: 149.029
+48000/69092	Loss: 148.726
+51200/69092	Loss: 149.572
+54400/69092	Loss: 144.836
+57600/69092	Loss: 149.442
+60800/69092	Loss: 152.128
+64000/69092	Loss: 148.383
+67200/69092	Loss: 147.801
+Training time 0:08:05.278064
+Epoch: 144 Average loss: 147.27
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 562)
+0/69092	Loss: 155.547
+3200/69092	Loss: 147.878
+6400/69092	Loss: 147.437
+9600/69092	Loss: 145.749
+12800/69092	Loss: 146.523
+16000/69092	Loss: 147.208
+19200/69092	Loss: 148.561
+22400/69092	Loss: 146.663
+25600/69092	Loss: 145.962
+28800/69092	Loss: 146.542
+32000/69092	Loss: 148.000
+35200/69092	Loss: 148.007
+38400/69092	Loss: 148.534
+41600/69092	Loss: 149.100
+44800/69092	Loss: 146.897
+48000/69092	Loss: 148.061
+51200/69092	Loss: 148.487
+54400/69092	Loss: 147.675
+57600/69092	Loss: 147.388
+60800/69092	Loss: 147.710
+64000/69092	Loss: 148.644
+67200/69092	Loss: 148.430
+Training time 0:08:05.462415
+Epoch: 145 Average loss: 147.52
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 563)
+0/69092	Loss: 141.476
+3200/69092	Loss: 149.284
+6400/69092	Loss: 144.505
+9600/69092	Loss: 148.749
+12800/69092	Loss: 146.887
+16000/69092	Loss: 147.784
+19200/69092	Loss: 149.906
+22400/69092	Loss: 145.781
+25600/69092	Loss: 144.321
+28800/69092	Loss: 149.136
+32000/69092	Loss: 149.494
+35200/69092	Loss: 149.456
+38400/69092	Loss: 150.965
+41600/69092	Loss: 147.199
+44800/69092	Loss: 148.103
+48000/69092	Loss: 147.629
+51200/69092	Loss: 146.827
+54400/69092	Loss: 146.338
+57600/69092	Loss: 145.584
+60800/69092	Loss: 146.086
+64000/69092	Loss: 144.735
+67200/69092	Loss: 147.242
+Training time 0:07:53.375742
+Epoch: 146 Average loss: 147.37
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 564)
+0/69092	Loss: 145.077
+3200/69092	Loss: 149.148
+6400/69092	Loss: 147.610
+9600/69092	Loss: 145.020
+12800/69092	Loss: 146.620
+16000/69092	Loss: 149.771
+19200/69092	Loss: 148.582
+22400/69092	Loss: 147.811
+25600/69092	Loss: 148.411
+28800/69092	Loss: 145.871
+32000/69092	Loss: 149.438
+35200/69092	Loss: 147.239
+38400/69092	Loss: 147.398
+41600/69092	Loss: 148.715
+44800/69092	Loss: 146.787
+48000/69092	Loss: 145.832
+51200/69092	Loss: 147.700
+54400/69092	Loss: 149.107
+57600/69092	Loss: 144.336
+60800/69092	Loss: 147.276
+64000/69092	Loss: 143.743
+67200/69092	Loss: 147.773
+Training time 0:08:05.876698
+Epoch: 147 Average loss: 147.33
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 565)
+0/69092	Loss: 142.938
+3200/69092	Loss: 148.796
+6400/69092	Loss: 148.258
+9600/69092	Loss: 145.669
+12800/69092	Loss: 145.873
+16000/69092	Loss: 147.909
+19200/69092	Loss: 148.045
+22400/69092	Loss: 148.101
+25600/69092	Loss: 147.774
+28800/69092	Loss: 148.303
+32000/69092	Loss: 145.500
+35200/69092	Loss: 147.596
+38400/69092	Loss: 146.555
+41600/69092	Loss: 148.442
+44800/69092	Loss: 148.635
+48000/69092	Loss: 148.830
+51200/69092	Loss: 148.524
+54400/69092	Loss: 147.142
+57600/69092	Loss: 147.998
+60800/69092	Loss: 149.083
+64000/69092	Loss: 146.412
+67200/69092	Loss: 145.932
+Training time 0:08:11.503127
+Epoch: 148 Average loss: 147.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 566)
+0/69092	Loss: 146.477
+3200/69092	Loss: 147.490
+6400/69092	Loss: 145.514
+9600/69092	Loss: 147.572
+12800/69092	Loss: 150.839
+16000/69092	Loss: 149.132
+19200/69092	Loss: 147.461
+22400/69092	Loss: 146.922
+25600/69092	Loss: 146.440
+28800/69092	Loss: 145.862
+32000/69092	Loss: 146.229
+35200/69092	Loss: 145.243
+38400/69092	Loss: 147.437
+41600/69092	Loss: 146.530
+44800/69092	Loss: 149.220
+48000/69092	Loss: 147.374
+51200/69092	Loss: 148.015
+54400/69092	Loss: 146.136
+57600/69092	Loss: 144.269
+60800/69092	Loss: 148.842
+64000/69092	Loss: 151.641
+67200/69092	Loss: 148.462
+Training time 0:07:57.278589
+Epoch: 149 Average loss: 147.49
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 567)
+0/69092	Loss: 145.207
+3200/69092	Loss: 146.490
+6400/69092	Loss: 147.967
+9600/69092	Loss: 147.514
+12800/69092	Loss: 147.989
+16000/69092	Loss: 147.985
+19200/69092	Loss: 146.667
+22400/69092	Loss: 146.715
+25600/69092	Loss: 146.711
+28800/69092	Loss: 148.897
+32000/69092	Loss: 147.984
+35200/69092	Loss: 146.848
+38400/69092	Loss: 145.464
+41600/69092	Loss: 146.983
+44800/69092	Loss: 149.883
+48000/69092	Loss: 149.218
+51200/69092	Loss: 148.783
+54400/69092	Loss: 148.493
+57600/69092	Loss: 148.876
+60800/69092	Loss: 146.480
+64000/69092	Loss: 146.203
+67200/69092	Loss: 149.277
+Training time 0:08:11.809089
+Epoch: 150 Average loss: 147.62
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 568)
+0/69092	Loss: 145.365
+3200/69092	Loss: 144.960
+6400/69092	Loss: 147.693
+9600/69092	Loss: 146.036
+12800/69092	Loss: 146.263
+16000/69092	Loss: 145.250
+19200/69092	Loss: 148.490
+22400/69092	Loss: 149.705
+25600/69092	Loss: 149.470
+28800/69092	Loss: 146.566
+32000/69092	Loss: 145.759
+35200/69092	Loss: 149.376
+38400/69092	Loss: 146.257
+41600/69092	Loss: 147.143
+44800/69092	Loss: 147.430
+48000/69092	Loss: 149.140
+51200/69092	Loss: 148.773
+54400/69092	Loss: 148.749
+57600/69092	Loss: 148.413
+60800/69092	Loss: 146.255
+64000/69092	Loss: 150.442
+67200/69092	Loss: 146.416
+Training time 0:08:16.196576
+Epoch: 151 Average loss: 147.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 569)
+0/69092	Loss: 146.574
+3200/69092	Loss: 151.177
+6400/69092	Loss: 146.402
+9600/69092	Loss: 145.951
+12800/69092	Loss: 146.410
+16000/69092	Loss: 147.403
+19200/69092	Loss: 149.892
+22400/69092	Loss: 147.560
+25600/69092	Loss: 149.338
+28800/69092	Loss: 147.166
+32000/69092	Loss: 147.069
+35200/69092	Loss: 146.217
+38400/69092	Loss: 145.716
+41600/69092	Loss: 145.488
+44800/69092	Loss: 148.051
+48000/69092	Loss: 148.589
+51200/69092	Loss: 149.149
+54400/69092	Loss: 147.680
+57600/69092	Loss: 144.959
+60800/69092	Loss: 147.551
+64000/69092	Loss: 147.548
+67200/69092	Loss: 145.768
+Training time 0:07:54.904224
+Epoch: 152 Average loss: 147.31
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 570)
+0/69092	Loss: 145.068
+3200/69092	Loss: 147.537
+6400/69092	Loss: 148.622
+9600/69092	Loss: 147.140
+12800/69092	Loss: 145.827
+16000/69092	Loss: 148.789
+19200/69092	Loss: 148.151
+22400/69092	Loss: 148.940
+25600/69092	Loss: 146.418
+28800/69092	Loss: 146.190
+32000/69092	Loss: 147.580
+35200/69092	Loss: 146.546
+38400/69092	Loss: 145.092
+41600/69092	Loss: 149.301
+44800/69092	Loss: 147.918
+48000/69092	Loss: 146.547
+51200/69092	Loss: 147.253
+54400/69092	Loss: 146.969
+57600/69092	Loss: 147.285
+60800/69092	Loss: 146.194
+64000/69092	Loss: 146.748
+67200/69092	Loss: 147.187
+Training time 0:08:16.881495
+Epoch: 153 Average loss: 147.18
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 571)
+0/69092	Loss: 159.744
+3200/69092	Loss: 146.211
+6400/69092	Loss: 147.397
+9600/69092	Loss: 146.285
+12800/69092	Loss: 148.917
+16000/69092	Loss: 146.914
+19200/69092	Loss: 147.067
+22400/69092	Loss: 147.831
+25600/69092	Loss: 147.842
+28800/69092	Loss: 147.920
+32000/69092	Loss: 146.866
+35200/69092	Loss: 145.670
+38400/69092	Loss: 147.534
+41600/69092	Loss: 147.350
+44800/69092	Loss: 149.753
+48000/69092	Loss: 147.743
+51200/69092	Loss: 147.723
+54400/69092	Loss: 148.435
+57600/69092	Loss: 146.846
+60800/69092	Loss: 147.330
+64000/69092	Loss: 148.129
+67200/69092	Loss: 144.898
+Training time 0:08:08.467235
+Epoch: 154 Average loss: 147.36
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 572)
+0/69092	Loss: 138.177
+3200/69092	Loss: 146.514
+6400/69092	Loss: 147.551
+9600/69092	Loss: 143.710
+12800/69092	Loss: 149.011
+16000/69092	Loss: 145.641
+19200/69092	Loss: 149.521
+22400/69092	Loss: 146.858
+25600/69092	Loss: 145.464
+28800/69092	Loss: 146.863
+32000/69092	Loss: 145.421
+35200/69092	Loss: 150.571
+38400/69092	Loss: 146.843
+41600/69092	Loss: 144.797
+44800/69092	Loss: 149.111
+48000/69092	Loss: 147.898
+51200/69092	Loss: 147.740
+54400/69092	Loss: 148.382
+57600/69092	Loss: 148.760
+60800/69092	Loss: 146.837
+64000/69092	Loss: 145.467
+67200/69092	Loss: 146.055
+Training time 0:08:09.439371
+Epoch: 155 Average loss: 147.14
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 573)
+0/69092	Loss: 152.974
+3200/69092	Loss: 146.848
+6400/69092	Loss: 146.924
+9600/69092	Loss: 146.766
+12800/69092	Loss: 148.556
+16000/69092	Loss: 147.481
+19200/69092	Loss: 146.657
+22400/69092	Loss: 147.372
+25600/69092	Loss: 147.000
+28800/69092	Loss: 145.636
+32000/69092	Loss: 147.123
+35200/69092	Loss: 146.664
+38400/69092	Loss: 146.039
+41600/69092	Loss: 147.847
+44800/69092	Loss: 148.166
+48000/69092	Loss: 145.284
+51200/69092	Loss: 148.066
+54400/69092	Loss: 145.196
+57600/69092	Loss: 147.271
+60800/69092	Loss: 147.550
+64000/69092	Loss: 148.953
+67200/69092	Loss: 146.986
+Training time 0:08:08.310172
+Epoch: 156 Average loss: 147.08
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last' (iter 574)
+0/69092	Loss: 171.319
+3200/69092	Loss: 145.073
+6400/69092	Loss: 147.437
+9600/69092	Loss: 145.683
diff --git a/OAR.2073650.stderr b/OAR.2073650.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..65b567295131a38d6567f9bfb6d59e94bd60c566
--- /dev/null
+++ b/OAR.2073650.stderr
@@ -0,0 +1,3 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+## OAR [2020-07-05 20:29:46] Job 2073650 KILLED ##
diff --git a/OAR.2073650.stdout b/OAR.2073650.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..2efcb5c8d55b967f9fb554cc1e1fae25b1c04fe3
--- /dev/null
+++ b/OAR.2073650.stdout
@@ -0,0 +1,201 @@
+Namespace(batch_size=64, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='beta_VAE_bs_64_ls_20', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=20, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=40, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=20, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 773035
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_20/checkpoints/last (iter 390)'
+0/69092	Loss: 145.765
+3200/69092	Loss: 147.315
+6400/69092	Loss: 148.337
+9600/69092	Loss: 145.964
+12800/69092	Loss: 148.572
+16000/69092	Loss: 149.361
+19200/69092	Loss: 147.523
+22400/69092	Loss: 149.899
+25600/69092	Loss: 151.143
+28800/69092	Loss: 148.882
+32000/69092	Loss: 150.949
+35200/69092	Loss: 146.058
+38400/69092	Loss: 148.318
+41600/69092	Loss: 150.406
+44800/69092	Loss: 147.602
+48000/69092	Loss: 151.432
+51200/69092	Loss: 148.786
+54400/69092	Loss: 148.442
+57600/69092	Loss: 150.469
+60800/69092	Loss: 147.312
+64000/69092	Loss: 148.590
+67200/69092	Loss: 148.844
+Training time 0:12:40.828613
+Epoch: 1 Average loss: 148.78
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_20/checkpoints/last' (iter 391)
+0/69092	Loss: 162.627
+3200/69092	Loss: 149.409
+6400/69092	Loss: 148.732
+9600/69092	Loss: 146.733
+12800/69092	Loss: 145.768
+16000/69092	Loss: 148.202
+19200/69092	Loss: 150.671
+22400/69092	Loss: 148.493
+25600/69092	Loss: 146.693
+28800/69092	Loss: 145.756
+32000/69092	Loss: 147.772
+35200/69092	Loss: 152.809
+38400/69092	Loss: 148.927
+41600/69092	Loss: 147.875
+44800/69092	Loss: 148.387
+48000/69092	Loss: 148.842
+51200/69092	Loss: 149.023
+54400/69092	Loss: 151.485
+57600/69092	Loss: 150.449
+60800/69092	Loss: 147.836
+64000/69092	Loss: 148.325
+67200/69092	Loss: 150.672
+Training time 0:07:51.103281
+Epoch: 2 Average loss: 148.81
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_20/checkpoints/last' (iter 392)
+0/69092	Loss: 119.724
+3200/69092	Loss: 149.423
+6400/69092	Loss: 148.858
+9600/69092	Loss: 148.994
+12800/69092	Loss: 147.881
+16000/69092	Loss: 149.553
+19200/69092	Loss: 148.149
+22400/69092	Loss: 151.134
+25600/69092	Loss: 150.630
+28800/69092	Loss: 151.023
+32000/69092	Loss: 149.217
+35200/69092	Loss: 148.181
+38400/69092	Loss: 149.857
+41600/69092	Loss: 147.063
+44800/69092	Loss: 150.003
+48000/69092	Loss: 148.208
+51200/69092	Loss: 148.987
+54400/69092	Loss: 148.855
+57600/69092	Loss: 148.799
+60800/69092	Loss: 147.418
+64000/69092	Loss: 147.488
+67200/69092	Loss: 148.435
+Training time 0:08:44.211685
+Epoch: 3 Average loss: 148.83
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_20/checkpoints/last' (iter 393)
+0/69092	Loss: 152.990
+3200/69092	Loss: 150.329
+6400/69092	Loss: 152.139
+9600/69092	Loss: 146.796
+12800/69092	Loss: 150.662
+16000/69092	Loss: 146.989
+19200/69092	Loss: 147.228
+22400/69092	Loss: 145.273
+25600/69092	Loss: 147.688
+28800/69092	Loss: 149.986
+32000/69092	Loss: 148.849
+35200/69092	Loss: 147.079
+38400/69092	Loss: 150.577
+41600/69092	Loss: 150.871
+44800/69092	Loss: 147.883
+48000/69092	Loss: 149.811
+51200/69092	Loss: 148.183
+54400/69092	Loss: 148.998
+57600/69092	Loss: 147.924
+60800/69092	Loss: 148.276
+64000/69092	Loss: 149.520
+67200/69092	Loss: 147.679
+Training time 0:10:01.435877
+Epoch: 4 Average loss: 148.72
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_20/checkpoints/last' (iter 394)
+0/69092	Loss: 148.686
+3200/69092	Loss: 151.682
+6400/69092	Loss: 147.438
+9600/69092	Loss: 148.873
+12800/69092	Loss: 147.928
+16000/69092	Loss: 148.323
+19200/69092	Loss: 149.025
+22400/69092	Loss: 146.181
+25600/69092	Loss: 150.025
+28800/69092	Loss: 148.004
+32000/69092	Loss: 148.554
+35200/69092	Loss: 149.418
+38400/69092	Loss: 149.126
+41600/69092	Loss: 149.163
+44800/69092	Loss: 150.799
+48000/69092	Loss: 145.510
+51200/69092	Loss: 147.544
+54400/69092	Loss: 146.746
+57600/69092	Loss: 149.351
+60800/69092	Loss: 149.152
+64000/69092	Loss: 150.710
+67200/69092	Loss: 147.245
+Training time 0:09:41.807893
+Epoch: 5 Average loss: 148.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_20/checkpoints/last' (iter 395)
+0/69092	Loss: 153.664
+3200/69092	Loss: 148.122
+6400/69092	Loss: 146.158
+9600/69092	Loss: 151.407
+12800/69092	Loss: 146.721
+16000/69092	Loss: 148.823
+19200/69092	Loss: 148.206
+22400/69092	Loss: 148.728
+25600/69092	Loss: 145.796
+28800/69092	Loss: 149.885
+32000/69092	Loss: 148.442
+35200/69092	Loss: 150.618
+38400/69092	Loss: 149.806
+41600/69092	Loss: 147.652
+44800/69092	Loss: 149.269
+48000/69092	Loss: 149.191
+51200/69092	Loss: 148.144
+54400/69092	Loss: 150.763
+57600/69092	Loss: 148.333
+60800/69092	Loss: 149.834
+64000/69092	Loss: 148.157
+67200/69092	Loss: 148.662
+Training time 0:09:42.791872
+Epoch: 6 Average loss: 148.67
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_20/checkpoints/last' (iter 396)
+0/69092	Loss: 151.873
+3200/69092	Loss: 147.416
+6400/69092	Loss: 147.394
+9600/69092	Loss: 150.011
diff --git a/OAR.2073651.stderr b/OAR.2073651.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..dfb27d850c18db25c96bfad25d3ed853f4adfd78
--- /dev/null
+++ b/OAR.2073651.stderr
@@ -0,0 +1,3 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+## OAR [2020-07-07 08:29:14] Job 2073651 KILLED ##
diff --git a/OAR.2073651.stdout b/OAR.2073651.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..48dfea6333c00ee0a623d7c5717fa37c608ddcf1
--- /dev/null
+++ b/OAR.2073651.stdout
@@ -0,0 +1,7074 @@
+Namespace(batch_size=64, beta=4, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='beta_VAE_bs_64_ls_5', gpu_devices=[0, 1], is_beta_VAE=True, latent_spec_cont=5, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=10, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=5, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 761485
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last (iter 423)'
+0/69092	Loss: 159.536
+3200/69092	Loss: 156.964
+6400/69092	Loss: 156.627
+9600/69092	Loss: 159.322
+12800/69092	Loss: 157.604
+16000/69092	Loss: 157.206
+19200/69092	Loss: 156.209
+22400/69092	Loss: 158.548
+25600/69092	Loss: 160.952
+28800/69092	Loss: 157.815
+32000/69092	Loss: 156.125
+35200/69092	Loss: 155.692
+38400/69092	Loss: 157.666
+41600/69092	Loss: 157.600
+44800/69092	Loss: 159.084
+48000/69092	Loss: 157.553
+51200/69092	Loss: 155.862
+54400/69092	Loss: 160.372
+57600/69092	Loss: 158.866
+60800/69092	Loss: 157.537
+64000/69092	Loss: 157.912
+67200/69092	Loss: 159.467
+Training time 0:12:14.428787
+Epoch: 1 Average loss: 157.89
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 424)
+0/69092	Loss: 136.983
+3200/69092	Loss: 161.328
+6400/69092	Loss: 158.126
+9600/69092	Loss: 157.329
+12800/69092	Loss: 158.636
+16000/69092	Loss: 158.760
+19200/69092	Loss: 159.480
+22400/69092	Loss: 157.049
+25600/69092	Loss: 157.733
+28800/69092	Loss: 157.126
+32000/69092	Loss: 158.278
+35200/69092	Loss: 158.989
+38400/69092	Loss: 156.966
+41600/69092	Loss: 159.647
+44800/69092	Loss: 159.306
+48000/69092	Loss: 156.091
+51200/69092	Loss: 158.123
+54400/69092	Loss: 157.545
+57600/69092	Loss: 158.712
+60800/69092	Loss: 159.296
+64000/69092	Loss: 158.417
+67200/69092	Loss: 157.313
+Training time 0:09:12.950775
+Epoch: 2 Average loss: 158.26
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 425)
+0/69092	Loss: 162.019
+3200/69092	Loss: 160.239
+6400/69092	Loss: 158.537
+9600/69092	Loss: 157.791
+12800/69092	Loss: 157.710
+16000/69092	Loss: 159.825
+19200/69092	Loss: 156.028
+22400/69092	Loss: 154.636
+25600/69092	Loss: 157.583
+28800/69092	Loss: 158.573
+32000/69092	Loss: 157.252
+35200/69092	Loss: 158.742
+38400/69092	Loss: 156.330
+41600/69092	Loss: 157.850
+44800/69092	Loss: 157.223
+48000/69092	Loss: 158.273
+51200/69092	Loss: 159.822
+54400/69092	Loss: 155.480
+57600/69092	Loss: 157.110
+60800/69092	Loss: 157.016
+64000/69092	Loss: 157.585
+67200/69092	Loss: 156.774
+Training time 0:08:07.513902
+Epoch: 3 Average loss: 157.63
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 426)
+0/69092	Loss: 148.759
+3200/69092	Loss: 156.159
+6400/69092	Loss: 156.133
+9600/69092	Loss: 158.954
+12800/69092	Loss: 157.994
+16000/69092	Loss: 156.004
+19200/69092	Loss: 158.864
+22400/69092	Loss: 159.584
+25600/69092	Loss: 158.186
+28800/69092	Loss: 159.375
+32000/69092	Loss: 158.775
+35200/69092	Loss: 157.204
+38400/69092	Loss: 156.828
+41600/69092	Loss: 156.434
+44800/69092	Loss: 160.350
+48000/69092	Loss: 155.378
+51200/69092	Loss: 161.229
+54400/69092	Loss: 158.433
+57600/69092	Loss: 158.731
+60800/69092	Loss: 159.032
+64000/69092	Loss: 153.309
+67200/69092	Loss: 158.461
+Training time 0:09:39.626804
+Epoch: 4 Average loss: 157.92
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 427)
+0/69092	Loss: 139.619
+3200/69092	Loss: 158.908
+6400/69092	Loss: 159.686
+9600/69092	Loss: 161.158
+12800/69092	Loss: 156.215
+16000/69092	Loss: 155.079
+19200/69092	Loss: 156.965
+22400/69092	Loss: 157.822
+25600/69092	Loss: 156.639
+28800/69092	Loss: 157.618
+32000/69092	Loss: 161.737
+35200/69092	Loss: 160.074
+38400/69092	Loss: 156.458
+41600/69092	Loss: 157.742
+44800/69092	Loss: 161.107
+48000/69092	Loss: 157.207
+51200/69092	Loss: 154.605
+54400/69092	Loss: 154.957
+57600/69092	Loss: 155.753
+60800/69092	Loss: 159.835
+64000/69092	Loss: 157.179
+67200/69092	Loss: 158.128
+Training time 0:08:50.536363
+Epoch: 5 Average loss: 157.79
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 428)
+0/69092	Loss: 150.030
+3200/69092	Loss: 160.528
+6400/69092	Loss: 157.679
+9600/69092	Loss: 157.090
+12800/69092	Loss: 158.818
+16000/69092	Loss: 157.122
+19200/69092	Loss: 157.595
+22400/69092	Loss: 159.602
+25600/69092	Loss: 158.655
+28800/69092	Loss: 157.908
+32000/69092	Loss: 161.211
+35200/69092	Loss: 156.909
+38400/69092	Loss: 159.956
+41600/69092	Loss: 155.615
+44800/69092	Loss: 157.701
+48000/69092	Loss: 156.338
+51200/69092	Loss: 155.603
+54400/69092	Loss: 158.105
+57600/69092	Loss: 157.580
+60800/69092	Loss: 155.637
+64000/69092	Loss: 154.851
+67200/69092	Loss: 157.567
+Training time 0:08:41.573118
+Epoch: 6 Average loss: 157.66
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 429)
+0/69092	Loss: 158.621
+3200/69092	Loss: 156.626
+6400/69092	Loss: 157.778
+9600/69092	Loss: 155.444
+12800/69092	Loss: 158.748
+16000/69092	Loss: 154.759
+19200/69092	Loss: 156.554
+22400/69092	Loss: 161.091
+25600/69092	Loss: 157.952
+28800/69092	Loss: 157.593
+32000/69092	Loss: 157.132
+35200/69092	Loss: 158.869
+38400/69092	Loss: 159.848
+41600/69092	Loss: 154.804
+44800/69092	Loss: 159.082
+48000/69092	Loss: 159.371
+51200/69092	Loss: 158.761
+54400/69092	Loss: 159.219
+57600/69092	Loss: 157.669
+60800/69092	Loss: 159.230
+64000/69092	Loss: 156.938
+67200/69092	Loss: 157.781
+Training time 0:07:39.687882
+Epoch: 7 Average loss: 157.85
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 430)
+0/69092	Loss: 151.337
+3200/69092	Loss: 156.832
+6400/69092	Loss: 156.516
+9600/69092	Loss: 157.503
+12800/69092	Loss: 159.391
+16000/69092	Loss: 156.212
+19200/69092	Loss: 157.825
+22400/69092	Loss: 160.044
+25600/69092	Loss: 155.110
+28800/69092	Loss: 158.103
+32000/69092	Loss: 156.077
+35200/69092	Loss: 155.735
+38400/69092	Loss: 157.534
+41600/69092	Loss: 155.975
+44800/69092	Loss: 158.959
+48000/69092	Loss: 160.933
+51200/69092	Loss: 157.570
+54400/69092	Loss: 158.874
+57600/69092	Loss: 156.658
+60800/69092	Loss: 159.475
+64000/69092	Loss: 158.879
+67200/69092	Loss: 158.843
+Training time 0:07:31.381801
+Epoch: 8 Average loss: 157.77
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 431)
+0/69092	Loss: 160.945
+3200/69092	Loss: 158.518
+6400/69092	Loss: 156.842
+9600/69092	Loss: 156.422
+12800/69092	Loss: 160.022
+16000/69092	Loss: 159.528
+19200/69092	Loss: 156.142
+22400/69092	Loss: 158.788
+25600/69092	Loss: 159.407
+28800/69092	Loss: 156.944
+32000/69092	Loss: 155.368
+35200/69092	Loss: 157.420
+38400/69092	Loss: 155.830
+41600/69092	Loss: 158.310
+44800/69092	Loss: 159.056
+48000/69092	Loss: 157.731
+51200/69092	Loss: 160.071
+54400/69092	Loss: 160.835
+57600/69092	Loss: 159.315
+60800/69092	Loss: 156.692
+64000/69092	Loss: 154.337
+67200/69092	Loss: 156.444
+Training time 0:07:35.292036
+Epoch: 9 Average loss: 157.88
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 432)
+0/69092	Loss: 153.914
+3200/69092	Loss: 159.609
+6400/69092	Loss: 157.889
+9600/69092	Loss: 157.788
+12800/69092	Loss: 159.061
+16000/69092	Loss: 157.617
+19200/69092	Loss: 157.626
+22400/69092	Loss: 156.800
+25600/69092	Loss: 159.390
+28800/69092	Loss: 156.528
+32000/69092	Loss: 158.310
+35200/69092	Loss: 159.955
+38400/69092	Loss: 156.574
+41600/69092	Loss: 158.475
+44800/69092	Loss: 155.531
+48000/69092	Loss: 157.169
+51200/69092	Loss: 158.367
+54400/69092	Loss: 159.216
+57600/69092	Loss: 158.485
+60800/69092	Loss: 160.287
+64000/69092	Loss: 158.240
+67200/69092	Loss: 158.035
+Training time 0:07:37.014366
+Epoch: 10 Average loss: 158.05
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 433)
+0/69092	Loss: 148.680
+3200/69092	Loss: 157.224
+6400/69092	Loss: 158.397
+9600/69092	Loss: 156.786
+12800/69092	Loss: 157.735
+16000/69092	Loss: 158.394
+19200/69092	Loss: 157.466
+22400/69092	Loss: 156.144
+25600/69092	Loss: 155.949
+28800/69092	Loss: 157.839
+32000/69092	Loss: 159.235
+35200/69092	Loss: 157.036
+38400/69092	Loss: 154.763
+41600/69092	Loss: 158.088
+44800/69092	Loss: 158.654
+48000/69092	Loss: 159.390
+51200/69092	Loss: 161.350
+54400/69092	Loss: 158.083
+57600/69092	Loss: 158.831
+60800/69092	Loss: 159.074
+64000/69092	Loss: 157.965
+67200/69092	Loss: 159.681
+Training time 0:07:35.085213
+Epoch: 11 Average loss: 157.92
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 434)
+0/69092	Loss: 153.850
+3200/69092	Loss: 159.010
+6400/69092	Loss: 160.210
+9600/69092	Loss: 155.147
+12800/69092	Loss: 157.174
+16000/69092	Loss: 157.598
+19200/69092	Loss: 159.140
+22400/69092	Loss: 156.286
+25600/69092	Loss: 158.417
+28800/69092	Loss: 154.750
+32000/69092	Loss: 157.324
+35200/69092	Loss: 160.133
+38400/69092	Loss: 159.134
+41600/69092	Loss: 159.046
+44800/69092	Loss: 153.860
+48000/69092	Loss: 158.555
+51200/69092	Loss: 157.517
+54400/69092	Loss: 160.169
+57600/69092	Loss: 155.645
+60800/69092	Loss: 160.217
+64000/69092	Loss: 156.511
+67200/69092	Loss: 157.118
+Training time 0:08:43.207458
+Epoch: 12 Average loss: 157.82
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 435)
+0/69092	Loss: 165.635
+3200/69092	Loss: 159.634
+6400/69092	Loss: 155.154
+9600/69092	Loss: 158.033
+12800/69092	Loss: 158.410
+16000/69092	Loss: 159.610
+19200/69092	Loss: 157.520
+22400/69092	Loss: 160.794
+25600/69092	Loss: 158.873
+28800/69092	Loss: 159.508
+32000/69092	Loss: 158.083
+35200/69092	Loss: 158.731
+38400/69092	Loss: 156.455
+41600/69092	Loss: 156.757
+44800/69092	Loss: 158.436
+48000/69092	Loss: 158.004
+51200/69092	Loss: 155.409
+54400/69092	Loss: 159.227
+57600/69092	Loss: 157.677
+60800/69092	Loss: 154.932
+64000/69092	Loss: 155.825
+67200/69092	Loss: 159.334
+Training time 0:07:47.871126
+Epoch: 13 Average loss: 157.91
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 436)
+0/69092	Loss: 135.028
+3200/69092	Loss: 160.175
+6400/69092	Loss: 157.534
+9600/69092	Loss: 157.038
+12800/69092	Loss: 160.133
+16000/69092	Loss: 155.530
+19200/69092	Loss: 158.124
+22400/69092	Loss: 157.626
+25600/69092	Loss: 161.138
+28800/69092	Loss: 158.219
+32000/69092	Loss: 160.403
+35200/69092	Loss: 159.659
+38400/69092	Loss: 155.102
+41600/69092	Loss: 156.331
+44800/69092	Loss: 155.884
+48000/69092	Loss: 159.341
+51200/69092	Loss: 157.517
+54400/69092	Loss: 155.084
+57600/69092	Loss: 157.817
+60800/69092	Loss: 158.205
+64000/69092	Loss: 159.767
+67200/69092	Loss: 153.757
+Training time 0:08:09.446855
+Epoch: 14 Average loss: 157.82
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 437)
+0/69092	Loss: 155.597
+3200/69092	Loss: 158.299
+6400/69092	Loss: 157.800
+9600/69092	Loss: 160.022
+12800/69092	Loss: 158.368
+16000/69092	Loss: 158.516
+19200/69092	Loss: 158.466
+22400/69092	Loss: 154.448
+25600/69092	Loss: 155.393
+28800/69092	Loss: 157.818
+32000/69092	Loss: 160.555
+35200/69092	Loss: 155.853
+38400/69092	Loss: 158.591
+41600/69092	Loss: 157.010
+44800/69092	Loss: 158.718
+48000/69092	Loss: 158.461
+51200/69092	Loss: 157.971
+54400/69092	Loss: 156.120
+57600/69092	Loss: 157.377
+60800/69092	Loss: 157.720
+64000/69092	Loss: 155.116
+67200/69092	Loss: 156.510
+Training time 0:07:35.945721
+Epoch: 15 Average loss: 157.69
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 438)
+0/69092	Loss: 177.483
+3200/69092	Loss: 154.189
+6400/69092	Loss: 159.241
+9600/69092	Loss: 158.459
+12800/69092	Loss: 155.605
+16000/69092	Loss: 158.645
+19200/69092	Loss: 158.505
+22400/69092	Loss: 154.217
+25600/69092	Loss: 159.937
+28800/69092	Loss: 158.370
+32000/69092	Loss: 156.295
+35200/69092	Loss: 159.231
+38400/69092	Loss: 159.712
+41600/69092	Loss: 155.789
+44800/69092	Loss: 158.654
+48000/69092	Loss: 156.719
+51200/69092	Loss: 158.857
+54400/69092	Loss: 159.011
+57600/69092	Loss: 157.526
+60800/69092	Loss: 155.950
+64000/69092	Loss: 159.854
+67200/69092	Loss: 158.624
+Training time 0:07:34.116056
+Epoch: 16 Average loss: 157.82
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 439)
+0/69092	Loss: 148.961
+3200/69092	Loss: 158.660
+6400/69092	Loss: 155.501
+9600/69092	Loss: 160.251
+12800/69092	Loss: 155.608
+16000/69092	Loss: 159.457
+19200/69092	Loss: 161.825
+22400/69092	Loss: 157.308
+25600/69092	Loss: 158.308
+28800/69092	Loss: 156.571
+32000/69092	Loss: 158.415
+35200/69092	Loss: 156.649
+38400/69092	Loss: 159.040
+41600/69092	Loss: 156.326
+44800/69092	Loss: 159.690
+48000/69092	Loss: 157.073
+51200/69092	Loss: 160.259
+54400/69092	Loss: 157.097
+57600/69092	Loss: 157.901
+60800/69092	Loss: 158.658
+64000/69092	Loss: 155.405
+67200/69092	Loss: 157.610
+Training time 0:07:48.198007
+Epoch: 17 Average loss: 157.99
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 440)
+0/69092	Loss: 138.413
+3200/69092	Loss: 158.417
+6400/69092	Loss: 158.447
+9600/69092	Loss: 155.117
+12800/69092	Loss: 158.345
+16000/69092	Loss: 158.679
+19200/69092	Loss: 157.537
+22400/69092	Loss: 156.858
+25600/69092	Loss: 158.419
+28800/69092	Loss: 160.004
+32000/69092	Loss: 156.825
+35200/69092	Loss: 154.287
+38400/69092	Loss: 160.405
+41600/69092	Loss: 160.493
+44800/69092	Loss: 158.079
+48000/69092	Loss: 154.292
+51200/69092	Loss: 160.759
+54400/69092	Loss: 155.447
+57600/69092	Loss: 157.609
+60800/69092	Loss: 157.401
+64000/69092	Loss: 160.541
+67200/69092	Loss: 156.489
+Training time 0:08:01.101580
+Epoch: 18 Average loss: 157.84
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 441)
+0/69092	Loss: 169.945
+3200/69092	Loss: 156.416
+6400/69092	Loss: 156.250
+9600/69092	Loss: 158.096
+12800/69092	Loss: 160.494
+16000/69092	Loss: 157.494
+19200/69092	Loss: 158.930
+22400/69092	Loss: 157.447
+25600/69092	Loss: 156.814
+28800/69092	Loss: 157.671
+32000/69092	Loss: 158.687
+35200/69092	Loss: 157.307
+38400/69092	Loss: 156.875
+41600/69092	Loss: 159.263
+44800/69092	Loss: 158.342
+48000/69092	Loss: 157.680
+51200/69092	Loss: 156.715
+54400/69092	Loss: 155.700
+57600/69092	Loss: 158.389
+60800/69092	Loss: 158.697
+64000/69092	Loss: 157.015
+67200/69092	Loss: 157.701
+Training time 0:07:32.109713
+Epoch: 19 Average loss: 157.73
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 442)
+0/69092	Loss: 169.998
+3200/69092	Loss: 159.432
+6400/69092	Loss: 157.711
+9600/69092	Loss: 159.400
+12800/69092	Loss: 159.333
+16000/69092	Loss: 157.852
+19200/69092	Loss: 157.206
+22400/69092	Loss: 158.495
+25600/69092	Loss: 158.703
+28800/69092	Loss: 158.501
+32000/69092	Loss: 156.430
+35200/69092	Loss: 158.784
+38400/69092	Loss: 160.165
+41600/69092	Loss: 157.315
+44800/69092	Loss: 155.959
+48000/69092	Loss: 155.729
+51200/69092	Loss: 155.444
+54400/69092	Loss: 156.798
+57600/69092	Loss: 156.547
+60800/69092	Loss: 154.793
+64000/69092	Loss: 156.876
+67200/69092	Loss: 159.865
+Training time 0:07:35.684876
+Epoch: 20 Average loss: 157.72
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 443)
+0/69092	Loss: 161.519
+3200/69092	Loss: 157.563
+6400/69092	Loss: 156.920
+9600/69092	Loss: 155.982
+12800/69092	Loss: 154.449
+16000/69092	Loss: 158.604
+19200/69092	Loss: 154.128
+22400/69092	Loss: 155.172
+25600/69092	Loss: 160.305
+28800/69092	Loss: 157.151
+32000/69092	Loss: 159.658
+35200/69092	Loss: 157.295
+38400/69092	Loss: 157.922
+41600/69092	Loss: 158.129
+44800/69092	Loss: 158.988
+48000/69092	Loss: 159.844
+51200/69092	Loss: 158.109
+54400/69092	Loss: 162.173
+57600/69092	Loss: 155.860
+60800/69092	Loss: 159.922
+64000/69092	Loss: 156.174
+67200/69092	Loss: 158.907
+Training time 0:07:28.638223
+Epoch: 21 Average loss: 157.80
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 444)
+0/69092	Loss: 153.325
+3200/69092	Loss: 158.200
+6400/69092	Loss: 155.818
+9600/69092	Loss: 158.507
+12800/69092	Loss: 157.911
+16000/69092	Loss: 155.296
+19200/69092	Loss: 158.632
+22400/69092	Loss: 155.027
+25600/69092	Loss: 156.718
+28800/69092	Loss: 156.570
+32000/69092	Loss: 158.150
+35200/69092	Loss: 158.443
+38400/69092	Loss: 159.040
+41600/69092	Loss: 157.918
+44800/69092	Loss: 157.619
+48000/69092	Loss: 156.201
+51200/69092	Loss: 160.044
+54400/69092	Loss: 159.485
+57600/69092	Loss: 159.081
+60800/69092	Loss: 158.667
+64000/69092	Loss: 159.902
+67200/69092	Loss: 157.733
+Training time 0:07:30.791146
+Epoch: 22 Average loss: 157.83
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 445)
+0/69092	Loss: 158.628
+3200/69092	Loss: 158.180
+6400/69092	Loss: 158.053
+9600/69092	Loss: 156.529
+12800/69092	Loss: 158.562
+16000/69092	Loss: 159.743
+19200/69092	Loss: 158.554
+22400/69092	Loss: 157.059
+25600/69092	Loss: 153.542
+28800/69092	Loss: 158.726
+32000/69092	Loss: 158.651
+35200/69092	Loss: 156.593
+38400/69092	Loss: 158.955
+41600/69092	Loss: 157.519
+44800/69092	Loss: 158.518
+48000/69092	Loss: 155.934
+51200/69092	Loss: 157.039
+54400/69092	Loss: 156.536
+57600/69092	Loss: 162.095
+60800/69092	Loss: 158.211
+64000/69092	Loss: 157.827
+67200/69092	Loss: 156.679
+Training time 0:07:28.715618
+Epoch: 23 Average loss: 157.78
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 446)
+0/69092	Loss: 135.041
+3200/69092	Loss: 159.116
+6400/69092	Loss: 156.269
+9600/69092	Loss: 156.588
+12800/69092	Loss: 155.984
+16000/69092	Loss: 160.897
+19200/69092	Loss: 158.422
+22400/69092	Loss: 154.919
+25600/69092	Loss: 158.799
+28800/69092	Loss: 159.270
+32000/69092	Loss: 157.490
+35200/69092	Loss: 155.106
+38400/69092	Loss: 157.986
+41600/69092	Loss: 156.978
+44800/69092	Loss: 157.706
+48000/69092	Loss: 160.118
+51200/69092	Loss: 157.313
+54400/69092	Loss: 156.847
+57600/69092	Loss: 160.380
+60800/69092	Loss: 159.421
+64000/69092	Loss: 161.294
+67200/69092	Loss: 157.942
+Training time 0:07:30.263099
+Epoch: 24 Average loss: 157.92
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 447)
+0/69092	Loss: 163.860
+3200/69092	Loss: 158.033
+6400/69092	Loss: 158.920
+9600/69092	Loss: 158.141
+12800/69092	Loss: 157.238
+16000/69092	Loss: 158.312
+19200/69092	Loss: 159.095
+22400/69092	Loss: 158.834
+25600/69092	Loss: 157.593
+28800/69092	Loss: 157.538
+32000/69092	Loss: 157.712
+35200/69092	Loss: 156.390
+38400/69092	Loss: 157.083
+41600/69092	Loss: 159.103
+44800/69092	Loss: 159.812
+48000/69092	Loss: 155.763
+51200/69092	Loss: 161.061
+54400/69092	Loss: 155.743
+57600/69092	Loss: 155.257
+60800/69092	Loss: 155.723
+64000/69092	Loss: 155.967
+67200/69092	Loss: 156.284
+Training time 0:07:28.319904
+Epoch: 25 Average loss: 157.58
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 448)
+0/69092	Loss: 157.403
+3200/69092	Loss: 157.724
+6400/69092	Loss: 155.377
+9600/69092	Loss: 157.979
+12800/69092	Loss: 156.250
+16000/69092	Loss: 156.869
+19200/69092	Loss: 159.364
+22400/69092	Loss: 157.592
+25600/69092	Loss: 157.574
+28800/69092	Loss: 159.507
+32000/69092	Loss: 156.364
+35200/69092	Loss: 156.684
+38400/69092	Loss: 161.020
+41600/69092	Loss: 159.087
+44800/69092	Loss: 156.981
+48000/69092	Loss: 156.067
+51200/69092	Loss: 159.865
+54400/69092	Loss: 154.966
+57600/69092	Loss: 157.134
+60800/69092	Loss: 155.247
+64000/69092	Loss: 160.806
+67200/69092	Loss: 157.971
+Training time 0:07:40.149343
+Epoch: 26 Average loss: 157.62
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 449)
+0/69092	Loss: 162.971
+3200/69092	Loss: 157.845
+6400/69092	Loss: 155.922
+9600/69092	Loss: 156.814
+12800/69092	Loss: 158.191
+16000/69092	Loss: 156.917
+19200/69092	Loss: 159.588
+22400/69092	Loss: 160.150
+25600/69092	Loss: 158.296
+28800/69092	Loss: 153.561
+32000/69092	Loss: 157.998
+35200/69092	Loss: 155.695
+38400/69092	Loss: 158.921
+41600/69092	Loss: 158.336
+44800/69092	Loss: 158.163
+48000/69092	Loss: 160.202
+51200/69092	Loss: 156.374
+54400/69092	Loss: 157.517
+57600/69092	Loss: 160.644
+60800/69092	Loss: 156.087
+64000/69092	Loss: 160.525
+67200/69092	Loss: 155.504
+Training time 0:07:30.363968
+Epoch: 27 Average loss: 157.80
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 450)
+0/69092	Loss: 165.755
+3200/69092	Loss: 159.196
+6400/69092	Loss: 160.127
+9600/69092	Loss: 159.290
+12800/69092	Loss: 155.791
+16000/69092	Loss: 156.838
+19200/69092	Loss: 159.976
+22400/69092	Loss: 157.286
+25600/69092	Loss: 156.672
+28800/69092	Loss: 156.827
+32000/69092	Loss: 154.734
+35200/69092	Loss: 157.951
+38400/69092	Loss: 160.563
+41600/69092	Loss: 157.092
+44800/69092	Loss: 157.523
+48000/69092	Loss: 158.848
+51200/69092	Loss: 156.014
+54400/69092	Loss: 158.609
+57600/69092	Loss: 159.528
+60800/69092	Loss: 156.997
+64000/69092	Loss: 156.395
+67200/69092	Loss: 156.661
+Training time 0:07:34.520403
+Epoch: 28 Average loss: 157.69
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 451)
+0/69092	Loss: 160.219
+3200/69092	Loss: 153.065
+6400/69092	Loss: 157.090
+9600/69092	Loss: 159.633
+12800/69092	Loss: 159.466
+16000/69092	Loss: 160.660
+19200/69092	Loss: 157.340
+22400/69092	Loss: 158.569
+25600/69092	Loss: 160.586
+28800/69092	Loss: 157.947
+32000/69092	Loss: 159.776
+35200/69092	Loss: 157.696
+38400/69092	Loss: 158.275
+41600/69092	Loss: 157.770
+44800/69092	Loss: 160.570
+48000/69092	Loss: 159.735
+51200/69092	Loss: 158.444
+54400/69092	Loss: 155.352
+57600/69092	Loss: 155.977
+60800/69092	Loss: 155.812
+64000/69092	Loss: 157.951
+67200/69092	Loss: 154.404
+Training time 0:07:31.941548
+Epoch: 29 Average loss: 157.94
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 452)
+0/69092	Loss: 166.430
+3200/69092	Loss: 159.564
+6400/69092	Loss: 156.582
+9600/69092	Loss: 157.540
+12800/69092	Loss: 158.818
+16000/69092	Loss: 156.869
+19200/69092	Loss: 156.178
+22400/69092	Loss: 158.644
+25600/69092	Loss: 157.656
+28800/69092	Loss: 157.686
+32000/69092	Loss: 158.225
+35200/69092	Loss: 159.664
+38400/69092	Loss: 157.870
+41600/69092	Loss: 157.813
+44800/69092	Loss: 159.590
+48000/69092	Loss: 155.009
+51200/69092	Loss: 156.005
+54400/69092	Loss: 156.799
+57600/69092	Loss: 156.104
+60800/69092	Loss: 157.916
+64000/69092	Loss: 156.787
+67200/69092	Loss: 155.482
+Training time 0:07:36.748072
+Epoch: 30 Average loss: 157.46
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 453)
+0/69092	Loss: 163.325
+3200/69092	Loss: 155.646
+6400/69092	Loss: 157.582
+9600/69092	Loss: 157.121
+12800/69092	Loss: 156.148
+16000/69092	Loss: 159.717
+19200/69092	Loss: 157.148
+22400/69092	Loss: 157.519
+25600/69092	Loss: 159.857
+28800/69092	Loss: 157.745
+32000/69092	Loss: 156.552
+35200/69092	Loss: 158.519
+38400/69092	Loss: 157.368
+41600/69092	Loss: 157.087
+44800/69092	Loss: 155.060
+48000/69092	Loss: 156.740
+51200/69092	Loss: 159.011
+54400/69092	Loss: 161.226
+57600/69092	Loss: 158.500
+60800/69092	Loss: 159.401
+64000/69092	Loss: 157.380
+67200/69092	Loss: 160.290
+Training time 0:07:31.573076
+Epoch: 31 Average loss: 157.89
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 454)
+0/69092	Loss: 146.385
+3200/69092	Loss: 157.417
+6400/69092	Loss: 158.278
+9600/69092	Loss: 157.038
+12800/69092	Loss: 159.594
+16000/69092	Loss: 157.125
+19200/69092	Loss: 157.863
+22400/69092	Loss: 152.382
+25600/69092	Loss: 155.450
+28800/69092	Loss: 156.221
+32000/69092	Loss: 161.784
+35200/69092	Loss: 158.565
+38400/69092	Loss: 161.362
+41600/69092	Loss: 159.096
+44800/69092	Loss: 155.598
+48000/69092	Loss: 159.111
+51200/69092	Loss: 159.060
+54400/69092	Loss: 158.627
+57600/69092	Loss: 157.373
+60800/69092	Loss: 157.541
+64000/69092	Loss: 156.879
+67200/69092	Loss: 154.919
+Training time 0:07:37.412683
+Epoch: 32 Average loss: 157.72
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 455)
+0/69092	Loss: 142.466
+3200/69092	Loss: 152.271
+6400/69092	Loss: 155.401
+9600/69092	Loss: 155.945
+12800/69092	Loss: 154.574
+16000/69092	Loss: 157.240
+19200/69092	Loss: 158.032
+22400/69092	Loss: 160.299
+25600/69092	Loss: 157.174
+28800/69092	Loss: 158.655
+32000/69092	Loss: 158.095
+35200/69092	Loss: 158.948
+38400/69092	Loss: 158.932
+41600/69092	Loss: 159.085
+44800/69092	Loss: 158.413
+48000/69092	Loss: 158.878
+51200/69092	Loss: 158.709
+54400/69092	Loss: 157.626
+57600/69092	Loss: 158.141
+60800/69092	Loss: 159.096
+64000/69092	Loss: 158.316
+67200/69092	Loss: 156.466
+Training time 0:07:27.948784
+Epoch: 33 Average loss: 157.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 456)
+0/69092	Loss: 153.999
+3200/69092	Loss: 156.933
+6400/69092	Loss: 155.182
+9600/69092	Loss: 159.844
+12800/69092	Loss: 154.900
+16000/69092	Loss: 156.357
+19200/69092	Loss: 157.805
+22400/69092	Loss: 156.866
+25600/69092	Loss: 157.166
+28800/69092	Loss: 154.984
+32000/69092	Loss: 157.503
+35200/69092	Loss: 158.644
+38400/69092	Loss: 157.302
+41600/69092	Loss: 158.051
+44800/69092	Loss: 159.428
+48000/69092	Loss: 161.496
+51200/69092	Loss: 158.001
+54400/69092	Loss: 155.704
+57600/69092	Loss: 157.623
+60800/69092	Loss: 158.762
+64000/69092	Loss: 157.340
+67200/69092	Loss: 161.074
+Training time 0:07:25.243557
+Epoch: 34 Average loss: 157.73
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 457)
+0/69092	Loss: 144.385
+3200/69092	Loss: 158.341
+6400/69092	Loss: 157.857
+9600/69092	Loss: 158.972
+12800/69092	Loss: 157.677
+16000/69092	Loss: 155.563
+19200/69092	Loss: 158.630
+22400/69092	Loss: 155.157
+25600/69092	Loss: 157.419
+28800/69092	Loss: 156.716
+32000/69092	Loss: 156.451
+35200/69092	Loss: 158.569
+38400/69092	Loss: 156.660
+41600/69092	Loss: 158.836
+44800/69092	Loss: 156.027
+48000/69092	Loss: 158.701
+51200/69092	Loss: 157.159
+54400/69092	Loss: 159.675
+57600/69092	Loss: 155.961
+60800/69092	Loss: 156.966
+64000/69092	Loss: 160.523
+67200/69092	Loss: 159.242
+Training time 0:07:35.939551
+Epoch: 35 Average loss: 157.67
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 458)
+0/69092	Loss: 164.249
+3200/69092	Loss: 154.462
+6400/69092	Loss: 157.998
+9600/69092	Loss: 163.055
+12800/69092	Loss: 158.905
+16000/69092	Loss: 159.674
+19200/69092	Loss: 159.829
+22400/69092	Loss: 156.884
+25600/69092	Loss: 161.338
+28800/69092	Loss: 156.185
+32000/69092	Loss: 157.947
+35200/69092	Loss: 155.582
+38400/69092	Loss: 158.581
+41600/69092	Loss: 158.427
+44800/69092	Loss: 157.159
+48000/69092	Loss: 155.027
+51200/69092	Loss: 153.522
+54400/69092	Loss: 157.793
+57600/69092	Loss: 159.441
+60800/69092	Loss: 157.273
+64000/69092	Loss: 157.635
+67200/69092	Loss: 159.946
+Training time 0:07:32.633520
+Epoch: 36 Average loss: 157.97
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 459)
+0/69092	Loss: 139.044
+3200/69092	Loss: 157.458
+6400/69092	Loss: 157.206
+9600/69092	Loss: 157.655
+12800/69092	Loss: 159.076
+16000/69092	Loss: 158.025
+19200/69092	Loss: 157.303
+22400/69092	Loss: 159.800
+25600/69092	Loss: 158.122
+28800/69092	Loss: 156.810
+32000/69092	Loss: 156.160
+35200/69092	Loss: 158.712
+38400/69092	Loss: 159.101
+41600/69092	Loss: 159.997
+44800/69092	Loss: 159.593
+48000/69092	Loss: 156.579
+51200/69092	Loss: 157.373
+54400/69092	Loss: 155.787
+57600/69092	Loss: 156.307
+60800/69092	Loss: 155.068
+64000/69092	Loss: 156.597
+67200/69092	Loss: 158.604
+Training time 0:07:33.490087
+Epoch: 37 Average loss: 157.68
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 460)
+0/69092	Loss: 165.975
+3200/69092	Loss: 158.789
+6400/69092	Loss: 156.324
+9600/69092	Loss: 158.873
+12800/69092	Loss: 159.270
+16000/69092	Loss: 158.967
+19200/69092	Loss: 160.449
+22400/69092	Loss: 159.487
+25600/69092	Loss: 157.722
+28800/69092	Loss: 157.806
+32000/69092	Loss: 156.079
+35200/69092	Loss: 161.162
+38400/69092	Loss: 154.722
+41600/69092	Loss: 157.306
+44800/69092	Loss: 155.380
+48000/69092	Loss: 155.809
+51200/69092	Loss: 158.918
+54400/69092	Loss: 157.188
+57600/69092	Loss: 156.670
+60800/69092	Loss: 159.142
+64000/69092	Loss: 158.229
+67200/69092	Loss: 159.156
+Training time 0:07:34.304181
+Epoch: 38 Average loss: 158.05
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 461)
+0/69092	Loss: 163.055
+3200/69092	Loss: 159.943
+6400/69092	Loss: 158.158
+9600/69092	Loss: 156.320
+12800/69092	Loss: 155.420
+16000/69092	Loss: 157.499
+19200/69092	Loss: 158.000
+22400/69092	Loss: 155.748
+25600/69092	Loss: 156.185
+28800/69092	Loss: 156.601
+32000/69092	Loss: 159.267
+35200/69092	Loss: 157.785
+38400/69092	Loss: 160.043
+41600/69092	Loss: 156.823
+44800/69092	Loss: 156.731
+48000/69092	Loss: 156.648
+51200/69092	Loss: 159.410
+54400/69092	Loss: 156.176
+57600/69092	Loss: 156.914
+60800/69092	Loss: 157.496
+64000/69092	Loss: 160.938
+67200/69092	Loss: 158.193
+Training time 0:07:39.282624
+Epoch: 39 Average loss: 157.69
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 462)
+0/69092	Loss: 160.755
+3200/69092	Loss: 159.788
+6400/69092	Loss: 160.640
+9600/69092	Loss: 158.701
+12800/69092	Loss: 155.827
+16000/69092	Loss: 158.481
+19200/69092	Loss: 156.902
+22400/69092	Loss: 158.198
+25600/69092	Loss: 158.487
+28800/69092	Loss: 155.883
+32000/69092	Loss: 157.862
+35200/69092	Loss: 159.911
+38400/69092	Loss: 155.398
+41600/69092	Loss: 156.336
+44800/69092	Loss: 160.418
+48000/69092	Loss: 157.492
+51200/69092	Loss: 156.238
+54400/69092	Loss: 155.950
+57600/69092	Loss: 158.323
+60800/69092	Loss: 158.120
+64000/69092	Loss: 160.272
+67200/69092	Loss: 159.877
+Training time 0:07:42.173467
+Epoch: 40 Average loss: 157.93
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 463)
+0/69092	Loss: 157.864
+3200/69092	Loss: 159.010
+6400/69092	Loss: 155.389
+9600/69092	Loss: 157.847
+12800/69092	Loss: 158.346
+16000/69092	Loss: 157.199
+19200/69092	Loss: 155.473
+22400/69092	Loss: 156.966
+25600/69092	Loss: 158.426
+28800/69092	Loss: 153.900
+32000/69092	Loss: 155.413
+35200/69092	Loss: 157.920
+38400/69092	Loss: 156.925
+41600/69092	Loss: 159.595
+44800/69092	Loss: 160.514
+48000/69092	Loss: 161.608
+51200/69092	Loss: 161.725
+54400/69092	Loss: 155.291
+57600/69092	Loss: 159.972
+60800/69092	Loss: 155.776
+64000/69092	Loss: 158.482
+67200/69092	Loss: 158.647
+Training time 0:07:31.080061
+Epoch: 41 Average loss: 157.84
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 464)
+0/69092	Loss: 198.417
+3200/69092	Loss: 156.595
+6400/69092	Loss: 160.298
+9600/69092	Loss: 156.485
+12800/69092	Loss: 161.984
+16000/69092	Loss: 157.696
+19200/69092	Loss: 162.508
+22400/69092	Loss: 157.214
+25600/69092	Loss: 156.766
+28800/69092	Loss: 157.453
+32000/69092	Loss: 156.545
+35200/69092	Loss: 155.983
+38400/69092	Loss: 158.753
+41600/69092	Loss: 155.557
+44800/69092	Loss: 162.291
+48000/69092	Loss: 157.190
+51200/69092	Loss: 159.337
+54400/69092	Loss: 153.634
+57600/69092	Loss: 155.849
+60800/69092	Loss: 153.693
+64000/69092	Loss: 158.057
+67200/69092	Loss: 159.184
+Training time 0:07:32.633305
+Epoch: 42 Average loss: 157.88
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 465)
+0/69092	Loss: 144.310
+3200/69092	Loss: 155.938
+6400/69092	Loss: 157.943
+9600/69092	Loss: 155.812
+12800/69092	Loss: 157.117
+16000/69092	Loss: 159.440
+19200/69092	Loss: 156.132
+22400/69092	Loss: 158.839
+25600/69092	Loss: 156.862
+28800/69092	Loss: 158.235
+32000/69092	Loss: 160.057
+35200/69092	Loss: 157.470
+38400/69092	Loss: 155.689
+41600/69092	Loss: 156.034
+44800/69092	Loss: 158.062
+48000/69092	Loss: 157.677
+51200/69092	Loss: 156.948
+54400/69092	Loss: 156.635
+57600/69092	Loss: 160.083
+60800/69092	Loss: 160.143
+64000/69092	Loss: 159.007
+67200/69092	Loss: 156.043
+Training time 0:07:28.668771
+Epoch: 43 Average loss: 157.67
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 466)
+0/69092	Loss: 143.828
+3200/69092	Loss: 155.298
+6400/69092	Loss: 155.176
+9600/69092	Loss: 158.871
+12800/69092	Loss: 159.521
+16000/69092	Loss: 157.098
+19200/69092	Loss: 158.389
+22400/69092	Loss: 158.505
+25600/69092	Loss: 156.950
+28800/69092	Loss: 158.765
+32000/69092	Loss: 162.927
+35200/69092	Loss: 155.623
+38400/69092	Loss: 157.428
+41600/69092	Loss: 159.964
+44800/69092	Loss: 155.743
+48000/69092	Loss: 158.573
+51200/69092	Loss: 161.717
+54400/69092	Loss: 155.745
+57600/69092	Loss: 155.543
+60800/69092	Loss: 158.965
+64000/69092	Loss: 156.742
+67200/69092	Loss: 156.293
+Training time 0:07:30.555282
+Epoch: 44 Average loss: 157.79
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 467)
+0/69092	Loss: 167.066
+3200/69092	Loss: 155.951
+6400/69092	Loss: 154.763
+9600/69092	Loss: 156.667
+12800/69092	Loss: 157.389
+16000/69092	Loss: 157.016
+19200/69092	Loss: 158.355
+22400/69092	Loss: 160.057
+25600/69092	Loss: 163.740
+28800/69092	Loss: 157.719
+32000/69092	Loss: 157.181
+35200/69092	Loss: 158.170
+38400/69092	Loss: 156.384
+41600/69092	Loss: 158.605
+44800/69092	Loss: 159.870
+48000/69092	Loss: 159.804
+51200/69092	Loss: 154.350
+54400/69092	Loss: 155.310
+57600/69092	Loss: 158.728
+60800/69092	Loss: 159.856
+64000/69092	Loss: 159.515
+67200/69092	Loss: 156.412
+Training time 0:07:28.581745
+Epoch: 45 Average loss: 157.83
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 468)
+0/69092	Loss: 165.600
+3200/69092	Loss: 159.889
+6400/69092	Loss: 158.593
+9600/69092	Loss: 157.733
+12800/69092	Loss: 157.333
+16000/69092	Loss: 156.285
+19200/69092	Loss: 159.797
+22400/69092	Loss: 158.490
+25600/69092	Loss: 158.735
+28800/69092	Loss: 156.754
+32000/69092	Loss: 156.805
+35200/69092	Loss: 156.848
+38400/69092	Loss: 159.611
+41600/69092	Loss: 156.584
+44800/69092	Loss: 157.814
+48000/69092	Loss: 156.737
+51200/69092	Loss: 157.790
+54400/69092	Loss: 155.975
+57600/69092	Loss: 159.745
+60800/69092	Loss: 161.202
+64000/69092	Loss: 155.437
+67200/69092	Loss: 157.135
+Training time 0:07:30.221401
+Epoch: 46 Average loss: 157.89
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 469)
+0/69092	Loss: 159.077
+3200/69092	Loss: 159.469
+6400/69092	Loss: 158.697
+9600/69092	Loss: 157.568
+12800/69092	Loss: 157.646
+16000/69092	Loss: 161.394
+19200/69092	Loss: 160.164
+22400/69092	Loss: 153.992
+25600/69092	Loss: 158.537
+28800/69092	Loss: 157.216
+32000/69092	Loss: 157.256
+35200/69092	Loss: 156.997
+38400/69092	Loss: 159.490
+41600/69092	Loss: 156.580
+44800/69092	Loss: 159.537
+48000/69092	Loss: 159.586
+51200/69092	Loss: 155.126
+54400/69092	Loss: 157.433
+57600/69092	Loss: 155.467
+60800/69092	Loss: 160.119
+64000/69092	Loss: 157.282
+67200/69092	Loss: 154.882
+Training time 0:07:49.702594
+Epoch: 47 Average loss: 157.88
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 470)
+0/69092	Loss: 159.025
+3200/69092	Loss: 155.234
+6400/69092	Loss: 157.276
+9600/69092	Loss: 159.072
+12800/69092	Loss: 157.287
+16000/69092	Loss: 157.078
+19200/69092	Loss: 157.664
+22400/69092	Loss: 158.371
+25600/69092	Loss: 156.353
+28800/69092	Loss: 160.357
+32000/69092	Loss: 161.027
+35200/69092	Loss: 155.301
+38400/69092	Loss: 158.415
+41600/69092	Loss: 156.501
+44800/69092	Loss: 158.796
+48000/69092	Loss: 156.372
+51200/69092	Loss: 155.284
+54400/69092	Loss: 156.160
+57600/69092	Loss: 159.940
+60800/69092	Loss: 158.967
+64000/69092	Loss: 161.591
+67200/69092	Loss: 159.111
+Training time 0:08:29.306800
+Epoch: 48 Average loss: 157.87
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 471)
+0/69092	Loss: 157.146
+3200/69092	Loss: 155.314
+6400/69092	Loss: 157.281
+9600/69092	Loss: 157.749
+12800/69092	Loss: 155.575
+16000/69092	Loss: 157.257
+19200/69092	Loss: 157.824
+22400/69092	Loss: 158.352
+25600/69092	Loss: 157.666
+28800/69092	Loss: 159.461
+32000/69092	Loss: 155.983
+35200/69092	Loss: 153.892
+38400/69092	Loss: 156.310
+41600/69092	Loss: 158.427
+44800/69092	Loss: 158.951
+48000/69092	Loss: 160.813
+51200/69092	Loss: 155.588
+54400/69092	Loss: 161.481
+57600/69092	Loss: 155.487
+60800/69092	Loss: 159.400
+64000/69092	Loss: 157.534
+67200/69092	Loss: 160.670
+Training time 0:07:29.275441
+Epoch: 49 Average loss: 157.77
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 472)
+0/69092	Loss: 172.591
+3200/69092	Loss: 155.204
+6400/69092	Loss: 158.104
+9600/69092	Loss: 159.351
+12800/69092	Loss: 154.560
+16000/69092	Loss: 155.691
+19200/69092	Loss: 158.396
+22400/69092	Loss: 156.553
+25600/69092	Loss: 157.996
+28800/69092	Loss: 158.379
+32000/69092	Loss: 156.720
+35200/69092	Loss: 161.390
+38400/69092	Loss: 158.068
+41600/69092	Loss: 157.631
+44800/69092	Loss: 155.707
+48000/69092	Loss: 160.336
+51200/69092	Loss: 158.281
+54400/69092	Loss: 158.087
+57600/69092	Loss: 158.537
+60800/69092	Loss: 157.649
+64000/69092	Loss: 156.861
+67200/69092	Loss: 155.258
+Training time 0:07:29.743816
+Epoch: 50 Average loss: 157.67
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 473)
+0/69092	Loss: 155.477
+3200/69092	Loss: 157.979
+6400/69092	Loss: 159.863
+9600/69092	Loss: 160.009
+12800/69092	Loss: 158.330
+16000/69092	Loss: 153.192
+19200/69092	Loss: 157.508
+22400/69092	Loss: 157.419
+25600/69092	Loss: 158.850
+28800/69092	Loss: 158.648
+32000/69092	Loss: 158.057
+35200/69092	Loss: 156.817
+38400/69092	Loss: 159.275
+41600/69092	Loss: 160.543
+44800/69092	Loss: 154.189
+48000/69092	Loss: 159.542
+51200/69092	Loss: 156.242
+54400/69092	Loss: 157.000
+57600/69092	Loss: 158.416
+60800/69092	Loss: 154.753
+64000/69092	Loss: 157.756
+67200/69092	Loss: 159.783
+Training time 0:07:36.223022
+Epoch: 51 Average loss: 157.72
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 474)
+0/69092	Loss: 165.735
+3200/69092	Loss: 157.595
+6400/69092	Loss: 156.003
+9600/69092	Loss: 155.961
+12800/69092	Loss: 158.992
+16000/69092	Loss: 159.623
+19200/69092	Loss: 155.420
+22400/69092	Loss: 151.796
+25600/69092	Loss: 156.521
+28800/69092	Loss: 158.757
+32000/69092	Loss: 157.291
+35200/69092	Loss: 158.200
+38400/69092	Loss: 157.655
+41600/69092	Loss: 157.352
+44800/69092	Loss: 157.901
+48000/69092	Loss: 160.207
+51200/69092	Loss: 158.081
+54400/69092	Loss: 160.122
+57600/69092	Loss: 159.104
+60800/69092	Loss: 158.453
+64000/69092	Loss: 157.288
+67200/69092	Loss: 159.032
+Training time 0:07:32.174426
+Epoch: 52 Average loss: 157.78
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 475)
+0/69092	Loss: 167.347
+3200/69092	Loss: 161.563
+6400/69092	Loss: 156.677
+9600/69092	Loss: 160.996
+12800/69092	Loss: 160.230
+16000/69092	Loss: 158.322
+19200/69092	Loss: 159.476
+22400/69092	Loss: 155.623
+25600/69092	Loss: 155.243
+28800/69092	Loss: 157.815
+32000/69092	Loss: 159.040
+35200/69092	Loss: 158.070
+38400/69092	Loss: 156.740
+41600/69092	Loss: 156.291
+44800/69092	Loss: 157.158
+48000/69092	Loss: 158.305
+51200/69092	Loss: 156.913
+54400/69092	Loss: 157.220
+57600/69092	Loss: 158.817
+60800/69092	Loss: 157.658
+64000/69092	Loss: 156.407
+67200/69092	Loss: 156.897
+Training time 0:07:31.289501
+Epoch: 53 Average loss: 157.88
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 476)
+0/69092	Loss: 158.875
+3200/69092	Loss: 155.913
+6400/69092	Loss: 158.100
+9600/69092	Loss: 158.476
+12800/69092	Loss: 158.445
+16000/69092	Loss: 152.969
+19200/69092	Loss: 158.938
+22400/69092	Loss: 156.929
+25600/69092	Loss: 156.582
+28800/69092	Loss: 159.499
+32000/69092	Loss: 158.120
+35200/69092	Loss: 156.898
+38400/69092	Loss: 157.154
+41600/69092	Loss: 155.716
+44800/69092	Loss: 159.241
+48000/69092	Loss: 158.169
+51200/69092	Loss: 156.931
+54400/69092	Loss: 158.298
+57600/69092	Loss: 157.166
+60800/69092	Loss: 159.364
+64000/69092	Loss: 159.900
+67200/69092	Loss: 159.146
+Training time 0:07:36.089106
+Epoch: 54 Average loss: 157.66
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 477)
+0/69092	Loss: 159.011
+3200/69092	Loss: 157.986
+6400/69092	Loss: 157.676
+9600/69092	Loss: 159.503
+12800/69092	Loss: 157.431
+16000/69092	Loss: 156.340
+19200/69092	Loss: 157.077
+22400/69092	Loss: 155.529
+25600/69092	Loss: 159.662
+28800/69092	Loss: 157.499
+32000/69092	Loss: 156.259
+35200/69092	Loss: 157.602
+38400/69092	Loss: 160.567
+41600/69092	Loss: 157.208
+44800/69092	Loss: 158.421
+48000/69092	Loss: 159.192
+51200/69092	Loss: 155.303
+54400/69092	Loss: 157.020
+57600/69092	Loss: 158.002
+60800/69092	Loss: 159.252
+64000/69092	Loss: 156.877
+67200/69092	Loss: 160.496
+Training time 0:07:29.785545
+Epoch: 55 Average loss: 157.79
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 478)
+0/69092	Loss: 151.712
+3200/69092	Loss: 158.548
+6400/69092	Loss: 156.886
+9600/69092	Loss: 157.200
+12800/69092	Loss: 159.449
+16000/69092	Loss: 157.285
+19200/69092	Loss: 158.016
+22400/69092	Loss: 157.836
+25600/69092	Loss: 157.994
+28800/69092	Loss: 157.491
+32000/69092	Loss: 161.676
+35200/69092	Loss: 161.374
+38400/69092	Loss: 155.570
+41600/69092	Loss: 159.026
+44800/69092	Loss: 157.879
+48000/69092	Loss: 155.676
+51200/69092	Loss: 156.321
+54400/69092	Loss: 157.255
+57600/69092	Loss: 158.790
+60800/69092	Loss: 157.885
+64000/69092	Loss: 159.198
+67200/69092	Loss: 158.576
+Training time 0:07:36.019956
+Epoch: 56 Average loss: 158.04
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 479)
+0/69092	Loss: 156.696
+3200/69092	Loss: 157.496
+6400/69092	Loss: 158.474
+9600/69092	Loss: 158.264
+12800/69092	Loss: 155.566
+16000/69092	Loss: 156.643
+19200/69092	Loss: 157.793
+22400/69092	Loss: 158.285
+25600/69092	Loss: 158.708
+28800/69092	Loss: 159.137
+32000/69092	Loss: 156.195
+35200/69092	Loss: 158.831
+38400/69092	Loss: 159.532
+41600/69092	Loss: 156.902
+44800/69092	Loss: 158.801
+48000/69092	Loss: 156.933
+51200/69092	Loss: 159.086
+54400/69092	Loss: 155.272
+57600/69092	Loss: 160.956
+60800/69092	Loss: 157.412
+64000/69092	Loss: 158.223
+67200/69092	Loss: 157.163
+Training time 0:07:37.716575
+Epoch: 57 Average loss: 157.90
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 480)
+0/69092	Loss: 148.896
+3200/69092	Loss: 157.887
+6400/69092	Loss: 157.917
+9600/69092	Loss: 157.860
+12800/69092	Loss: 157.949
+16000/69092	Loss: 157.004
+19200/69092	Loss: 157.736
+22400/69092	Loss: 160.963
+25600/69092	Loss: 160.660
+28800/69092	Loss: 158.485
+32000/69092	Loss: 157.079
+35200/69092	Loss: 155.928
+38400/69092	Loss: 154.981
+41600/69092	Loss: 159.016
+44800/69092	Loss: 157.633
+48000/69092	Loss: 158.116
+51200/69092	Loss: 155.318
+54400/69092	Loss: 157.204
+57600/69092	Loss: 153.138
+60800/69092	Loss: 159.904
+64000/69092	Loss: 155.828
+67200/69092	Loss: 156.614
+Training time 0:07:28.466256
+Epoch: 58 Average loss: 157.53
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 481)
+0/69092	Loss: 178.673
+3200/69092	Loss: 155.829
+6400/69092	Loss: 156.476
+9600/69092	Loss: 156.880
+12800/69092	Loss: 155.676
+16000/69092	Loss: 158.761
+19200/69092	Loss: 161.487
+22400/69092	Loss: 158.028
+25600/69092	Loss: 157.643
+28800/69092	Loss: 160.287
+32000/69092	Loss: 159.935
+35200/69092	Loss: 157.920
+38400/69092	Loss: 158.957
+41600/69092	Loss: 157.600
+44800/69092	Loss: 155.572
+48000/69092	Loss: 159.200
+51200/69092	Loss: 157.740
+54400/69092	Loss: 157.863
+57600/69092	Loss: 157.484
+60800/69092	Loss: 156.703
+64000/69092	Loss: 159.493
+67200/69092	Loss: 158.097
+Training time 0:07:31.131752
+Epoch: 59 Average loss: 157.97
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 482)
+0/69092	Loss: 151.102
+3200/69092	Loss: 157.276
+6400/69092	Loss: 159.549
+9600/69092	Loss: 157.093
+12800/69092	Loss: 159.041
+16000/69092	Loss: 161.438
+19200/69092	Loss: 158.270
+22400/69092	Loss: 158.304
+25600/69092	Loss: 157.209
+28800/69092	Loss: 157.592
+32000/69092	Loss: 156.703
+35200/69092	Loss: 159.556
+38400/69092	Loss: 157.933
+41600/69092	Loss: 158.015
+44800/69092	Loss: 158.100
+48000/69092	Loss: 157.244
+51200/69092	Loss: 158.557
+54400/69092	Loss: 156.265
+57600/69092	Loss: 156.502
+60800/69092	Loss: 157.331
+64000/69092	Loss: 156.732
+67200/69092	Loss: 157.119
+Training time 0:07:40.180973
+Epoch: 60 Average loss: 157.89
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 483)
+0/69092	Loss: 146.360
+3200/69092	Loss: 157.591
+6400/69092	Loss: 156.830
+9600/69092	Loss: 156.833
+12800/69092	Loss: 157.044
+16000/69092	Loss: 154.918
+19200/69092	Loss: 154.866
+22400/69092	Loss: 156.445
+25600/69092	Loss: 158.546
+28800/69092	Loss: 160.042
+32000/69092	Loss: 161.277
+35200/69092	Loss: 155.353
+38400/69092	Loss: 157.046
+41600/69092	Loss: 158.467
+44800/69092	Loss: 157.417
+48000/69092	Loss: 159.266
+51200/69092	Loss: 155.781
+54400/69092	Loss: 156.215
+57600/69092	Loss: 156.808
+60800/69092	Loss: 157.807
+64000/69092	Loss: 159.583
+67200/69092	Loss: 159.790
+Training time 0:08:00.641862
+Epoch: 61 Average loss: 157.53
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 484)
+0/69092	Loss: 167.018
+3200/69092	Loss: 156.631
+6400/69092	Loss: 158.543
+9600/69092	Loss: 157.933
+12800/69092	Loss: 158.797
+16000/69092	Loss: 156.845
+19200/69092	Loss: 156.346
+22400/69092	Loss: 160.184
+25600/69092	Loss: 156.655
+28800/69092	Loss: 159.033
+32000/69092	Loss: 159.177
+35200/69092	Loss: 157.871
+38400/69092	Loss: 157.949
+41600/69092	Loss: 159.109
+44800/69092	Loss: 157.267
+48000/69092	Loss: 155.324
+51200/69092	Loss: 157.927
+54400/69092	Loss: 159.365
+57600/69092	Loss: 156.606
+60800/69092	Loss: 158.809
+64000/69092	Loss: 158.727
+67200/69092	Loss: 155.436
+Training time 0:07:30.974796
+Epoch: 62 Average loss: 157.91
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 485)
+0/69092	Loss: 155.326
+3200/69092	Loss: 156.929
+6400/69092	Loss: 155.049
+9600/69092	Loss: 158.304
+12800/69092	Loss: 163.425
+16000/69092	Loss: 156.725
+19200/69092	Loss: 156.249
+22400/69092	Loss: 160.923
+25600/69092	Loss: 155.296
+28800/69092	Loss: 159.084
+32000/69092	Loss: 156.402
+35200/69092	Loss: 157.944
+38400/69092	Loss: 158.721
+41600/69092	Loss: 155.966
+44800/69092	Loss: 158.320
+48000/69092	Loss: 158.684
+51200/69092	Loss: 159.604
+54400/69092	Loss: 156.545
+57600/69092	Loss: 159.011
+60800/69092	Loss: 156.561
+64000/69092	Loss: 158.070
+67200/69092	Loss: 154.584
+Training time 0:08:09.582895
+Epoch: 63 Average loss: 157.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 486)
+0/69092	Loss: 168.420
+3200/69092	Loss: 156.431
+6400/69092	Loss: 157.543
+9600/69092	Loss: 158.296
+12800/69092	Loss: 156.973
+16000/69092	Loss: 156.646
+19200/69092	Loss: 157.887
+22400/69092	Loss: 159.200
+25600/69092	Loss: 157.018
+28800/69092	Loss: 155.296
+32000/69092	Loss: 159.029
+35200/69092	Loss: 157.972
+38400/69092	Loss: 159.447
+41600/69092	Loss: 157.054
+44800/69092	Loss: 156.327
+48000/69092	Loss: 160.036
+51200/69092	Loss: 157.215
+54400/69092	Loss: 161.374
+57600/69092	Loss: 158.391
+60800/69092	Loss: 155.169
+64000/69092	Loss: 157.558
+67200/69092	Loss: 153.867
+Training time 0:07:30.493331
+Epoch: 64 Average loss: 157.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 487)
+0/69092	Loss: 144.962
+3200/69092	Loss: 155.772
+6400/69092	Loss: 159.550
+9600/69092	Loss: 157.597
+12800/69092	Loss: 157.691
+16000/69092	Loss: 156.698
+19200/69092	Loss: 158.598
+22400/69092	Loss: 157.551
+25600/69092	Loss: 156.226
+28800/69092	Loss: 158.912
+32000/69092	Loss: 159.055
+35200/69092	Loss: 158.394
+38400/69092	Loss: 158.601
+41600/69092	Loss: 157.803
+44800/69092	Loss: 159.575
+48000/69092	Loss: 156.542
+51200/69092	Loss: 156.270
+54400/69092	Loss: 159.968
+57600/69092	Loss: 158.202
+60800/69092	Loss: 156.081
+64000/69092	Loss: 156.754
+67200/69092	Loss: 156.584
+Training time 0:07:32.118855
+Epoch: 65 Average loss: 157.75
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 488)
+0/69092	Loss: 143.323
+3200/69092	Loss: 158.589
+6400/69092	Loss: 153.716
+9600/69092	Loss: 156.417
+12800/69092	Loss: 158.518
+16000/69092	Loss: 158.377
+19200/69092	Loss: 159.547
+22400/69092	Loss: 155.179
+25600/69092	Loss: 154.204
+28800/69092	Loss: 157.441
+32000/69092	Loss: 157.618
+35200/69092	Loss: 158.159
+38400/69092	Loss: 158.831
+41600/69092	Loss: 159.529
+44800/69092	Loss: 159.033
+48000/69092	Loss: 160.695
+51200/69092	Loss: 157.434
+54400/69092	Loss: 156.107
+57600/69092	Loss: 156.562
+60800/69092	Loss: 160.719
+64000/69092	Loss: 158.900
+67200/69092	Loss: 158.112
+Training time 0:07:32.329658
+Epoch: 66 Average loss: 157.75
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 489)
+0/69092	Loss: 163.275
+3200/69092	Loss: 159.104
+6400/69092	Loss: 159.158
+9600/69092	Loss: 161.419
+12800/69092	Loss: 157.232
+16000/69092	Loss: 157.068
+19200/69092	Loss: 156.820
+22400/69092	Loss: 155.693
+25600/69092	Loss: 158.043
+28800/69092	Loss: 158.508
+32000/69092	Loss: 158.496
+35200/69092	Loss: 156.385
+38400/69092	Loss: 157.975
+41600/69092	Loss: 158.994
+44800/69092	Loss: 155.701
+48000/69092	Loss: 158.541
+51200/69092	Loss: 158.515
+54400/69092	Loss: 160.072
+57600/69092	Loss: 158.282
+60800/69092	Loss: 155.165
+64000/69092	Loss: 158.147
+67200/69092	Loss: 156.474
+Training time 0:07:33.695244
+Epoch: 67 Average loss: 157.85
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 490)
+0/69092	Loss: 183.316
+3200/69092	Loss: 157.776
+6400/69092	Loss: 159.626
+9600/69092	Loss: 159.549
+12800/69092	Loss: 156.583
+16000/69092	Loss: 156.609
+19200/69092	Loss: 157.547
+22400/69092	Loss: 159.544
+25600/69092	Loss: 156.285
+28800/69092	Loss: 158.823
+32000/69092	Loss: 158.139
+35200/69092	Loss: 157.351
+38400/69092	Loss: 158.399
+41600/69092	Loss: 154.968
+44800/69092	Loss: 158.081
+48000/69092	Loss: 158.903
+51200/69092	Loss: 155.875
+54400/69092	Loss: 156.611
+57600/69092	Loss: 158.537
+60800/69092	Loss: 159.901
+64000/69092	Loss: 158.478
+67200/69092	Loss: 155.375
+Training time 0:07:30.351889
+Epoch: 68 Average loss: 157.79
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 491)
+0/69092	Loss: 156.753
+3200/69092	Loss: 157.296
+6400/69092	Loss: 157.190
+9600/69092	Loss: 157.249
+12800/69092	Loss: 157.096
+16000/69092	Loss: 156.875
+19200/69092	Loss: 156.136
+22400/69092	Loss: 155.847
+25600/69092	Loss: 156.994
+28800/69092	Loss: 156.398
+32000/69092	Loss: 157.977
+35200/69092	Loss: 156.912
+38400/69092	Loss: 157.829
+41600/69092	Loss: 157.409
+44800/69092	Loss: 161.576
+48000/69092	Loss: 159.671
+51200/69092	Loss: 156.388
+54400/69092	Loss: 157.143
+57600/69092	Loss: 160.184
+60800/69092	Loss: 157.542
+64000/69092	Loss: 156.720
+67200/69092	Loss: 157.236
+Training time 0:07:27.149328
+Epoch: 69 Average loss: 157.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 492)
+0/69092	Loss: 146.036
+3200/69092	Loss: 158.580
+6400/69092	Loss: 160.748
+9600/69092	Loss: 158.193
+12800/69092	Loss: 156.470
+16000/69092	Loss: 161.262
+19200/69092	Loss: 158.562
+22400/69092	Loss: 159.261
+25600/69092	Loss: 160.112
+28800/69092	Loss: 156.451
+32000/69092	Loss: 156.681
+35200/69092	Loss: 158.118
+38400/69092	Loss: 156.407
+41600/69092	Loss: 158.808
+44800/69092	Loss: 157.607
+48000/69092	Loss: 154.996
+51200/69092	Loss: 157.781
+54400/69092	Loss: 158.173
+57600/69092	Loss: 158.151
+60800/69092	Loss: 157.266
+64000/69092	Loss: 155.779
+67200/69092	Loss: 157.892
+Training time 0:07:34.042645
+Epoch: 70 Average loss: 157.92
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 493)
+0/69092	Loss: 148.045
+3200/69092	Loss: 159.902
+6400/69092	Loss: 159.570
+9600/69092	Loss: 159.575
+12800/69092	Loss: 158.521
+16000/69092	Loss: 156.979
+19200/69092	Loss: 158.946
+22400/69092	Loss: 157.023
+25600/69092	Loss: 157.809
+28800/69092	Loss: 158.470
+32000/69092	Loss: 156.692
+35200/69092	Loss: 156.278
+38400/69092	Loss: 155.847
+41600/69092	Loss: 156.178
+44800/69092	Loss: 157.457
+48000/69092	Loss: 157.843
+51200/69092	Loss: 154.199
+54400/69092	Loss: 157.615
+57600/69092	Loss: 158.812
+60800/69092	Loss: 156.712
+64000/69092	Loss: 156.000
+67200/69092	Loss: 156.968
+Training time 0:07:30.942015
+Epoch: 71 Average loss: 157.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 494)
+0/69092	Loss: 193.557
+3200/69092	Loss: 158.581
+6400/69092	Loss: 159.960
+9600/69092	Loss: 158.709
+12800/69092	Loss: 157.749
+16000/69092	Loss: 155.311
+19200/69092	Loss: 157.527
+22400/69092	Loss: 155.882
+25600/69092	Loss: 154.842
+28800/69092	Loss: 156.252
+32000/69092	Loss: 157.488
+35200/69092	Loss: 156.919
+38400/69092	Loss: 159.173
+41600/69092	Loss: 158.074
+44800/69092	Loss: 158.017
+48000/69092	Loss: 161.706
+51200/69092	Loss: 156.514
+54400/69092	Loss: 157.500
+57600/69092	Loss: 157.416
+60800/69092	Loss: 157.818
+64000/69092	Loss: 156.300
+67200/69092	Loss: 159.368
+Training time 0:07:32.607108
+Epoch: 72 Average loss: 157.68
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 495)
+0/69092	Loss: 177.926
+3200/69092	Loss: 157.066
+6400/69092	Loss: 159.206
+9600/69092	Loss: 154.233
+12800/69092	Loss: 159.151
+16000/69092	Loss: 156.032
+19200/69092	Loss: 158.726
+22400/69092	Loss: 159.773
+25600/69092	Loss: 158.140
+28800/69092	Loss: 159.467
+32000/69092	Loss: 154.816
+35200/69092	Loss: 157.403
+38400/69092	Loss: 159.988
+41600/69092	Loss: 156.329
+44800/69092	Loss: 154.020
+48000/69092	Loss: 156.968
+51200/69092	Loss: 156.505
+54400/69092	Loss: 157.025
+57600/69092	Loss: 159.158
+60800/69092	Loss: 158.788
+64000/69092	Loss: 160.673
+67200/69092	Loss: 159.491
+Training time 0:07:28.142897
+Epoch: 73 Average loss: 157.69
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 496)
+0/69092	Loss: 160.803
+3200/69092	Loss: 155.213
+6400/69092	Loss: 156.567
+9600/69092	Loss: 159.224
+12800/69092	Loss: 157.978
+16000/69092	Loss: 156.166
+19200/69092	Loss: 157.324
+22400/69092	Loss: 160.065
+25600/69092	Loss: 158.215
+28800/69092	Loss: 156.018
+32000/69092	Loss: 156.612
+35200/69092	Loss: 159.352
+38400/69092	Loss: 159.471
+41600/69092	Loss: 154.980
+44800/69092	Loss: 156.727
+48000/69092	Loss: 156.928
+51200/69092	Loss: 159.177
+54400/69092	Loss: 159.593
+57600/69092	Loss: 158.898
+60800/69092	Loss: 156.536
+64000/69092	Loss: 158.953
+67200/69092	Loss: 159.860
+Training time 0:07:39.044267
+Epoch: 74 Average loss: 157.76
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 497)
+0/69092	Loss: 153.554
+3200/69092	Loss: 157.763
+6400/69092	Loss: 159.655
+9600/69092	Loss: 158.467
+12800/69092	Loss: 155.612
+16000/69092	Loss: 155.849
+19200/69092	Loss: 157.095
+22400/69092	Loss: 160.706
+25600/69092	Loss: 157.661
+28800/69092	Loss: 157.534
+32000/69092	Loss: 156.247
+35200/69092	Loss: 156.362
+38400/69092	Loss: 159.599
+41600/69092	Loss: 157.146
+44800/69092	Loss: 159.098
+48000/69092	Loss: 156.492
+51200/69092	Loss: 156.702
+54400/69092	Loss: 155.818
+57600/69092	Loss: 160.725
+60800/69092	Loss: 157.031
+64000/69092	Loss: 157.832
+67200/69092	Loss: 156.698
+Training time 0:07:26.504107
+Epoch: 75 Average loss: 157.66
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 498)
+0/69092	Loss: 161.422
+3200/69092	Loss: 157.520
+6400/69092	Loss: 156.469
+9600/69092	Loss: 157.827
+12800/69092	Loss: 159.594
+16000/69092	Loss: 158.252
+19200/69092	Loss: 158.536
+22400/69092	Loss: 156.967
+25600/69092	Loss: 159.976
+28800/69092	Loss: 156.504
+32000/69092	Loss: 157.253
+35200/69092	Loss: 156.574
+38400/69092	Loss: 158.118
+41600/69092	Loss: 155.130
+44800/69092	Loss: 158.647
+48000/69092	Loss: 154.845
+51200/69092	Loss: 160.102
+54400/69092	Loss: 157.422
+57600/69092	Loss: 159.893
+60800/69092	Loss: 157.545
+64000/69092	Loss: 156.112
+67200/69092	Loss: 158.826
+Training time 0:07:32.783897
+Epoch: 76 Average loss: 157.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 499)
+0/69092	Loss: 177.210
+3200/69092	Loss: 158.884
+6400/69092	Loss: 155.924
+9600/69092	Loss: 156.157
+12800/69092	Loss: 158.097
+16000/69092	Loss: 156.407
+19200/69092	Loss: 156.113
+22400/69092	Loss: 158.193
+25600/69092	Loss: 158.247
+28800/69092	Loss: 158.418
+32000/69092	Loss: 155.925
+35200/69092	Loss: 160.295
+38400/69092	Loss: 158.446
+41600/69092	Loss: 156.533
+44800/69092	Loss: 154.964
+48000/69092	Loss: 159.130
+51200/69092	Loss: 157.237
+54400/69092	Loss: 157.130
+57600/69092	Loss: 158.043
+60800/69092	Loss: 156.191
+64000/69092	Loss: 157.533
+67200/69092	Loss: 162.101
+Training time 0:07:34.133075
+Epoch: 77 Average loss: 157.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 500)
+0/69092	Loss: 153.853
+3200/69092	Loss: 156.814
+6400/69092	Loss: 157.885
+9600/69092	Loss: 157.709
+12800/69092	Loss: 155.759
+16000/69092	Loss: 157.194
+19200/69092	Loss: 158.385
+22400/69092	Loss: 158.610
+25600/69092	Loss: 159.825
+28800/69092	Loss: 157.883
+32000/69092	Loss: 156.003
+35200/69092	Loss: 156.775
+38400/69092	Loss: 157.722
+41600/69092	Loss: 158.185
+44800/69092	Loss: 159.210
+48000/69092	Loss: 158.070
+51200/69092	Loss: 156.546
+54400/69092	Loss: 155.647
+57600/69092	Loss: 157.785
+60800/69092	Loss: 157.660
+64000/69092	Loss: 157.465
+67200/69092	Loss: 159.105
+Training time 0:07:32.954687
+Epoch: 78 Average loss: 157.67
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 501)
+0/69092	Loss: 154.571
+3200/69092	Loss: 155.958
+6400/69092	Loss: 159.548
+9600/69092	Loss: 158.884
+12800/69092	Loss: 155.646
+16000/69092	Loss: 154.697
+19200/69092	Loss: 157.752
+22400/69092	Loss: 157.124
+25600/69092	Loss: 157.724
+28800/69092	Loss: 157.061
+32000/69092	Loss: 155.054
+35200/69092	Loss: 160.488
+38400/69092	Loss: 157.938
+41600/69092	Loss: 156.897
+44800/69092	Loss: 160.877
+48000/69092	Loss: 156.670
+51200/69092	Loss: 159.104
+54400/69092	Loss: 157.708
+57600/69092	Loss: 160.187
+60800/69092	Loss: 156.840
+64000/69092	Loss: 156.505
+67200/69092	Loss: 159.275
+Training time 0:07:29.071097
+Epoch: 79 Average loss: 157.72
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 502)
+0/69092	Loss: 171.694
+3200/69092	Loss: 157.378
+6400/69092	Loss: 158.375
+9600/69092	Loss: 160.253
+12800/69092	Loss: 156.585
+16000/69092	Loss: 157.419
+19200/69092	Loss: 156.079
+22400/69092	Loss: 157.016
+25600/69092	Loss: 157.493
+28800/69092	Loss: 158.673
+32000/69092	Loss: 154.919
+35200/69092	Loss: 159.952
+38400/69092	Loss: 156.969
+41600/69092	Loss: 157.544
+44800/69092	Loss: 158.691
+48000/69092	Loss: 156.667
+51200/69092	Loss: 155.791
+54400/69092	Loss: 158.113
+57600/69092	Loss: 156.650
+60800/69092	Loss: 157.105
+64000/69092	Loss: 157.365
+67200/69092	Loss: 159.565
+Training time 0:07:36.664371
+Epoch: 80 Average loss: 157.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 503)
+0/69092	Loss: 180.853
+3200/69092	Loss: 156.686
+6400/69092	Loss: 156.408
+9600/69092	Loss: 158.892
+12800/69092	Loss: 157.009
+16000/69092	Loss: 158.433
+19200/69092	Loss: 157.543
+22400/69092	Loss: 156.384
+25600/69092	Loss: 158.493
+28800/69092	Loss: 159.497
+32000/69092	Loss: 160.577
+35200/69092	Loss: 158.540
+38400/69092	Loss: 160.839
+41600/69092	Loss: 159.118
+44800/69092	Loss: 155.514
+48000/69092	Loss: 154.819
+51200/69092	Loss: 153.832
+54400/69092	Loss: 156.862
+57600/69092	Loss: 155.018
+60800/69092	Loss: 157.100
+64000/69092	Loss: 160.682
+67200/69092	Loss: 159.814
+Training time 0:07:41.365855
+Epoch: 81 Average loss: 157.80
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 504)
+0/69092	Loss: 166.087
+3200/69092	Loss: 157.924
+6400/69092	Loss: 153.683
+9600/69092	Loss: 157.940
+12800/69092	Loss: 158.585
+16000/69092	Loss: 157.431
+19200/69092	Loss: 156.970
+22400/69092	Loss: 157.899
+25600/69092	Loss: 154.913
+28800/69092	Loss: 157.029
+32000/69092	Loss: 159.909
+35200/69092	Loss: 158.122
+38400/69092	Loss: 156.410
+41600/69092	Loss: 159.825
+44800/69092	Loss: 158.490
+48000/69092	Loss: 157.772
+51200/69092	Loss: 162.079
+54400/69092	Loss: 159.966
+57600/69092	Loss: 156.245
+60800/69092	Loss: 158.083
+64000/69092	Loss: 157.085
+67200/69092	Loss: 155.864
+Training time 0:08:16.314267
+Epoch: 82 Average loss: 157.76
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 505)
+0/69092	Loss: 140.381
+3200/69092	Loss: 157.880
+6400/69092	Loss: 156.526
+9600/69092	Loss: 158.492
+12800/69092	Loss: 156.435
+16000/69092	Loss: 158.491
+19200/69092	Loss: 156.780
+22400/69092	Loss: 160.067
+25600/69092	Loss: 159.845
+28800/69092	Loss: 157.697
+32000/69092	Loss: 158.112
+35200/69092	Loss: 156.679
+38400/69092	Loss: 157.398
+41600/69092	Loss: 154.574
+44800/69092	Loss: 159.494
+48000/69092	Loss: 154.338
+51200/69092	Loss: 158.943
+54400/69092	Loss: 159.074
+57600/69092	Loss: 155.267
+60800/69092	Loss: 158.214
+64000/69092	Loss: 158.086
+67200/69092	Loss: 158.946
+Training time 0:07:36.062949
+Epoch: 83 Average loss: 157.77
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 506)
+0/69092	Loss: 175.959
+3200/69092	Loss: 156.967
+6400/69092	Loss: 159.068
+9600/69092	Loss: 155.671
+12800/69092	Loss: 158.297
+16000/69092	Loss: 155.674
+19200/69092	Loss: 159.069
+22400/69092	Loss: 158.530
+25600/69092	Loss: 154.055
+28800/69092	Loss: 155.656
+32000/69092	Loss: 154.008
+35200/69092	Loss: 157.444
+38400/69092	Loss: 155.039
+41600/69092	Loss: 158.831
+44800/69092	Loss: 158.923
+48000/69092	Loss: 160.924
+51200/69092	Loss: 157.080
+54400/69092	Loss: 159.392
+57600/69092	Loss: 159.830
+60800/69092	Loss: 158.372
+64000/69092	Loss: 160.610
+67200/69092	Loss: 159.146
+Training time 0:07:28.071768
+Epoch: 84 Average loss: 157.92
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 507)
+0/69092	Loss: 144.935
+3200/69092	Loss: 156.230
+6400/69092	Loss: 157.904
+9600/69092	Loss: 157.111
+12800/69092	Loss: 156.397
+16000/69092	Loss: 161.397
+19200/69092	Loss: 158.465
+22400/69092	Loss: 157.977
+25600/69092	Loss: 158.557
+28800/69092	Loss: 157.043
+32000/69092	Loss: 160.598
+35200/69092	Loss: 160.585
+38400/69092	Loss: 160.295
+41600/69092	Loss: 157.566
+44800/69092	Loss: 157.047
+48000/69092	Loss: 156.283
+51200/69092	Loss: 157.593
+54400/69092	Loss: 155.550
+57600/69092	Loss: 158.410
+60800/69092	Loss: 157.781
+64000/69092	Loss: 155.881
+67200/69092	Loss: 158.025
+Training time 0:07:34.064737
+Epoch: 85 Average loss: 157.91
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 508)
+0/69092	Loss: 152.740
+3200/69092	Loss: 153.671
+6400/69092	Loss: 159.215
+9600/69092	Loss: 161.432
+12800/69092	Loss: 159.513
+16000/69092	Loss: 157.684
+19200/69092	Loss: 156.483
+22400/69092	Loss: 159.997
+25600/69092	Loss: 159.024
+28800/69092	Loss: 158.370
+32000/69092	Loss: 157.508
+35200/69092	Loss: 155.269
+38400/69092	Loss: 155.662
+41600/69092	Loss: 156.736
+44800/69092	Loss: 157.925
+48000/69092	Loss: 159.825
+51200/69092	Loss: 154.409
+54400/69092	Loss: 156.880
+57600/69092	Loss: 158.776
+60800/69092	Loss: 158.358
+64000/69092	Loss: 156.484
+67200/69092	Loss: 157.780
+Training time 0:07:35.892446
+Epoch: 86 Average loss: 157.59
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 509)
+0/69092	Loss: 152.511
+3200/69092	Loss: 160.191
+6400/69092	Loss: 158.204
+9600/69092	Loss: 158.823
+12800/69092	Loss: 158.925
+16000/69092	Loss: 159.903
+19200/69092	Loss: 158.950
+22400/69092	Loss: 155.247
+25600/69092	Loss: 155.340
+28800/69092	Loss: 158.975
+32000/69092	Loss: 156.164
+35200/69092	Loss: 159.493
+38400/69092	Loss: 154.748
+41600/69092	Loss: 157.242
+44800/69092	Loss: 158.245
+48000/69092	Loss: 155.570
+51200/69092	Loss: 159.349
+54400/69092	Loss: 155.647
+57600/69092	Loss: 157.646
+60800/69092	Loss: 155.890
+64000/69092	Loss: 157.267
+67200/69092	Loss: 162.443
+Training time 0:07:44.662175
+Epoch: 87 Average loss: 157.85
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 510)
+0/69092	Loss: 151.160
+3200/69092	Loss: 157.396
+6400/69092	Loss: 159.034
+9600/69092	Loss: 156.480
+12800/69092	Loss: 156.810
+16000/69092	Loss: 161.978
+19200/69092	Loss: 154.267
+22400/69092	Loss: 158.934
+25600/69092	Loss: 160.265
+28800/69092	Loss: 159.777
+32000/69092	Loss: 156.637
+35200/69092	Loss: 158.547
+38400/69092	Loss: 156.789
+41600/69092	Loss: 157.268
+44800/69092	Loss: 155.549
+48000/69092	Loss: 158.503
+51200/69092	Loss: 158.325
+54400/69092	Loss: 155.834
+57600/69092	Loss: 158.405
+60800/69092	Loss: 156.796
+64000/69092	Loss: 157.036
+67200/69092	Loss: 155.809
+Training time 0:07:46.648842
+Epoch: 88 Average loss: 157.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 511)
+0/69092	Loss: 149.176
+3200/69092	Loss: 156.270
+6400/69092	Loss: 159.844
+9600/69092	Loss: 158.502
+12800/69092	Loss: 156.811
+16000/69092	Loss: 158.520
+19200/69092	Loss: 155.946
+22400/69092	Loss: 157.646
+25600/69092	Loss: 159.586
+28800/69092	Loss: 158.628
+32000/69092	Loss: 158.061
+35200/69092	Loss: 155.156
+38400/69092	Loss: 156.480
+41600/69092	Loss: 157.869
+44800/69092	Loss: 154.838
+48000/69092	Loss: 155.653
+51200/69092	Loss: 158.589
+54400/69092	Loss: 155.287
+57600/69092	Loss: 159.938
+60800/69092	Loss: 156.214
+64000/69092	Loss: 159.472
+67200/69092	Loss: 161.634
+Training time 0:07:38.683238
+Epoch: 89 Average loss: 157.69
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 512)
+0/69092	Loss: 149.412
+3200/69092	Loss: 155.525
+6400/69092	Loss: 158.904
+9600/69092	Loss: 157.171
+12800/69092	Loss: 155.118
+16000/69092	Loss: 155.509
+19200/69092	Loss: 159.854
+22400/69092	Loss: 157.420
+25600/69092	Loss: 157.897
+28800/69092	Loss: 158.223
+32000/69092	Loss: 158.064
+35200/69092	Loss: 158.312
+38400/69092	Loss: 156.556
+41600/69092	Loss: 156.076
+44800/69092	Loss: 157.220
+48000/69092	Loss: 157.626
+51200/69092	Loss: 160.222
+54400/69092	Loss: 158.497
+57600/69092	Loss: 160.412
+60800/69092	Loss: 159.398
+64000/69092	Loss: 156.802
+67200/69092	Loss: 156.908
+Training time 0:07:39.444737
+Epoch: 90 Average loss: 157.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 513)
+0/69092	Loss: 154.813
+3200/69092	Loss: 159.117
+6400/69092	Loss: 159.558
+9600/69092	Loss: 158.387
+12800/69092	Loss: 158.814
+16000/69092	Loss: 155.542
+19200/69092	Loss: 157.716
+22400/69092	Loss: 156.328
+25600/69092	Loss: 159.649
+28800/69092	Loss: 156.218
+32000/69092	Loss: 157.246
+35200/69092	Loss: 155.319
+38400/69092	Loss: 159.493
+41600/69092	Loss: 161.007
+44800/69092	Loss: 158.224
+48000/69092	Loss: 155.385
+51200/69092	Loss: 155.362
+54400/69092	Loss: 158.967
+57600/69092	Loss: 157.250
+60800/69092	Loss: 154.913
+64000/69092	Loss: 159.351
+67200/69092	Loss: 155.443
+Training time 0:07:32.094765
+Epoch: 91 Average loss: 157.71
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 514)
+0/69092	Loss: 159.650
+3200/69092	Loss: 157.919
+6400/69092	Loss: 160.026
+9600/69092	Loss: 158.221
+12800/69092	Loss: 157.497
+16000/69092	Loss: 159.998
+19200/69092	Loss: 161.137
+22400/69092	Loss: 154.795
+25600/69092	Loss: 158.357
+28800/69092	Loss: 161.084
+32000/69092	Loss: 154.626
+35200/69092	Loss: 153.999
+38400/69092	Loss: 158.061
+41600/69092	Loss: 155.212
+44800/69092	Loss: 154.351
+48000/69092	Loss: 159.020
+51200/69092	Loss: 159.936
+54400/69092	Loss: 157.242
+57600/69092	Loss: 157.101
+60800/69092	Loss: 159.235
+64000/69092	Loss: 158.422
+67200/69092	Loss: 155.296
+Training time 0:07:32.004785
+Epoch: 92 Average loss: 157.72
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 515)
+0/69092	Loss: 133.340
+3200/69092	Loss: 158.566
+6400/69092	Loss: 158.643
+9600/69092	Loss: 158.676
+12800/69092	Loss: 156.503
+16000/69092	Loss: 159.262
+19200/69092	Loss: 156.363
+22400/69092	Loss: 157.053
+25600/69092	Loss: 157.230
+28800/69092	Loss: 155.916
+32000/69092	Loss: 157.024
+35200/69092	Loss: 158.469
+38400/69092	Loss: 159.448
+41600/69092	Loss: 152.880
+44800/69092	Loss: 160.283
+48000/69092	Loss: 157.761
+51200/69092	Loss: 159.088
+54400/69092	Loss: 157.107
+57600/69092	Loss: 156.287
+60800/69092	Loss: 154.336
+64000/69092	Loss: 159.178
+67200/69092	Loss: 160.539
+Training time 0:07:29.730490
+Epoch: 93 Average loss: 157.69
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 516)
+0/69092	Loss: 133.082
+3200/69092	Loss: 156.999
+6400/69092	Loss: 155.885
+9600/69092	Loss: 159.934
+12800/69092	Loss: 158.078
+16000/69092	Loss: 157.008
+19200/69092	Loss: 157.699
+22400/69092	Loss: 156.368
+25600/69092	Loss: 157.416
+28800/69092	Loss: 157.283
+32000/69092	Loss: 157.344
+35200/69092	Loss: 158.307
+38400/69092	Loss: 159.427
+41600/69092	Loss: 155.643
+44800/69092	Loss: 155.279
+48000/69092	Loss: 160.106
+51200/69092	Loss: 159.145
+54400/69092	Loss: 156.276
+57600/69092	Loss: 156.176
+60800/69092	Loss: 156.426
+64000/69092	Loss: 157.087
+67200/69092	Loss: 158.761
+Training time 0:07:39.387163
+Epoch: 94 Average loss: 157.46
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 517)
+0/69092	Loss: 163.615
+3200/69092	Loss: 160.066
+6400/69092	Loss: 159.195
+9600/69092	Loss: 158.727
+12800/69092	Loss: 157.707
+16000/69092	Loss: 159.915
+19200/69092	Loss: 157.481
+22400/69092	Loss: 160.829
+25600/69092	Loss: 154.970
+28800/69092	Loss: 157.831
+32000/69092	Loss: 156.736
+35200/69092	Loss: 158.355
+38400/69092	Loss: 158.129
+41600/69092	Loss: 155.511
+44800/69092	Loss: 157.054
+48000/69092	Loss: 159.390
+51200/69092	Loss: 157.639
+54400/69092	Loss: 157.697
+57600/69092	Loss: 156.910
+60800/69092	Loss: 155.846
+64000/69092	Loss: 156.083
+67200/69092	Loss: 155.491
+Training time 0:07:32.986929
+Epoch: 95 Average loss: 157.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 518)
+0/69092	Loss: 153.329
+3200/69092	Loss: 157.565
+6400/69092	Loss: 155.014
+9600/69092	Loss: 156.838
+12800/69092	Loss: 158.355
+16000/69092	Loss: 158.197
+19200/69092	Loss: 160.262
+22400/69092	Loss: 158.112
+25600/69092	Loss: 156.113
+28800/69092	Loss: 155.881
+32000/69092	Loss: 155.352
+35200/69092	Loss: 156.577
+38400/69092	Loss: 155.390
+41600/69092	Loss: 157.399
+44800/69092	Loss: 158.062
+48000/69092	Loss: 157.288
+51200/69092	Loss: 156.992
+54400/69092	Loss: 159.520
+57600/69092	Loss: 156.766
+60800/69092	Loss: 157.826
+64000/69092	Loss: 158.585
+67200/69092	Loss: 159.178
+Training time 0:07:37.982177
+Epoch: 96 Average loss: 157.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 519)
+0/69092	Loss: 162.029
+3200/69092	Loss: 156.626
+6400/69092	Loss: 153.748
+9600/69092	Loss: 158.342
+12800/69092	Loss: 158.772
+16000/69092	Loss: 155.870
+19200/69092	Loss: 156.046
+22400/69092	Loss: 159.318
+25600/69092	Loss: 158.274
+28800/69092	Loss: 155.267
+32000/69092	Loss: 156.078
+35200/69092	Loss: 159.641
+38400/69092	Loss: 159.899
+41600/69092	Loss: 158.241
+44800/69092	Loss: 158.806
+48000/69092	Loss: 158.657
+51200/69092	Loss: 157.880
+54400/69092	Loss: 153.940
+57600/69092	Loss: 159.558
+60800/69092	Loss: 159.391
+64000/69092	Loss: 156.917
+67200/69092	Loss: 159.417
+Training time 0:07:31.927608
+Epoch: 97 Average loss: 157.73
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 520)
+0/69092	Loss: 165.583
+3200/69092	Loss: 158.770
+6400/69092	Loss: 157.282
+9600/69092	Loss: 157.116
+12800/69092	Loss: 158.771
+16000/69092	Loss: 159.874
+19200/69092	Loss: 156.210
+22400/69092	Loss: 156.745
+25600/69092	Loss: 156.833
+28800/69092	Loss: 159.779
+32000/69092	Loss: 157.629
+35200/69092	Loss: 157.827
+38400/69092	Loss: 153.247
+41600/69092	Loss: 159.797
+44800/69092	Loss: 158.356
+48000/69092	Loss: 159.857
+51200/69092	Loss: 156.370
+54400/69092	Loss: 153.245
+57600/69092	Loss: 157.504
+60800/69092	Loss: 158.390
+64000/69092	Loss: 158.892
+67200/69092	Loss: 157.246
+Training time 0:07:37.231391
+Epoch: 98 Average loss: 157.66
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 521)
+0/69092	Loss: 141.044
+3200/69092	Loss: 158.203
+6400/69092	Loss: 153.718
+9600/69092	Loss: 157.338
+12800/69092	Loss: 157.688
+16000/69092	Loss: 157.834
+19200/69092	Loss: 157.629
+22400/69092	Loss: 160.042
+25600/69092	Loss: 157.854
+28800/69092	Loss: 157.055
+32000/69092	Loss: 159.542
+35200/69092	Loss: 156.095
+38400/69092	Loss: 156.955
+41600/69092	Loss: 159.779
+44800/69092	Loss: 158.995
+48000/69092	Loss: 157.464
+51200/69092	Loss: 158.600
+54400/69092	Loss: 157.075
+57600/69092	Loss: 155.842
+60800/69092	Loss: 159.863
+64000/69092	Loss: 156.596
+67200/69092	Loss: 160.781
+Training time 0:07:34.204102
+Epoch: 99 Average loss: 157.86
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 522)
+0/69092	Loss: 180.745
+3200/69092	Loss: 157.653
+6400/69092	Loss: 158.186
+9600/69092	Loss: 156.445
+12800/69092	Loss: 154.923
+16000/69092	Loss: 160.860
+19200/69092	Loss: 158.407
+22400/69092	Loss: 159.320
+25600/69092	Loss: 158.541
+28800/69092	Loss: 157.419
+32000/69092	Loss: 154.546
+35200/69092	Loss: 158.590
+38400/69092	Loss: 162.366
+41600/69092	Loss: 156.903
+44800/69092	Loss: 155.062
+48000/69092	Loss: 156.125
+51200/69092	Loss: 156.371
+54400/69092	Loss: 157.718
+57600/69092	Loss: 156.786
+60800/69092	Loss: 158.285
+64000/69092	Loss: 159.447
+67200/69092	Loss: 158.777
+Training time 0:07:29.705925
+Epoch: 100 Average loss: 157.83
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 523)
+0/69092	Loss: 157.171
+3200/69092	Loss: 157.894
+6400/69092	Loss: 156.242
+9600/69092	Loss: 157.526
+12800/69092	Loss: 156.011
+16000/69092	Loss: 158.175
+19200/69092	Loss: 157.286
+22400/69092	Loss: 157.715
+25600/69092	Loss: 157.283
+28800/69092	Loss: 156.726
+32000/69092	Loss: 157.936
+35200/69092	Loss: 157.302
+38400/69092	Loss: 158.715
+41600/69092	Loss: 161.168
+44800/69092	Loss: 155.476
+48000/69092	Loss: 158.630
+51200/69092	Loss: 157.993
+54400/69092	Loss: 158.533
+57600/69092	Loss: 158.010
+60800/69092	Loss: 155.998
+64000/69092	Loss: 155.585
+67200/69092	Loss: 162.289
+Training time 0:07:38.889646
+Epoch: 101 Average loss: 157.82
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 524)
+0/69092	Loss: 153.805
+3200/69092	Loss: 156.773
+6400/69092	Loss: 158.692
+9600/69092	Loss: 158.670
+12800/69092	Loss: 158.378
+16000/69092	Loss: 161.036
+19200/69092	Loss: 157.005
+22400/69092	Loss: 157.486
+25600/69092	Loss: 161.685
+28800/69092	Loss: 155.105
+32000/69092	Loss: 155.731
+35200/69092	Loss: 158.598
+38400/69092	Loss: 159.383
+41600/69092	Loss: 159.138
+44800/69092	Loss: 156.092
+48000/69092	Loss: 155.319
+51200/69092	Loss: 155.354
+54400/69092	Loss: 153.979
+57600/69092	Loss: 159.201
+60800/69092	Loss: 156.898
+64000/69092	Loss: 155.546
+67200/69092	Loss: 158.344
+Training time 0:07:33.440113
+Epoch: 102 Average loss: 157.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 525)
+0/69092	Loss: 175.364
+3200/69092	Loss: 157.498
+6400/69092	Loss: 156.026
+9600/69092	Loss: 158.885
+12800/69092	Loss: 157.601
+16000/69092	Loss: 155.731
+19200/69092	Loss: 159.688
+22400/69092	Loss: 158.584
+25600/69092	Loss: 155.957
+28800/69092	Loss: 155.444
+32000/69092	Loss: 159.895
+35200/69092	Loss: 155.682
+38400/69092	Loss: 159.003
+41600/69092	Loss: 157.092
+44800/69092	Loss: 156.799
+48000/69092	Loss: 160.252
+51200/69092	Loss: 158.584
+54400/69092	Loss: 156.823
+57600/69092	Loss: 157.794
+60800/69092	Loss: 158.527
+64000/69092	Loss: 161.254
+67200/69092	Loss: 155.707
+Training time 0:07:38.758941
+Epoch: 103 Average loss: 157.75
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 526)
+0/69092	Loss: 166.588
+3200/69092	Loss: 159.379
+6400/69092	Loss: 155.092
+9600/69092	Loss: 157.486
+12800/69092	Loss: 160.161
+16000/69092	Loss: 157.334
+19200/69092	Loss: 156.723
+22400/69092	Loss: 155.221
+25600/69092	Loss: 157.481
+28800/69092	Loss: 156.966
+32000/69092	Loss: 160.210
+35200/69092	Loss: 158.788
+38400/69092	Loss: 160.669
+41600/69092	Loss: 156.398
+44800/69092	Loss: 158.739
+48000/69092	Loss: 156.517
+51200/69092	Loss: 157.833
+54400/69092	Loss: 157.629
+57600/69092	Loss: 157.974
+60800/69092	Loss: 157.256
+64000/69092	Loss: 157.863
+67200/69092	Loss: 156.069
+Training time 0:07:34.366990
+Epoch: 104 Average loss: 157.72
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 527)
+0/69092	Loss: 148.907
+3200/69092	Loss: 158.471
+6400/69092	Loss: 157.535
+9600/69092	Loss: 156.035
+12800/69092	Loss: 153.833
+16000/69092	Loss: 155.330
+19200/69092	Loss: 157.304
+22400/69092	Loss: 159.477
+25600/69092	Loss: 161.069
+28800/69092	Loss: 154.926
+32000/69092	Loss: 157.506
+35200/69092	Loss: 162.517
+38400/69092	Loss: 158.310
+41600/69092	Loss: 159.988
+44800/69092	Loss: 154.527
+48000/69092	Loss: 157.365
+51200/69092	Loss: 155.951
+54400/69092	Loss: 156.660
+57600/69092	Loss: 157.906
+60800/69092	Loss: 161.578
+64000/69092	Loss: 157.248
+67200/69092	Loss: 155.029
+Training time 0:07:43.933782
+Epoch: 105 Average loss: 157.63
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 528)
+0/69092	Loss: 138.659
+3200/69092	Loss: 157.540
+6400/69092	Loss: 158.332
+9600/69092	Loss: 157.455
+12800/69092	Loss: 158.218
+16000/69092	Loss: 161.150
+19200/69092	Loss: 159.393
+22400/69092	Loss: 157.972
+25600/69092	Loss: 159.304
+28800/69092	Loss: 155.094
+32000/69092	Loss: 158.448
+35200/69092	Loss: 156.939
+38400/69092	Loss: 157.354
+41600/69092	Loss: 158.582
+44800/69092	Loss: 157.610
+48000/69092	Loss: 156.005
+51200/69092	Loss: 158.786
+54400/69092	Loss: 158.008
+57600/69092	Loss: 155.811
+60800/69092	Loss: 155.675
+64000/69092	Loss: 157.527
+67200/69092	Loss: 158.638
+Training time 0:08:14.252079
+Epoch: 106 Average loss: 157.75
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 529)
+0/69092	Loss: 154.639
+3200/69092	Loss: 158.463
+6400/69092	Loss: 160.434
+9600/69092	Loss: 160.350
+12800/69092	Loss: 157.455
+16000/69092	Loss: 156.921
+19200/69092	Loss: 156.405
+22400/69092	Loss: 160.849
+25600/69092	Loss: 157.923
+28800/69092	Loss: 156.720
+32000/69092	Loss: 155.894
+35200/69092	Loss: 158.784
+38400/69092	Loss: 156.914
+41600/69092	Loss: 157.736
+44800/69092	Loss: 157.359
+48000/69092	Loss: 158.633
+51200/69092	Loss: 159.198
+54400/69092	Loss: 157.491
+57600/69092	Loss: 157.254
+60800/69092	Loss: 155.340
+64000/69092	Loss: 155.930
+67200/69092	Loss: 158.540
+Training time 0:07:33.596004
+Epoch: 107 Average loss: 157.86
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 530)
+0/69092	Loss: 167.570
+3200/69092	Loss: 157.847
+6400/69092	Loss: 157.940
+9600/69092	Loss: 159.031
+12800/69092	Loss: 156.011
+16000/69092	Loss: 156.789
+19200/69092	Loss: 157.924
+22400/69092	Loss: 156.473
+25600/69092	Loss: 159.354
+28800/69092	Loss: 156.620
+32000/69092	Loss: 158.289
+35200/69092	Loss: 158.404
+38400/69092	Loss: 158.593
+41600/69092	Loss: 157.324
+44800/69092	Loss: 156.190
+48000/69092	Loss: 157.745
+51200/69092	Loss: 155.562
+54400/69092	Loss: 155.357
+57600/69092	Loss: 158.929
+60800/69092	Loss: 159.424
+64000/69092	Loss: 158.075
+67200/69092	Loss: 159.811
+Training time 0:07:36.767132
+Epoch: 108 Average loss: 157.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 531)
+0/69092	Loss: 162.367
+3200/69092	Loss: 156.644
+6400/69092	Loss: 156.080
+9600/69092	Loss: 157.753
+12800/69092	Loss: 158.813
+16000/69092	Loss: 156.766
+19200/69092	Loss: 157.441
+22400/69092	Loss: 157.998
+25600/69092	Loss: 157.398
+28800/69092	Loss: 159.541
+32000/69092	Loss: 154.696
+35200/69092	Loss: 160.105
+38400/69092	Loss: 156.032
+41600/69092	Loss: 156.427
+44800/69092	Loss: 157.212
+48000/69092	Loss: 157.728
+51200/69092	Loss: 155.416
+54400/69092	Loss: 156.667
+57600/69092	Loss: 157.998
+60800/69092	Loss: 160.001
+64000/69092	Loss: 160.777
+67200/69092	Loss: 159.602
+Training time 0:07:39.017471
+Epoch: 109 Average loss: 157.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 532)
+0/69092	Loss: 175.037
+3200/69092	Loss: 156.504
+6400/69092	Loss: 158.976
+9600/69092	Loss: 160.418
+12800/69092	Loss: 157.926
+16000/69092	Loss: 156.491
+19200/69092	Loss: 158.173
+22400/69092	Loss: 156.645
+25600/69092	Loss: 158.619
+28800/69092	Loss: 156.447
+32000/69092	Loss: 155.338
+35200/69092	Loss: 156.937
+38400/69092	Loss: 158.081
+41600/69092	Loss: 158.036
+44800/69092	Loss: 154.806
+48000/69092	Loss: 159.961
+51200/69092	Loss: 159.160
+54400/69092	Loss: 159.260
+57600/69092	Loss: 160.224
+60800/69092	Loss: 158.742
+64000/69092	Loss: 158.323
+67200/69092	Loss: 157.368
+Training time 0:07:36.974228
+Epoch: 110 Average loss: 157.95
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 533)
+0/69092	Loss: 179.771
+3200/69092	Loss: 154.565
+6400/69092	Loss: 161.583
+9600/69092	Loss: 158.368
+12800/69092	Loss: 156.272
+16000/69092	Loss: 156.113
+19200/69092	Loss: 157.924
+22400/69092	Loss: 159.049
+25600/69092	Loss: 158.233
+28800/69092	Loss: 158.169
+32000/69092	Loss: 159.938
+35200/69092	Loss: 158.658
+38400/69092	Loss: 158.060
+41600/69092	Loss: 162.068
+44800/69092	Loss: 156.388
+48000/69092	Loss: 156.615
+51200/69092	Loss: 155.177
+54400/69092	Loss: 156.735
+57600/69092	Loss: 156.178
+60800/69092	Loss: 158.855
+64000/69092	Loss: 153.721
+67200/69092	Loss: 156.748
+Training time 0:07:37.014190
+Epoch: 111 Average loss: 157.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 534)
+0/69092	Loss: 162.394
+3200/69092	Loss: 159.000
+6400/69092	Loss: 160.320
+9600/69092	Loss: 158.007
+12800/69092	Loss: 159.478
+16000/69092	Loss: 159.099
+19200/69092	Loss: 156.682
+22400/69092	Loss: 159.713
+25600/69092	Loss: 157.806
+28800/69092	Loss: 159.176
+32000/69092	Loss: 156.696
+35200/69092	Loss: 157.030
+38400/69092	Loss: 158.218
+41600/69092	Loss: 156.629
+44800/69092	Loss: 156.802
+48000/69092	Loss: 157.418
+51200/69092	Loss: 156.118
+54400/69092	Loss: 157.219
+57600/69092	Loss: 157.793
+60800/69092	Loss: 157.957
+64000/69092	Loss: 155.350
+67200/69092	Loss: 155.440
+Training time 0:07:33.607448
+Epoch: 112 Average loss: 157.85
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 535)
+0/69092	Loss: 154.372
+3200/69092	Loss: 161.210
+6400/69092	Loss: 158.909
+9600/69092	Loss: 158.434
+12800/69092	Loss: 160.500
+16000/69092	Loss: 155.414
+19200/69092	Loss: 156.818
+22400/69092	Loss: 152.939
+25600/69092	Loss: 158.943
+28800/69092	Loss: 156.231
+32000/69092	Loss: 156.918
+35200/69092	Loss: 159.132
+38400/69092	Loss: 158.406
+41600/69092	Loss: 160.160
+44800/69092	Loss: 156.350
+48000/69092	Loss: 157.058
+51200/69092	Loss: 158.736
+54400/69092	Loss: 157.486
+57600/69092	Loss: 156.042
+60800/69092	Loss: 157.649
+64000/69092	Loss: 159.331
+67200/69092	Loss: 156.511
+Training time 0:07:31.432569
+Epoch: 113 Average loss: 157.72
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 536)
+0/69092	Loss: 155.213
+3200/69092	Loss: 157.873
+6400/69092	Loss: 156.680
+9600/69092	Loss: 158.211
+12800/69092	Loss: 157.539
+16000/69092	Loss: 159.580
+19200/69092	Loss: 161.102
+22400/69092	Loss: 159.066
+25600/69092	Loss: 157.993
+28800/69092	Loss: 153.145
+32000/69092	Loss: 156.692
+35200/69092	Loss: 155.099
+38400/69092	Loss: 157.060
+41600/69092	Loss: 158.202
+44800/69092	Loss: 158.167
+48000/69092	Loss: 157.341
+51200/69092	Loss: 158.491
+54400/69092	Loss: 155.059
+57600/69092	Loss: 156.088
+60800/69092	Loss: 156.604
+64000/69092	Loss: 158.748
+67200/69092	Loss: 159.491
+Training time 0:07:48.434067
+Epoch: 114 Average loss: 157.54
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 537)
+0/69092	Loss: 151.641
+3200/69092	Loss: 156.945
+6400/69092	Loss: 158.783
+9600/69092	Loss: 158.498
+12800/69092	Loss: 156.144
+16000/69092	Loss: 154.472
+19200/69092	Loss: 156.409
+22400/69092	Loss: 159.653
+25600/69092	Loss: 157.343
+28800/69092	Loss: 158.705
+32000/69092	Loss: 157.564
+35200/69092	Loss: 157.154
+38400/69092	Loss: 155.107
+41600/69092	Loss: 156.172
+44800/69092	Loss: 160.661
+48000/69092	Loss: 158.266
+51200/69092	Loss: 157.888
+54400/69092	Loss: 159.203
+57600/69092	Loss: 154.964
+60800/69092	Loss: 157.041
+64000/69092	Loss: 160.978
+67200/69092	Loss: 156.787
+Training time 0:07:30.532157
+Epoch: 115 Average loss: 157.61
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 538)
+0/69092	Loss: 137.076
+3200/69092	Loss: 157.124
+6400/69092	Loss: 157.279
+9600/69092	Loss: 158.082
+12800/69092	Loss: 156.043
+16000/69092	Loss: 156.691
+19200/69092	Loss: 159.120
+22400/69092	Loss: 157.479
+25600/69092	Loss: 158.891
+28800/69092	Loss: 156.418
+32000/69092	Loss: 157.741
+35200/69092	Loss: 159.003
+38400/69092	Loss: 158.222
+41600/69092	Loss: 155.730
+44800/69092	Loss: 157.036
+48000/69092	Loss: 156.345
+51200/69092	Loss: 158.013
+54400/69092	Loss: 155.993
+57600/69092	Loss: 159.208
+60800/69092	Loss: 156.974
+64000/69092	Loss: 159.441
+67200/69092	Loss: 157.091
+Training time 0:07:34.693144
+Epoch: 116 Average loss: 157.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 539)
+0/69092	Loss: 149.649
+3200/69092	Loss: 158.083
+6400/69092	Loss: 157.855
+9600/69092	Loss: 155.776
+12800/69092	Loss: 157.110
+16000/69092	Loss: 156.025
+19200/69092	Loss: 156.228
+22400/69092	Loss: 160.435
+25600/69092	Loss: 158.659
+28800/69092	Loss: 159.455
+32000/69092	Loss: 158.097
+35200/69092	Loss: 155.090
+38400/69092	Loss: 160.601
+41600/69092	Loss: 158.407
+44800/69092	Loss: 157.914
+48000/69092	Loss: 158.019
+51200/69092	Loss: 159.770
+54400/69092	Loss: 155.188
+57600/69092	Loss: 154.323
+60800/69092	Loss: 156.814
+64000/69092	Loss: 155.683
+67200/69092	Loss: 156.353
+Training time 0:07:36.189551
+Epoch: 117 Average loss: 157.53
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 540)
+0/69092	Loss: 169.442
+3200/69092	Loss: 158.095
+6400/69092	Loss: 157.981
+9600/69092	Loss: 158.030
+12800/69092	Loss: 158.142
+16000/69092	Loss: 157.510
+19200/69092	Loss: 158.548
+22400/69092	Loss: 156.893
+25600/69092	Loss: 160.023
+28800/69092	Loss: 155.014
+32000/69092	Loss: 157.423
+35200/69092	Loss: 156.354
+38400/69092	Loss: 159.705
+41600/69092	Loss: 156.175
+44800/69092	Loss: 156.050
+48000/69092	Loss: 157.878
+51200/69092	Loss: 158.591
+54400/69092	Loss: 157.971
+57600/69092	Loss: 159.717
+60800/69092	Loss: 157.341
+64000/69092	Loss: 158.109
+67200/69092	Loss: 159.147
+Training time 0:07:41.286300
+Epoch: 118 Average loss: 157.81
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 541)
+0/69092	Loss: 153.137
+3200/69092	Loss: 161.917
+6400/69092	Loss: 157.672
+9600/69092	Loss: 154.587
+12800/69092	Loss: 156.489
+16000/69092	Loss: 158.081
+19200/69092	Loss: 156.600
+22400/69092	Loss: 158.864
+25600/69092	Loss: 158.821
+28800/69092	Loss: 160.553
+32000/69092	Loss: 156.911
+35200/69092	Loss: 155.479
+38400/69092	Loss: 154.620
+41600/69092	Loss: 159.646
+44800/69092	Loss: 158.487
+48000/69092	Loss: 155.076
+51200/69092	Loss: 158.790
+54400/69092	Loss: 160.677
+57600/69092	Loss: 157.842
+60800/69092	Loss: 157.588
+64000/69092	Loss: 157.628
+67200/69092	Loss: 156.536
+Training time 0:07:42.715600
+Epoch: 119 Average loss: 157.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 542)
+0/69092	Loss: 153.410
+3200/69092	Loss: 157.655
+6400/69092	Loss: 156.319
+9600/69092	Loss: 157.130
+12800/69092	Loss: 158.155
+16000/69092	Loss: 156.282
+19200/69092	Loss: 159.313
+22400/69092	Loss: 157.748
+25600/69092	Loss: 158.311
+28800/69092	Loss: 158.539
+32000/69092	Loss: 156.371
+35200/69092	Loss: 155.880
+38400/69092	Loss: 158.229
+41600/69092	Loss: 161.615
+44800/69092	Loss: 155.849
+48000/69092	Loss: 158.351
+51200/69092	Loss: 157.506
+54400/69092	Loss: 158.126
+57600/69092	Loss: 156.234
+60800/69092	Loss: 158.687
+64000/69092	Loss: 158.833
+67200/69092	Loss: 155.857
+Training time 0:07:32.009732
+Epoch: 120 Average loss: 157.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 543)
+0/69092	Loss: 179.363
+3200/69092	Loss: 158.294
+6400/69092	Loss: 158.698
+9600/69092	Loss: 159.869
+12800/69092	Loss: 156.849
+16000/69092	Loss: 157.781
+19200/69092	Loss: 156.632
+22400/69092	Loss: 158.853
+25600/69092	Loss: 157.685
+28800/69092	Loss: 156.085
+32000/69092	Loss: 154.915
+35200/69092	Loss: 161.598
+38400/69092	Loss: 157.391
+41600/69092	Loss: 157.427
+44800/69092	Loss: 155.825
+48000/69092	Loss: 159.498
+51200/69092	Loss: 156.742
+54400/69092	Loss: 155.002
+57600/69092	Loss: 156.491
+60800/69092	Loss: 159.239
+64000/69092	Loss: 157.330
+67200/69092	Loss: 158.634
+Training time 0:07:34.852113
+Epoch: 121 Average loss: 157.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 544)
+0/69092	Loss: 137.819
+3200/69092	Loss: 157.019
+6400/69092	Loss: 157.263
+9600/69092	Loss: 157.098
+12800/69092	Loss: 159.498
+16000/69092	Loss: 156.247
+19200/69092	Loss: 159.691
+22400/69092	Loss: 156.537
+25600/69092	Loss: 160.002
+28800/69092	Loss: 158.084
+32000/69092	Loss: 159.027
+35200/69092	Loss: 153.295
+38400/69092	Loss: 159.349
+41600/69092	Loss: 157.174
+44800/69092	Loss: 156.608
+48000/69092	Loss: 157.920
+51200/69092	Loss: 158.569
+54400/69092	Loss: 159.910
+57600/69092	Loss: 157.080
+60800/69092	Loss: 155.810
+64000/69092	Loss: 157.640
+67200/69092	Loss: 158.447
+Training time 0:07:39.426315
+Epoch: 122 Average loss: 157.75
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 545)
+0/69092	Loss: 170.004
+3200/69092	Loss: 160.362
+6400/69092	Loss: 158.722
+9600/69092	Loss: 157.007
+12800/69092	Loss: 154.457
+16000/69092	Loss: 155.164
+19200/69092	Loss: 159.093
+22400/69092	Loss: 160.189
+25600/69092	Loss: 159.434
+28800/69092	Loss: 158.000
+32000/69092	Loss: 161.001
+35200/69092	Loss: 156.351
+38400/69092	Loss: 153.391
+41600/69092	Loss: 156.968
+44800/69092	Loss: 155.192
+48000/69092	Loss: 155.886
+51200/69092	Loss: 160.045
+54400/69092	Loss: 157.289
+57600/69092	Loss: 159.222
+60800/69092	Loss: 159.050
+64000/69092	Loss: 156.111
+67200/69092	Loss: 158.931
+Training time 0:07:37.343092
+Epoch: 123 Average loss: 157.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 546)
+0/69092	Loss: 174.328
+3200/69092	Loss: 155.237
+6400/69092	Loss: 159.603
+9600/69092	Loss: 156.943
+12800/69092	Loss: 156.390
+16000/69092	Loss: 158.366
+19200/69092	Loss: 155.592
+22400/69092	Loss: 160.915
+25600/69092	Loss: 157.330
+28800/69092	Loss: 157.144
+32000/69092	Loss: 156.733
+35200/69092	Loss: 157.930
+38400/69092	Loss: 156.557
+41600/69092	Loss: 158.043
+44800/69092	Loss: 157.822
+48000/69092	Loss: 161.522
+51200/69092	Loss: 158.922
+54400/69092	Loss: 156.538
+57600/69092	Loss: 156.733
+60800/69092	Loss: 156.486
+64000/69092	Loss: 157.491
+67200/69092	Loss: 154.345
+Training time 0:07:39.944313
+Epoch: 124 Average loss: 157.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 547)
+0/69092	Loss: 160.394
+3200/69092	Loss: 157.469
+6400/69092	Loss: 156.858
+9600/69092	Loss: 158.479
+12800/69092	Loss: 156.681
+16000/69092	Loss: 157.442
+19200/69092	Loss: 155.448
+22400/69092	Loss: 157.970
+25600/69092	Loss: 158.692
+28800/69092	Loss: 153.689
+32000/69092	Loss: 158.340
+35200/69092	Loss: 160.584
+38400/69092	Loss: 158.523
+41600/69092	Loss: 155.824
+44800/69092	Loss: 159.318
+48000/69092	Loss: 155.997
+51200/69092	Loss: 157.354
+54400/69092	Loss: 157.836
+57600/69092	Loss: 156.951
+60800/69092	Loss: 158.756
+64000/69092	Loss: 156.022
+67200/69092	Loss: 158.210
+Training time 0:07:30.659569
+Epoch: 125 Average loss: 157.47
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 548)
+0/69092	Loss: 160.689
+3200/69092	Loss: 160.385
+6400/69092	Loss: 155.574
+9600/69092	Loss: 157.549
+12800/69092	Loss: 155.905
+16000/69092	Loss: 158.574
+19200/69092	Loss: 157.234
+22400/69092	Loss: 157.416
+25600/69092	Loss: 157.406
+28800/69092	Loss: 156.412
+32000/69092	Loss: 159.487
+35200/69092	Loss: 156.872
+38400/69092	Loss: 158.171
+41600/69092	Loss: 156.892
+44800/69092	Loss: 158.599
+48000/69092	Loss: 159.727
+51200/69092	Loss: 155.946
+54400/69092	Loss: 158.131
+57600/69092	Loss: 156.736
+60800/69092	Loss: 159.232
+64000/69092	Loss: 155.416
+67200/69092	Loss: 159.607
+Training time 0:07:39.661861
+Epoch: 126 Average loss: 157.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 549)
+0/69092	Loss: 149.110
+3200/69092	Loss: 156.887
+6400/69092	Loss: 158.658
+9600/69092	Loss: 159.439
+12800/69092	Loss: 156.015
+16000/69092	Loss: 154.967
+19200/69092	Loss: 160.868
+22400/69092	Loss: 158.704
+25600/69092	Loss: 155.430
+28800/69092	Loss: 156.584
+32000/69092	Loss: 160.100
+35200/69092	Loss: 158.211
+38400/69092	Loss: 158.787
+41600/69092	Loss: 157.194
+44800/69092	Loss: 160.943
+48000/69092	Loss: 156.191
+51200/69092	Loss: 158.944
+54400/69092	Loss: 155.895
+57600/69092	Loss: 156.671
+60800/69092	Loss: 160.419
+64000/69092	Loss: 158.792
+67200/69092	Loss: 154.660
+Training time 0:07:32.259968
+Epoch: 127 Average loss: 157.75
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 550)
+0/69092	Loss: 149.246
+3200/69092	Loss: 156.037
+6400/69092	Loss: 156.968
+9600/69092	Loss: 156.575
+12800/69092	Loss: 158.100
+16000/69092	Loss: 160.061
+19200/69092	Loss: 159.751
+22400/69092	Loss: 157.136
+25600/69092	Loss: 157.351
+28800/69092	Loss: 158.194
+32000/69092	Loss: 156.615
+35200/69092	Loss: 154.513
+38400/69092	Loss: 159.028
+41600/69092	Loss: 156.446
+44800/69092	Loss: 155.243
+48000/69092	Loss: 157.796
+51200/69092	Loss: 160.048
+54400/69092	Loss: 156.069
+57600/69092	Loss: 157.878
+60800/69092	Loss: 157.147
+64000/69092	Loss: 158.952
+67200/69092	Loss: 156.280
+Training time 0:07:35.727273
+Epoch: 128 Average loss: 157.53
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 551)
+0/69092	Loss: 151.922
+3200/69092	Loss: 158.455
+6400/69092	Loss: 160.622
+9600/69092	Loss: 155.704
+12800/69092	Loss: 158.521
+16000/69092	Loss: 155.192
+19200/69092	Loss: 158.924
+22400/69092	Loss: 161.128
+25600/69092	Loss: 158.221
+28800/69092	Loss: 159.442
+32000/69092	Loss: 155.222
+35200/69092	Loss: 156.489
+38400/69092	Loss: 156.253
+41600/69092	Loss: 158.622
+44800/69092	Loss: 155.789
+48000/69092	Loss: 159.086
+51200/69092	Loss: 157.604
+54400/69092	Loss: 156.975
+57600/69092	Loss: 157.523
+60800/69092	Loss: 156.466
+64000/69092	Loss: 156.221
+67200/69092	Loss: 158.753
+Training time 0:07:31.982051
+Epoch: 129 Average loss: 157.63
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 552)
+0/69092	Loss: 157.552
+3200/69092	Loss: 156.863
+6400/69092	Loss: 158.178
+9600/69092	Loss: 159.923
+12800/69092	Loss: 158.983
+16000/69092	Loss: 160.690
+19200/69092	Loss: 159.687
+22400/69092	Loss: 155.216
+25600/69092	Loss: 158.828
+28800/69092	Loss: 159.243
+32000/69092	Loss: 158.921
+35200/69092	Loss: 155.196
+38400/69092	Loss: 159.039
+41600/69092	Loss: 154.585
+44800/69092	Loss: 156.886
+48000/69092	Loss: 160.080
+51200/69092	Loss: 154.623
+54400/69092	Loss: 157.087
+57600/69092	Loss: 156.692
+60800/69092	Loss: 156.039
+64000/69092	Loss: 156.557
+67200/69092	Loss: 156.796
+Training time 0:07:27.748161
+Epoch: 130 Average loss: 157.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 553)
+0/69092	Loss: 151.445
+3200/69092	Loss: 160.886
+6400/69092	Loss: 158.578
+9600/69092	Loss: 159.083
+12800/69092	Loss: 155.244
+16000/69092	Loss: 155.853
+19200/69092	Loss: 157.628
+22400/69092	Loss: 159.420
+25600/69092	Loss: 159.323
+28800/69092	Loss: 155.715
+32000/69092	Loss: 155.918
+35200/69092	Loss: 159.235
+38400/69092	Loss: 161.040
+41600/69092	Loss: 155.665
+44800/69092	Loss: 155.954
+48000/69092	Loss: 155.505
+51200/69092	Loss: 159.228
+54400/69092	Loss: 158.519
+57600/69092	Loss: 158.319
+60800/69092	Loss: 157.675
+64000/69092	Loss: 157.176
+67200/69092	Loss: 157.067
+Training time 0:07:31.240596
+Epoch: 131 Average loss: 157.71
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 554)
+0/69092	Loss: 151.562
+3200/69092	Loss: 158.496
+6400/69092	Loss: 158.880
+9600/69092	Loss: 156.507
+12800/69092	Loss: 155.950
+16000/69092	Loss: 156.512
+19200/69092	Loss: 157.274
+22400/69092	Loss: 159.114
+25600/69092	Loss: 154.284
+28800/69092	Loss: 158.299
+32000/69092	Loss: 158.954
+35200/69092	Loss: 156.397
+38400/69092	Loss: 155.934
+41600/69092	Loss: 156.704
+44800/69092	Loss: 157.631
+48000/69092	Loss: 159.806
+51200/69092	Loss: 160.580
+54400/69092	Loss: 158.373
+57600/69092	Loss: 155.902
+60800/69092	Loss: 156.825
+64000/69092	Loss: 156.582
+67200/69092	Loss: 157.746
+Training time 0:07:36.552860
+Epoch: 132 Average loss: 157.56
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 555)
+0/69092	Loss: 156.585
+3200/69092	Loss: 156.940
+6400/69092	Loss: 157.925
+9600/69092	Loss: 158.641
+12800/69092	Loss: 158.766
+16000/69092	Loss: 154.475
+19200/69092	Loss: 157.123
+22400/69092	Loss: 156.140
+25600/69092	Loss: 157.949
+28800/69092	Loss: 156.293
+32000/69092	Loss: 156.870
+35200/69092	Loss: 159.570
+38400/69092	Loss: 158.292
+41600/69092	Loss: 160.321
+44800/69092	Loss: 156.911
+48000/69092	Loss: 158.080
+51200/69092	Loss: 157.669
+54400/69092	Loss: 156.592
+57600/69092	Loss: 159.447
+60800/69092	Loss: 158.283
+64000/69092	Loss: 158.935
+67200/69092	Loss: 159.733
+Training time 0:07:33.368496
+Epoch: 133 Average loss: 157.75
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 556)
+0/69092	Loss: 150.330
+3200/69092	Loss: 158.740
+6400/69092	Loss: 158.504
+9600/69092	Loss: 156.857
+12800/69092	Loss: 159.995
+16000/69092	Loss: 158.288
+19200/69092	Loss: 159.422
+22400/69092	Loss: 159.759
+25600/69092	Loss: 155.959
+28800/69092	Loss: 157.435
+32000/69092	Loss: 155.511
+35200/69092	Loss: 156.140
+38400/69092	Loss: 155.265
+41600/69092	Loss: 158.958
+44800/69092	Loss: 155.890
+48000/69092	Loss: 156.560
+51200/69092	Loss: 157.505
+54400/69092	Loss: 156.555
+57600/69092	Loss: 157.701
+60800/69092	Loss: 157.473
+64000/69092	Loss: 156.480
+67200/69092	Loss: 157.461
+Training time 0:07:37.041754
+Epoch: 134 Average loss: 157.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 557)
+0/69092	Loss: 172.086
+3200/69092	Loss: 157.709
+6400/69092	Loss: 159.150
+9600/69092	Loss: 155.036
+12800/69092	Loss: 157.026
+16000/69092	Loss: 156.621
+19200/69092	Loss: 157.727
+22400/69092	Loss: 157.726
+25600/69092	Loss: 157.719
+28800/69092	Loss: 156.382
+32000/69092	Loss: 155.383
+35200/69092	Loss: 156.653
+38400/69092	Loss: 156.165
+41600/69092	Loss: 158.031
+44800/69092	Loss: 158.078
+48000/69092	Loss: 158.477
+51200/69092	Loss: 159.168
+54400/69092	Loss: 158.892
+57600/69092	Loss: 156.917
+60800/69092	Loss: 160.670
+64000/69092	Loss: 158.868
+67200/69092	Loss: 156.348
+Training time 0:07:36.754586
+Epoch: 135 Average loss: 157.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 558)
+0/69092	Loss: 172.547
+3200/69092	Loss: 158.034
+6400/69092	Loss: 160.220
+9600/69092	Loss: 158.167
+12800/69092	Loss: 157.359
+16000/69092	Loss: 156.467
+19200/69092	Loss: 154.688
+22400/69092	Loss: 156.849
+25600/69092	Loss: 159.270
+28800/69092	Loss: 155.340
+32000/69092	Loss: 155.756
+35200/69092	Loss: 159.042
+38400/69092	Loss: 157.911
+41600/69092	Loss: 160.961
+44800/69092	Loss: 161.927
+48000/69092	Loss: 154.191
+51200/69092	Loss: 156.660
+54400/69092	Loss: 156.343
+57600/69092	Loss: 158.113
+60800/69092	Loss: 158.078
+64000/69092	Loss: 156.939
+67200/69092	Loss: 157.892
+Training time 0:07:50.220120
+Epoch: 136 Average loss: 157.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 559)
+0/69092	Loss: 174.445
+3200/69092	Loss: 154.993
+6400/69092	Loss: 159.176
+9600/69092	Loss: 159.244
+12800/69092	Loss: 158.363
+16000/69092	Loss: 158.955
+19200/69092	Loss: 155.242
+22400/69092	Loss: 159.683
+25600/69092	Loss: 157.203
+28800/69092	Loss: 156.860
+32000/69092	Loss: 157.487
+35200/69092	Loss: 156.931
+38400/69092	Loss: 157.995
+41600/69092	Loss: 156.932
+44800/69092	Loss: 155.384
+48000/69092	Loss: 158.965
+51200/69092	Loss: 158.571
+54400/69092	Loss: 159.130
+57600/69092	Loss: 156.192
+60800/69092	Loss: 157.434
+64000/69092	Loss: 155.856
+67200/69092	Loss: 159.269
+Training time 0:07:32.263084
+Epoch: 137 Average loss: 157.59
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 560)
+0/69092	Loss: 147.103
+3200/69092	Loss: 156.539
+6400/69092	Loss: 156.454
+9600/69092	Loss: 159.312
+12800/69092	Loss: 157.100
+16000/69092	Loss: 159.078
+19200/69092	Loss: 157.501
+22400/69092	Loss: 159.186
+25600/69092	Loss: 154.777
+28800/69092	Loss: 159.359
+32000/69092	Loss: 157.333
+35200/69092	Loss: 155.639
+38400/69092	Loss: 163.222
+41600/69092	Loss: 156.795
+44800/69092	Loss: 160.510
+48000/69092	Loss: 156.618
+51200/69092	Loss: 156.652
+54400/69092	Loss: 157.446
+57600/69092	Loss: 156.295
+60800/69092	Loss: 157.645
+64000/69092	Loss: 156.577
+67200/69092	Loss: 156.857
+Training time 0:07:29.166213
+Epoch: 138 Average loss: 157.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 561)
+0/69092	Loss: 170.943
+3200/69092	Loss: 157.639
+6400/69092	Loss: 158.043
+9600/69092	Loss: 157.371
+12800/69092	Loss: 157.514
+16000/69092	Loss: 160.305
+19200/69092	Loss: 157.355
+22400/69092	Loss: 156.155
+25600/69092	Loss: 156.073
+28800/69092	Loss: 159.727
+32000/69092	Loss: 158.306
+35200/69092	Loss: 156.657
+38400/69092	Loss: 155.775
+41600/69092	Loss: 156.455
+44800/69092	Loss: 157.475
+48000/69092	Loss: 158.948
+51200/69092	Loss: 156.795
+54400/69092	Loss: 157.214
+57600/69092	Loss: 157.687
+60800/69092	Loss: 156.088
+64000/69092	Loss: 160.783
+67200/69092	Loss: 159.322
+Training time 0:07:38.692024
+Epoch: 139 Average loss: 157.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 562)
+0/69092	Loss: 179.612
+3200/69092	Loss: 155.447
+6400/69092	Loss: 156.380
+9600/69092	Loss: 159.278
+12800/69092	Loss: 156.468
+16000/69092	Loss: 156.650
+19200/69092	Loss: 157.592
+22400/69092	Loss: 157.142
+25600/69092	Loss: 161.815
+28800/69092	Loss: 157.884
+32000/69092	Loss: 158.676
+35200/69092	Loss: 156.305
+38400/69092	Loss: 159.655
+41600/69092	Loss: 157.841
+44800/69092	Loss: 157.702
+48000/69092	Loss: 156.135
+51200/69092	Loss: 159.790
+54400/69092	Loss: 157.179
+57600/69092	Loss: 160.587
+60800/69092	Loss: 157.249
+64000/69092	Loss: 157.380
+67200/69092	Loss: 154.489
+Training time 0:07:33.759771
+Epoch: 140 Average loss: 157.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 563)
+0/69092	Loss: 151.940
+3200/69092	Loss: 154.769
+6400/69092	Loss: 157.635
+9600/69092	Loss: 156.257
+12800/69092	Loss: 156.871
+16000/69092	Loss: 156.371
+19200/69092	Loss: 157.391
+22400/69092	Loss: 159.100
+25600/69092	Loss: 155.099
+28800/69092	Loss: 158.059
+32000/69092	Loss: 157.667
+35200/69092	Loss: 158.421
+38400/69092	Loss: 158.139
+41600/69092	Loss: 159.278
+44800/69092	Loss: 162.742
+48000/69092	Loss: 158.485
+51200/69092	Loss: 156.742
+54400/69092	Loss: 156.999
+57600/69092	Loss: 156.105
+60800/69092	Loss: 158.540
+64000/69092	Loss: 158.390
+67200/69092	Loss: 158.914
+Training time 0:07:38.529632
+Epoch: 141 Average loss: 157.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 564)
+0/69092	Loss: 134.936
+3200/69092	Loss: 156.142
+6400/69092	Loss: 156.290
+9600/69092	Loss: 156.892
+12800/69092	Loss: 156.823
+16000/69092	Loss: 159.848
+19200/69092	Loss: 160.416
+22400/69092	Loss: 158.661
+25600/69092	Loss: 156.366
+28800/69092	Loss: 157.418
+32000/69092	Loss: 157.358
+35200/69092	Loss: 157.473
+38400/69092	Loss: 156.318
+41600/69092	Loss: 161.031
+44800/69092	Loss: 158.307
+48000/69092	Loss: 155.263
+51200/69092	Loss: 157.837
+54400/69092	Loss: 158.823
+57600/69092	Loss: 158.565
+60800/69092	Loss: 157.197
+64000/69092	Loss: 156.653
+67200/69092	Loss: 158.134
+Training time 0:07:33.031430
+Epoch: 142 Average loss: 157.71
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 565)
+0/69092	Loss: 138.290
+3200/69092	Loss: 158.065
+6400/69092	Loss: 160.900
+9600/69092	Loss: 157.415
+12800/69092	Loss: 156.159
+16000/69092	Loss: 158.781
+19200/69092	Loss: 157.327
+22400/69092	Loss: 157.692
+25600/69092	Loss: 159.307
+28800/69092	Loss: 158.612
+32000/69092	Loss: 155.432
+35200/69092	Loss: 158.188
+38400/69092	Loss: 158.421
+41600/69092	Loss: 158.745
+44800/69092	Loss: 157.045
+48000/69092	Loss: 154.721
+51200/69092	Loss: 157.948
+54400/69092	Loss: 158.203
+57600/69092	Loss: 158.470
+60800/69092	Loss: 156.306
+64000/69092	Loss: 157.323
+67200/69092	Loss: 158.209
+Training time 0:07:32.882592
+Epoch: 143 Average loss: 157.62
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 566)
+0/69092	Loss: 165.816
+3200/69092	Loss: 158.589
+6400/69092	Loss: 158.320
+9600/69092	Loss: 154.226
+12800/69092	Loss: 155.964
+16000/69092	Loss: 157.126
+19200/69092	Loss: 158.443
+22400/69092	Loss: 157.113
+25600/69092	Loss: 158.750
+28800/69092	Loss: 156.506
+32000/69092	Loss: 156.697
+35200/69092	Loss: 158.375
+38400/69092	Loss: 160.871
+41600/69092	Loss: 156.209
+44800/69092	Loss: 157.836
+48000/69092	Loss: 160.432
+51200/69092	Loss: 156.294
+54400/69092	Loss: 158.507
+57600/69092	Loss: 157.464
+60800/69092	Loss: 159.123
+64000/69092	Loss: 154.387
+67200/69092	Loss: 157.301
+Training time 0:07:37.051703
+Epoch: 144 Average loss: 157.52
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 567)
+0/69092	Loss: 151.906
+3200/69092	Loss: 159.466
+6400/69092	Loss: 157.882
+9600/69092	Loss: 156.481
+12800/69092	Loss: 157.955
+16000/69092	Loss: 159.651
+19200/69092	Loss: 155.534
+22400/69092	Loss: 153.136
+25600/69092	Loss: 159.864
+28800/69092	Loss: 157.575
+32000/69092	Loss: 160.670
+35200/69092	Loss: 158.845
+38400/69092	Loss: 157.844
+41600/69092	Loss: 157.322
+44800/69092	Loss: 157.093
+48000/69092	Loss: 157.155
+51200/69092	Loss: 158.484
+54400/69092	Loss: 157.726
+57600/69092	Loss: 157.877
+60800/69092	Loss: 157.902
+64000/69092	Loss: 157.429
+67200/69092	Loss: 155.661
+Training time 0:07:40.172647
+Epoch: 145 Average loss: 157.73
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 568)
+0/69092	Loss: 155.941
+3200/69092	Loss: 156.528
+6400/69092	Loss: 156.156
+9600/69092	Loss: 155.926
+12800/69092	Loss: 160.122
+16000/69092	Loss: 159.266
+19200/69092	Loss: 156.164
+22400/69092	Loss: 161.245
+25600/69092	Loss: 155.799
+28800/69092	Loss: 158.147
+32000/69092	Loss: 157.278
+35200/69092	Loss: 155.746
+38400/69092	Loss: 156.716
+41600/69092	Loss: 156.799
+44800/69092	Loss: 159.564
+48000/69092	Loss: 156.814
+51200/69092	Loss: 158.785
+54400/69092	Loss: 158.308
+57600/69092	Loss: 158.322
+60800/69092	Loss: 157.712
+64000/69092	Loss: 157.641
+67200/69092	Loss: 157.965
+Training time 0:07:35.113159
+Epoch: 146 Average loss: 157.71
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 569)
+0/69092	Loss: 162.413
+3200/69092	Loss: 157.637
+6400/69092	Loss: 154.652
+9600/69092	Loss: 156.862
+12800/69092	Loss: 160.446
+16000/69092	Loss: 157.836
+19200/69092	Loss: 155.493
+22400/69092	Loss: 156.408
+25600/69092	Loss: 157.957
+28800/69092	Loss: 158.517
+32000/69092	Loss: 156.975
+35200/69092	Loss: 159.872
+38400/69092	Loss: 156.428
+41600/69092	Loss: 159.732
+44800/69092	Loss: 156.381
+48000/69092	Loss: 157.746
+51200/69092	Loss: 156.800
+54400/69092	Loss: 157.887
+57600/69092	Loss: 156.202
+60800/69092	Loss: 156.999
+64000/69092	Loss: 156.427
+67200/69092	Loss: 157.321
+Training time 0:07:37.974020
+Epoch: 147 Average loss: 157.41
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 570)
+0/69092	Loss: 157.540
+3200/69092	Loss: 158.477
+6400/69092	Loss: 159.515
+9600/69092	Loss: 158.417
+12800/69092	Loss: 158.495
+16000/69092	Loss: 154.786
+19200/69092	Loss: 160.099
+22400/69092	Loss: 156.751
+25600/69092	Loss: 158.726
+28800/69092	Loss: 159.040
+32000/69092	Loss: 156.782
+35200/69092	Loss: 157.749
+38400/69092	Loss: 157.976
+41600/69092	Loss: 157.520
+44800/69092	Loss: 158.275
+48000/69092	Loss: 155.623
+51200/69092	Loss: 159.340
+54400/69092	Loss: 155.644
+57600/69092	Loss: 159.055
+60800/69092	Loss: 155.638
+64000/69092	Loss: 157.971
+67200/69092	Loss: 156.784
+Training time 0:07:34.040837
+Epoch: 148 Average loss: 157.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 571)
+0/69092	Loss: 161.969
+3200/69092	Loss: 156.266
+6400/69092	Loss: 159.168
+9600/69092	Loss: 155.671
+12800/69092	Loss: 156.644
+16000/69092	Loss: 156.128
+19200/69092	Loss: 158.327
+22400/69092	Loss: 158.152
+25600/69092	Loss: 157.229
+28800/69092	Loss: 158.405
+32000/69092	Loss: 158.227
+35200/69092	Loss: 161.026
+38400/69092	Loss: 158.292
+41600/69092	Loss: 155.421
+44800/69092	Loss: 156.554
+48000/69092	Loss: 159.499
+51200/69092	Loss: 156.884
+54400/69092	Loss: 159.473
+57600/69092	Loss: 158.906
+60800/69092	Loss: 157.057
+64000/69092	Loss: 157.263
+67200/69092	Loss: 158.798
+Training time 0:07:33.300036
+Epoch: 149 Average loss: 157.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 572)
+0/69092	Loss: 147.575
+3200/69092	Loss: 155.691
+6400/69092	Loss: 158.440
+9600/69092	Loss: 156.984
+12800/69092	Loss: 158.317
+16000/69092	Loss: 157.635
+19200/69092	Loss: 161.228
+22400/69092	Loss: 154.388
+25600/69092	Loss: 156.727
+28800/69092	Loss: 161.078
+32000/69092	Loss: 157.491
+35200/69092	Loss: 158.318
+38400/69092	Loss: 158.364
+41600/69092	Loss: 159.265
+44800/69092	Loss: 157.156
+48000/69092	Loss: 157.230
+51200/69092	Loss: 158.163
+54400/69092	Loss: 155.237
+57600/69092	Loss: 157.997
+60800/69092	Loss: 158.076
+64000/69092	Loss: 158.344
+67200/69092	Loss: 156.163
+Training time 0:07:34.015131
+Epoch: 150 Average loss: 157.67
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 573)
+0/69092	Loss: 156.372
+3200/69092	Loss: 157.531
+6400/69092	Loss: 153.738
+9600/69092	Loss: 156.251
+12800/69092	Loss: 156.623
+16000/69092	Loss: 156.240
+19200/69092	Loss: 160.660
+22400/69092	Loss: 158.848
+25600/69092	Loss: 159.892
+28800/69092	Loss: 155.658
+32000/69092	Loss: 158.692
+35200/69092	Loss: 160.047
+38400/69092	Loss: 156.790
+41600/69092	Loss: 159.111
+44800/69092	Loss: 158.932
+48000/69092	Loss: 154.847
+51200/69092	Loss: 159.027
+54400/69092	Loss: 157.751
+57600/69092	Loss: 158.262
+60800/69092	Loss: 158.945
+64000/69092	Loss: 158.123
+67200/69092	Loss: 156.328
+Training time 0:07:35.692055
+Epoch: 151 Average loss: 157.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 574)
+0/69092	Loss: 157.629
+3200/69092	Loss: 157.319
+6400/69092	Loss: 155.297
+9600/69092	Loss: 159.079
+12800/69092	Loss: 158.089
+16000/69092	Loss: 155.334
+19200/69092	Loss: 157.682
+22400/69092	Loss: 160.591
+25600/69092	Loss: 153.539
+28800/69092	Loss: 159.145
+32000/69092	Loss: 157.782
+35200/69092	Loss: 156.195
+38400/69092	Loss: 156.305
+41600/69092	Loss: 158.123
+44800/69092	Loss: 157.942
+48000/69092	Loss: 160.998
+51200/69092	Loss: 157.680
+54400/69092	Loss: 159.152
+57600/69092	Loss: 157.167
+60800/69092	Loss: 157.719
+64000/69092	Loss: 157.060
+67200/69092	Loss: 156.538
+Training time 0:07:30.807987
+Epoch: 152 Average loss: 157.62
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 575)
+0/69092	Loss: 158.606
+3200/69092	Loss: 159.367
+6400/69092	Loss: 158.610
+9600/69092	Loss: 156.728
+12800/69092	Loss: 158.428
+16000/69092	Loss: 158.012
+19200/69092	Loss: 160.548
+22400/69092	Loss: 156.056
+25600/69092	Loss: 157.358
+28800/69092	Loss: 156.122
+32000/69092	Loss: 155.810
+35200/69092	Loss: 157.920
+38400/69092	Loss: 157.542
+41600/69092	Loss: 155.280
+44800/69092	Loss: 159.999
+48000/69092	Loss: 157.542
+51200/69092	Loss: 157.614
+54400/69092	Loss: 158.417
+57600/69092	Loss: 158.175
+60800/69092	Loss: 158.242
+64000/69092	Loss: 154.758
+67200/69092	Loss: 157.766
+Training time 0:07:29.214958
+Epoch: 153 Average loss: 157.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 576)
+0/69092	Loss: 168.942
+3200/69092	Loss: 155.688
+6400/69092	Loss: 156.287
+9600/69092	Loss: 158.142
+12800/69092	Loss: 155.721
+16000/69092	Loss: 156.256
+19200/69092	Loss: 158.818
+22400/69092	Loss: 154.299
+25600/69092	Loss: 157.721
+28800/69092	Loss: 159.517
+32000/69092	Loss: 156.966
+35200/69092	Loss: 159.170
+38400/69092	Loss: 156.202
+41600/69092	Loss: 160.466
+44800/69092	Loss: 159.677
+48000/69092	Loss: 159.785
+51200/69092	Loss: 157.685
+54400/69092	Loss: 157.489
+57600/69092	Loss: 158.254
+60800/69092	Loss: 156.083
+64000/69092	Loss: 157.199
+67200/69092	Loss: 156.997
+Training time 0:07:39.012350
+Epoch: 154 Average loss: 157.59
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 577)
+0/69092	Loss: 161.232
+3200/69092	Loss: 156.203
+6400/69092	Loss: 157.742
+9600/69092	Loss: 155.068
+12800/69092	Loss: 155.648
+16000/69092	Loss: 158.624
+19200/69092	Loss: 158.679
+22400/69092	Loss: 158.236
+25600/69092	Loss: 157.195
+28800/69092	Loss: 160.149
+32000/69092	Loss: 154.798
+35200/69092	Loss: 157.432
+38400/69092	Loss: 157.620
+41600/69092	Loss: 159.608
+44800/69092	Loss: 157.899
+48000/69092	Loss: 156.649
+51200/69092	Loss: 161.352
+54400/69092	Loss: 160.268
+57600/69092	Loss: 158.071
+60800/69092	Loss: 154.520
+64000/69092	Loss: 159.978
+67200/69092	Loss: 156.549
+Training time 0:07:36.146058
+Epoch: 155 Average loss: 157.75
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 578)
+0/69092	Loss: 157.331
+3200/69092	Loss: 154.817
+6400/69092	Loss: 154.749
+9600/69092	Loss: 156.004
+12800/69092	Loss: 159.058
+16000/69092	Loss: 158.516
+19200/69092	Loss: 159.369
+22400/69092	Loss: 160.356
+25600/69092	Loss: 159.928
+28800/69092	Loss: 158.600
+32000/69092	Loss: 159.409
+35200/69092	Loss: 154.035
+38400/69092	Loss: 156.726
+41600/69092	Loss: 159.601
+44800/69092	Loss: 156.436
+48000/69092	Loss: 159.958
+51200/69092	Loss: 160.012
+54400/69092	Loss: 158.891
+57600/69092	Loss: 155.204
+60800/69092	Loss: 158.772
+64000/69092	Loss: 155.424
+67200/69092	Loss: 155.731
+Training time 0:07:44.521468
+Epoch: 156 Average loss: 157.68
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 579)
+0/69092	Loss: 157.496
+3200/69092	Loss: 157.541
+6400/69092	Loss: 152.987
+9600/69092	Loss: 155.788
+12800/69092	Loss: 157.378
+16000/69092	Loss: 156.998
+19200/69092	Loss: 158.461
+22400/69092	Loss: 157.885
+25600/69092	Loss: 156.643
+28800/69092	Loss: 156.350
+32000/69092	Loss: 157.118
+35200/69092	Loss: 160.775
+38400/69092	Loss: 159.535
+41600/69092	Loss: 157.165
+44800/69092	Loss: 158.838
+48000/69092	Loss: 154.420
+51200/69092	Loss: 159.609
+54400/69092	Loss: 157.423
+57600/69092	Loss: 159.854
+60800/69092	Loss: 156.587
+64000/69092	Loss: 158.592
+67200/69092	Loss: 157.958
+Training time 0:07:36.105986
+Epoch: 157 Average loss: 157.44
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 580)
+0/69092	Loss: 160.850
+3200/69092	Loss: 159.117
+6400/69092	Loss: 157.698
+9600/69092	Loss: 158.008
+12800/69092	Loss: 156.495
+16000/69092	Loss: 159.852
+19200/69092	Loss: 158.409
+22400/69092	Loss: 157.026
+25600/69092	Loss: 158.382
+28800/69092	Loss: 157.361
+32000/69092	Loss: 156.182
+35200/69092	Loss: 156.698
+38400/69092	Loss: 156.975
+41600/69092	Loss: 155.870
+44800/69092	Loss: 157.218
+48000/69092	Loss: 159.132
+51200/69092	Loss: 158.100
+54400/69092	Loss: 155.740
+57600/69092	Loss: 160.819
+60800/69092	Loss: 158.610
+64000/69092	Loss: 156.735
+67200/69092	Loss: 157.518
+Training time 0:07:37.671465
+Epoch: 158 Average loss: 157.72
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 581)
+0/69092	Loss: 149.397
+3200/69092	Loss: 158.202
+6400/69092	Loss: 158.326
+9600/69092	Loss: 158.630
+12800/69092	Loss: 156.976
+16000/69092	Loss: 155.844
+19200/69092	Loss: 156.389
+22400/69092	Loss: 158.058
+25600/69092	Loss: 157.957
+28800/69092	Loss: 158.209
+32000/69092	Loss: 158.773
+35200/69092	Loss: 155.653
+38400/69092	Loss: 157.369
+41600/69092	Loss: 156.969
+44800/69092	Loss: 158.648
+48000/69092	Loss: 155.004
+51200/69092	Loss: 158.904
+54400/69092	Loss: 157.876
+57600/69092	Loss: 157.111
+60800/69092	Loss: 157.359
+64000/69092	Loss: 159.632
+67200/69092	Loss: 160.806
+Training time 0:07:41.364212
+Epoch: 159 Average loss: 157.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 582)
+0/69092	Loss: 164.168
+3200/69092	Loss: 156.120
+6400/69092	Loss: 155.482
+9600/69092	Loss: 156.257
+12800/69092	Loss: 159.174
+16000/69092	Loss: 156.061
+19200/69092	Loss: 157.886
+22400/69092	Loss: 157.194
+25600/69092	Loss: 155.159
+28800/69092	Loss: 159.429
+32000/69092	Loss: 157.514
+35200/69092	Loss: 156.551
+38400/69092	Loss: 157.895
+41600/69092	Loss: 157.831
+44800/69092	Loss: 157.575
+48000/69092	Loss: 156.571
+51200/69092	Loss: 161.243
+54400/69092	Loss: 158.887
+57600/69092	Loss: 154.868
+60800/69092	Loss: 160.358
+64000/69092	Loss: 160.210
+67200/69092	Loss: 158.976
+Training time 0:07:35.514233
+Epoch: 160 Average loss: 157.77
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 583)
+0/69092	Loss: 168.368
+3200/69092	Loss: 154.760
+6400/69092	Loss: 158.793
+9600/69092	Loss: 156.824
+12800/69092	Loss: 158.812
+16000/69092	Loss: 158.357
+19200/69092	Loss: 157.593
+22400/69092	Loss: 156.447
+25600/69092	Loss: 158.375
+28800/69092	Loss: 159.535
+32000/69092	Loss: 156.386
+35200/69092	Loss: 157.691
+38400/69092	Loss: 157.110
+41600/69092	Loss: 158.631
+44800/69092	Loss: 155.094
+48000/69092	Loss: 157.894
+51200/69092	Loss: 157.890
+54400/69092	Loss: 157.593
+57600/69092	Loss: 157.227
+60800/69092	Loss: 155.624
+64000/69092	Loss: 157.391
+67200/69092	Loss: 159.611
+Training time 0:07:35.033398
+Epoch: 161 Average loss: 157.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 584)
+0/69092	Loss: 165.207
+3200/69092	Loss: 158.466
+6400/69092	Loss: 160.988
+9600/69092	Loss: 157.273
+12800/69092	Loss: 159.614
+16000/69092	Loss: 158.125
+19200/69092	Loss: 159.237
+22400/69092	Loss: 158.507
+25600/69092	Loss: 158.233
+28800/69092	Loss: 157.058
+32000/69092	Loss: 159.193
+35200/69092	Loss: 153.101
+38400/69092	Loss: 157.462
+41600/69092	Loss: 156.859
+44800/69092	Loss: 157.796
+48000/69092	Loss: 157.700
+51200/69092	Loss: 154.186
+54400/69092	Loss: 157.121
+57600/69092	Loss: 156.711
+60800/69092	Loss: 157.822
+64000/69092	Loss: 155.033
+67200/69092	Loss: 158.255
+Training time 0:07:39.541165
+Epoch: 162 Average loss: 157.69
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 585)
+0/69092	Loss: 138.320
+3200/69092	Loss: 155.451
+6400/69092	Loss: 157.330
+9600/69092	Loss: 158.322
+12800/69092	Loss: 155.975
+16000/69092	Loss: 158.303
+19200/69092	Loss: 159.179
+22400/69092	Loss: 157.473
+25600/69092	Loss: 157.194
+28800/69092	Loss: 160.414
+32000/69092	Loss: 157.592
+35200/69092	Loss: 157.834
+38400/69092	Loss: 154.972
+41600/69092	Loss: 156.708
+44800/69092	Loss: 159.109
+48000/69092	Loss: 159.086
+51200/69092	Loss: 156.588
+54400/69092	Loss: 159.890
+57600/69092	Loss: 156.334
+60800/69092	Loss: 156.099
+64000/69092	Loss: 157.336
+67200/69092	Loss: 158.788
+Training time 0:07:35.086432
+Epoch: 163 Average loss: 157.59
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 586)
+0/69092	Loss: 165.900
+3200/69092	Loss: 158.198
+6400/69092	Loss: 155.431
+9600/69092	Loss: 158.344
+12800/69092	Loss: 159.762
+16000/69092	Loss: 155.675
+19200/69092	Loss: 155.244
+22400/69092	Loss: 160.708
+25600/69092	Loss: 159.464
+28800/69092	Loss: 156.408
+32000/69092	Loss: 159.559
+35200/69092	Loss: 159.711
+38400/69092	Loss: 160.937
+41600/69092	Loss: 154.514
+44800/69092	Loss: 157.858
+48000/69092	Loss: 155.412
+51200/69092	Loss: 157.878
+54400/69092	Loss: 158.454
+57600/69092	Loss: 157.101
+60800/69092	Loss: 159.258
+64000/69092	Loss: 158.499
+67200/69092	Loss: 158.199
+Training time 0:07:36.880300
+Epoch: 164 Average loss: 157.97
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 587)
+0/69092	Loss: 141.148
+3200/69092	Loss: 159.687
+6400/69092	Loss: 156.635
+9600/69092	Loss: 156.497
+12800/69092	Loss: 157.843
+16000/69092	Loss: 157.354
+19200/69092	Loss: 157.629
+22400/69092	Loss: 159.723
+25600/69092	Loss: 159.514
+28800/69092	Loss: 155.280
+32000/69092	Loss: 157.964
+35200/69092	Loss: 159.061
+38400/69092	Loss: 160.602
+41600/69092	Loss: 158.340
+44800/69092	Loss: 152.932
+48000/69092	Loss: 158.254
+51200/69092	Loss: 159.090
+54400/69092	Loss: 156.299
+57600/69092	Loss: 156.386
+60800/69092	Loss: 158.229
+64000/69092	Loss: 157.547
+67200/69092	Loss: 157.726
+Training time 0:07:38.550898
+Epoch: 165 Average loss: 157.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 588)
+0/69092	Loss: 160.765
+3200/69092	Loss: 157.126
+6400/69092	Loss: 156.447
+9600/69092	Loss: 159.068
+12800/69092	Loss: 157.285
+16000/69092	Loss: 155.405
+19200/69092	Loss: 157.813
+22400/69092	Loss: 158.670
+25600/69092	Loss: 155.494
+28800/69092	Loss: 156.514
+32000/69092	Loss: 156.943
+35200/69092	Loss: 154.752
+38400/69092	Loss: 156.897
+41600/69092	Loss: 157.593
+44800/69092	Loss: 159.810
+48000/69092	Loss: 159.160
+51200/69092	Loss: 157.756
+54400/69092	Loss: 157.367
+57600/69092	Loss: 156.229
+60800/69092	Loss: 158.080
+64000/69092	Loss: 159.853
+67200/69092	Loss: 157.733
+Training time 0:07:35.165190
+Epoch: 166 Average loss: 157.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 589)
+0/69092	Loss: 159.348
+3200/69092	Loss: 158.664
+6400/69092	Loss: 154.618
+9600/69092	Loss: 155.180
+12800/69092	Loss: 156.193
+16000/69092	Loss: 157.908
+19200/69092	Loss: 155.748
+22400/69092	Loss: 160.448
+25600/69092	Loss: 155.524
+28800/69092	Loss: 158.314
+32000/69092	Loss: 157.238
+35200/69092	Loss: 155.111
+38400/69092	Loss: 161.002
+41600/69092	Loss: 161.296
+44800/69092	Loss: 157.794
+48000/69092	Loss: 157.986
+51200/69092	Loss: 156.786
+54400/69092	Loss: 157.191
+57600/69092	Loss: 160.684
+60800/69092	Loss: 156.962
+64000/69092	Loss: 160.131
+67200/69092	Loss: 158.277
+Training time 0:07:34.766934
+Epoch: 167 Average loss: 157.73
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 590)
+0/69092	Loss: 155.969
+3200/69092	Loss: 156.915
+6400/69092	Loss: 160.469
+9600/69092	Loss: 155.958
+12800/69092	Loss: 159.059
+16000/69092	Loss: 159.818
+19200/69092	Loss: 157.555
+22400/69092	Loss: 157.441
+25600/69092	Loss: 159.666
+28800/69092	Loss: 156.989
+32000/69092	Loss: 157.511
+35200/69092	Loss: 155.771
+38400/69092	Loss: 154.154
+41600/69092	Loss: 159.000
+44800/69092	Loss: 159.744
+48000/69092	Loss: 158.419
+51200/69092	Loss: 155.037
+54400/69092	Loss: 156.153
+57600/69092	Loss: 159.510
+60800/69092	Loss: 161.079
+64000/69092	Loss: 158.898
+67200/69092	Loss: 156.675
+Training time 0:07:29.686827
+Epoch: 168 Average loss: 157.79
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 591)
+0/69092	Loss: 165.386
+3200/69092	Loss: 155.850
+6400/69092	Loss: 158.909
+9600/69092	Loss: 157.740
+12800/69092	Loss: 156.855
+16000/69092	Loss: 152.735
+19200/69092	Loss: 155.648
+22400/69092	Loss: 156.709
+25600/69092	Loss: 156.016
+28800/69092	Loss: 158.331
+32000/69092	Loss: 157.529
+35200/69092	Loss: 158.512
+38400/69092	Loss: 158.528
+41600/69092	Loss: 155.483
+44800/69092	Loss: 160.280
+48000/69092	Loss: 157.706
+51200/69092	Loss: 159.157
+54400/69092	Loss: 158.383
+57600/69092	Loss: 158.947
+60800/69092	Loss: 159.239
+64000/69092	Loss: 160.786
+67200/69092	Loss: 158.631
+Training time 0:07:36.384444
+Epoch: 169 Average loss: 157.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 592)
+0/69092	Loss: 154.395
+3200/69092	Loss: 157.242
+6400/69092	Loss: 158.456
+9600/69092	Loss: 157.566
+12800/69092	Loss: 158.523
+16000/69092	Loss: 155.000
+19200/69092	Loss: 155.762
+22400/69092	Loss: 159.672
+25600/69092	Loss: 159.687
+28800/69092	Loss: 159.685
+32000/69092	Loss: 159.410
+35200/69092	Loss: 159.551
+38400/69092	Loss: 159.012
+41600/69092	Loss: 155.671
+44800/69092	Loss: 157.067
+48000/69092	Loss: 158.265
+51200/69092	Loss: 158.251
+54400/69092	Loss: 158.763
+57600/69092	Loss: 160.267
+60800/69092	Loss: 157.815
+64000/69092	Loss: 154.141
+67200/69092	Loss: 160.085
+Training time 0:07:40.152736
+Epoch: 170 Average loss: 158.00
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 593)
+0/69092	Loss: 171.260
+3200/69092	Loss: 161.330
+6400/69092	Loss: 156.507
+9600/69092	Loss: 157.869
+12800/69092	Loss: 158.359
+16000/69092	Loss: 159.218
+19200/69092	Loss: 156.429
+22400/69092	Loss: 157.623
+25600/69092	Loss: 156.294
+28800/69092	Loss: 154.625
+32000/69092	Loss: 157.367
+35200/69092	Loss: 156.660
+38400/69092	Loss: 155.588
+41600/69092	Loss: 157.521
+44800/69092	Loss: 158.097
+48000/69092	Loss: 157.386
+51200/69092	Loss: 158.002
+54400/69092	Loss: 156.418
+57600/69092	Loss: 159.561
+60800/69092	Loss: 159.149
+64000/69092	Loss: 157.309
+67200/69092	Loss: 155.133
+Training time 0:07:35.152269
+Epoch: 171 Average loss: 157.40
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 594)
+0/69092	Loss: 177.483
+3200/69092	Loss: 156.440
+6400/69092	Loss: 157.100
+9600/69092	Loss: 157.633
+12800/69092	Loss: 156.243
+16000/69092	Loss: 159.834
+19200/69092	Loss: 156.708
+22400/69092	Loss: 155.138
+25600/69092	Loss: 156.997
+28800/69092	Loss: 157.461
+32000/69092	Loss: 156.920
+35200/69092	Loss: 159.017
+38400/69092	Loss: 157.894
+41600/69092	Loss: 155.722
+44800/69092	Loss: 158.760
+48000/69092	Loss: 159.385
+51200/69092	Loss: 158.632
+54400/69092	Loss: 159.996
+57600/69092	Loss: 157.450
+60800/69092	Loss: 159.991
+64000/69092	Loss: 153.244
+67200/69092	Loss: 158.906
+Training time 0:07:38.241058
+Epoch: 172 Average loss: 157.62
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 595)
+0/69092	Loss: 166.485
+3200/69092	Loss: 158.436
+6400/69092	Loss: 157.324
+9600/69092	Loss: 158.178
+12800/69092	Loss: 156.055
+16000/69092	Loss: 157.700
+19200/69092	Loss: 159.334
+22400/69092	Loss: 157.934
+25600/69092	Loss: 158.722
+28800/69092	Loss: 159.795
+32000/69092	Loss: 156.964
+35200/69092	Loss: 156.047
+38400/69092	Loss: 156.924
+41600/69092	Loss: 159.855
+44800/69092	Loss: 158.209
+48000/69092	Loss: 155.539
+51200/69092	Loss: 155.959
+54400/69092	Loss: 157.026
+57600/69092	Loss: 156.007
+60800/69092	Loss: 158.623
+64000/69092	Loss: 156.867
+67200/69092	Loss: 158.229
+Training time 0:07:42.910369
+Epoch: 173 Average loss: 157.58
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 596)
+0/69092	Loss: 141.178
+3200/69092	Loss: 157.746
+6400/69092	Loss: 157.070
+9600/69092	Loss: 154.965
+12800/69092	Loss: 162.220
+16000/69092	Loss: 159.964
+19200/69092	Loss: 157.555
+22400/69092	Loss: 160.990
+25600/69092	Loss: 157.136
+28800/69092	Loss: 157.806
+32000/69092	Loss: 158.328
+35200/69092	Loss: 156.697
+38400/69092	Loss: 159.196
+41600/69092	Loss: 156.823
+44800/69092	Loss: 155.562
+48000/69092	Loss: 156.899
+51200/69092	Loss: 157.460
+54400/69092	Loss: 156.030
+57600/69092	Loss: 157.469
+60800/69092	Loss: 157.496
+64000/69092	Loss: 158.228
+67200/69092	Loss: 157.746
+Training time 0:07:37.251206
+Epoch: 174 Average loss: 157.62
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 597)
+0/69092	Loss: 168.837
+3200/69092	Loss: 158.414
+6400/69092	Loss: 157.100
+9600/69092	Loss: 159.997
+12800/69092	Loss: 156.166
+16000/69092	Loss: 158.511
+19200/69092	Loss: 158.966
+22400/69092	Loss: 156.826
+25600/69092	Loss: 158.046
+28800/69092	Loss: 162.048
+32000/69092	Loss: 155.340
+35200/69092	Loss: 158.604
+38400/69092	Loss: 157.979
+41600/69092	Loss: 156.428
+44800/69092	Loss: 160.221
+48000/69092	Loss: 156.886
+51200/69092	Loss: 157.056
+54400/69092	Loss: 158.518
+57600/69092	Loss: 155.829
+60800/69092	Loss: 159.613
+64000/69092	Loss: 156.314
+67200/69092	Loss: 153.499
+Training time 0:07:41.461541
+Epoch: 175 Average loss: 157.71
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 598)
+0/69092	Loss: 159.585
+3200/69092	Loss: 154.874
+6400/69092	Loss: 158.457
+9600/69092	Loss: 154.007
+12800/69092	Loss: 157.953
+16000/69092	Loss: 158.239
+19200/69092	Loss: 156.989
+22400/69092	Loss: 157.668
+25600/69092	Loss: 159.302
+28800/69092	Loss: 158.750
+32000/69092	Loss: 158.621
+35200/69092	Loss: 157.667
+38400/69092	Loss: 158.795
+41600/69092	Loss: 158.600
+44800/69092	Loss: 155.883
+48000/69092	Loss: 160.499
+51200/69092	Loss: 155.893
+54400/69092	Loss: 158.664
+57600/69092	Loss: 153.297
+60800/69092	Loss: 157.384
+64000/69092	Loss: 158.331
+67200/69092	Loss: 160.109
+Training time 0:07:37.710212
+Epoch: 176 Average loss: 157.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 599)
+0/69092	Loss: 160.920
+3200/69092	Loss: 158.659
+6400/69092	Loss: 156.873
+9600/69092	Loss: 157.227
+12800/69092	Loss: 156.968
+16000/69092	Loss: 155.658
+19200/69092	Loss: 158.138
+22400/69092	Loss: 157.335
+25600/69092	Loss: 156.164
+28800/69092	Loss: 157.401
+32000/69092	Loss: 157.507
+35200/69092	Loss: 157.700
+38400/69092	Loss: 156.494
+41600/69092	Loss: 160.415
+44800/69092	Loss: 155.215
+48000/69092	Loss: 154.603
+51200/69092	Loss: 157.051
+54400/69092	Loss: 158.753
+57600/69092	Loss: 158.697
+60800/69092	Loss: 159.003
+64000/69092	Loss: 159.154
+67200/69092	Loss: 157.155
+Training time 0:07:36.311156
+Epoch: 177 Average loss: 157.38
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 600)
+0/69092	Loss: 150.988
+3200/69092	Loss: 158.310
+6400/69092	Loss: 155.896
+9600/69092	Loss: 155.675
+12800/69092	Loss: 156.712
+16000/69092	Loss: 157.989
+19200/69092	Loss: 159.349
+22400/69092	Loss: 157.821
+25600/69092	Loss: 160.085
+28800/69092	Loss: 158.995
+32000/69092	Loss: 157.454
+35200/69092	Loss: 158.746
+38400/69092	Loss: 158.789
+41600/69092	Loss: 158.579
+44800/69092	Loss: 156.085
+48000/69092	Loss: 156.502
+51200/69092	Loss: 156.648
+54400/69092	Loss: 157.603
+57600/69092	Loss: 156.512
+60800/69092	Loss: 156.832
+64000/69092	Loss: 155.638
+67200/69092	Loss: 158.790
+Training time 0:08:05.916671
+Epoch: 178 Average loss: 157.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 601)
+0/69092	Loss: 169.491
+3200/69092	Loss: 156.528
+6400/69092	Loss: 161.458
+9600/69092	Loss: 157.217
+12800/69092	Loss: 156.467
+16000/69092	Loss: 159.129
+19200/69092	Loss: 156.950
+22400/69092	Loss: 157.813
+25600/69092	Loss: 156.928
+28800/69092	Loss: 154.885
+32000/69092	Loss: 155.419
+35200/69092	Loss: 157.629
+38400/69092	Loss: 157.844
+41600/69092	Loss: 156.886
+44800/69092	Loss: 155.190
+48000/69092	Loss: 158.683
+51200/69092	Loss: 160.116
+54400/69092	Loss: 155.946
+57600/69092	Loss: 157.248
+60800/69092	Loss: 160.106
+64000/69092	Loss: 155.087
+67200/69092	Loss: 161.082
+Training time 0:07:34.403645
+Epoch: 179 Average loss: 157.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 602)
+0/69092	Loss: 167.608
+3200/69092	Loss: 159.435
+6400/69092	Loss: 158.108
+9600/69092	Loss: 157.288
+12800/69092	Loss: 156.517
+16000/69092	Loss: 156.863
+19200/69092	Loss: 156.393
+22400/69092	Loss: 157.945
+25600/69092	Loss: 158.303
+28800/69092	Loss: 159.508
+32000/69092	Loss: 156.490
+35200/69092	Loss: 157.311
+38400/69092	Loss: 156.896
+41600/69092	Loss: 159.701
+44800/69092	Loss: 159.847
+48000/69092	Loss: 156.521
+51200/69092	Loss: 157.384
+54400/69092	Loss: 156.918
+57600/69092	Loss: 159.120
+60800/69092	Loss: 156.268
+64000/69092	Loss: 156.010
+67200/69092	Loss: 157.066
+Training time 0:07:34.545298
+Epoch: 180 Average loss: 157.56
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 603)
+0/69092	Loss: 148.676
+3200/69092	Loss: 156.439
+6400/69092	Loss: 160.112
+9600/69092	Loss: 160.696
+12800/69092	Loss: 155.957
+16000/69092	Loss: 156.509
+19200/69092	Loss: 159.799
+22400/69092	Loss: 159.549
+25600/69092	Loss: 157.601
+28800/69092	Loss: 158.060
+32000/69092	Loss: 155.266
+35200/69092	Loss: 157.444
+38400/69092	Loss: 156.037
+41600/69092	Loss: 159.626
+44800/69092	Loss: 157.327
+48000/69092	Loss: 156.531
+51200/69092	Loss: 155.651
+54400/69092	Loss: 157.492
+57600/69092	Loss: 155.488
+60800/69092	Loss: 159.355
+64000/69092	Loss: 156.963
+67200/69092	Loss: 158.526
+Training time 0:07:34.366560
+Epoch: 181 Average loss: 157.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 604)
+0/69092	Loss: 143.644
+3200/69092	Loss: 155.323
+6400/69092	Loss: 157.121
+9600/69092	Loss: 155.870
+12800/69092	Loss: 159.925
+16000/69092	Loss: 156.942
+19200/69092	Loss: 159.134
+22400/69092	Loss: 157.727
+25600/69092	Loss: 158.373
+28800/69092	Loss: 154.012
+32000/69092	Loss: 158.499
+35200/69092	Loss: 159.468
+38400/69092	Loss: 160.424
+41600/69092	Loss: 159.488
+44800/69092	Loss: 155.264
+48000/69092	Loss: 156.358
+51200/69092	Loss: 156.569
+54400/69092	Loss: 155.001
+57600/69092	Loss: 156.082
+60800/69092	Loss: 160.624
+64000/69092	Loss: 160.117
+67200/69092	Loss: 156.360
+Training time 0:07:41.079643
+Epoch: 182 Average loss: 157.56
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 605)
+0/69092	Loss: 133.890
+3200/69092	Loss: 156.213
+6400/69092	Loss: 158.994
+9600/69092	Loss: 157.136
+12800/69092	Loss: 157.116
+16000/69092	Loss: 160.643
+19200/69092	Loss: 156.756
+22400/69092	Loss: 158.026
+25600/69092	Loss: 152.892
+28800/69092	Loss: 158.951
+32000/69092	Loss: 159.433
+35200/69092	Loss: 155.035
+38400/69092	Loss: 157.525
+41600/69092	Loss: 156.527
+44800/69092	Loss: 158.945
+48000/69092	Loss: 160.184
+51200/69092	Loss: 158.659
+54400/69092	Loss: 154.336
+57600/69092	Loss: 158.405
+60800/69092	Loss: 159.350
+64000/69092	Loss: 158.548
+67200/69092	Loss: 156.981
+Training time 0:07:37.461778
+Epoch: 183 Average loss: 157.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 606)
+0/69092	Loss: 145.325
+3200/69092	Loss: 157.000
+6400/69092	Loss: 161.352
+9600/69092	Loss: 154.287
+12800/69092	Loss: 158.631
+16000/69092	Loss: 154.803
+19200/69092	Loss: 157.109
+22400/69092	Loss: 157.306
+25600/69092	Loss: 156.488
+28800/69092	Loss: 158.934
+32000/69092	Loss: 156.908
+35200/69092	Loss: 159.783
+38400/69092	Loss: 155.848
+41600/69092	Loss: 157.559
+44800/69092	Loss: 156.732
+48000/69092	Loss: 158.123
+51200/69092	Loss: 158.195
+54400/69092	Loss: 157.608
+57600/69092	Loss: 158.760
+60800/69092	Loss: 156.997
+64000/69092	Loss: 157.911
+67200/69092	Loss: 159.239
+Training time 0:07:34.433890
+Epoch: 184 Average loss: 157.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 607)
+0/69092	Loss: 177.742
+3200/69092	Loss: 156.059
+6400/69092	Loss: 157.517
+9600/69092	Loss: 154.764
+12800/69092	Loss: 156.131
+16000/69092	Loss: 157.224
+19200/69092	Loss: 156.580
+22400/69092	Loss: 157.351
+25600/69092	Loss: 158.039
+28800/69092	Loss: 155.882
+32000/69092	Loss: 156.152
+35200/69092	Loss: 159.161
+38400/69092	Loss: 159.803
+41600/69092	Loss: 159.802
+44800/69092	Loss: 160.223
+48000/69092	Loss: 159.518
+51200/69092	Loss: 157.102
+54400/69092	Loss: 156.523
+57600/69092	Loss: 154.298
+60800/69092	Loss: 159.953
+64000/69092	Loss: 158.586
+67200/69092	Loss: 157.217
+Training time 0:07:35.334517
+Epoch: 185 Average loss: 157.67
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 608)
+0/69092	Loss: 182.018
+3200/69092	Loss: 156.924
+6400/69092	Loss: 159.277
+9600/69092	Loss: 155.167
+12800/69092	Loss: 156.623
+16000/69092	Loss: 158.364
+19200/69092	Loss: 156.229
+22400/69092	Loss: 156.371
+25600/69092	Loss: 156.666
+28800/69092	Loss: 158.292
+32000/69092	Loss: 160.448
+35200/69092	Loss: 158.838
+38400/69092	Loss: 159.192
+41600/69092	Loss: 156.650
+44800/69092	Loss: 156.176
+48000/69092	Loss: 159.092
+51200/69092	Loss: 154.732
+54400/69092	Loss: 157.818
+57600/69092	Loss: 156.083
+60800/69092	Loss: 159.137
+64000/69092	Loss: 159.914
+67200/69092	Loss: 155.665
+Training time 0:07:39.703439
+Epoch: 186 Average loss: 157.53
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 609)
+0/69092	Loss: 172.023
+3200/69092	Loss: 156.334
+6400/69092	Loss: 157.239
+9600/69092	Loss: 159.482
+12800/69092	Loss: 160.004
+16000/69092	Loss: 156.459
+19200/69092	Loss: 158.972
+22400/69092	Loss: 156.472
+25600/69092	Loss: 158.676
+28800/69092	Loss: 158.023
+32000/69092	Loss: 156.167
+35200/69092	Loss: 157.349
+38400/69092	Loss: 157.466
+41600/69092	Loss: 156.012
+44800/69092	Loss: 160.488
+48000/69092	Loss: 156.160
+51200/69092	Loss: 155.272
+54400/69092	Loss: 155.341
+57600/69092	Loss: 157.444
+60800/69092	Loss: 156.807
+64000/69092	Loss: 158.850
+67200/69092	Loss: 158.939
+Training time 0:07:36.607504
+Epoch: 187 Average loss: 157.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 610)
+0/69092	Loss: 163.892
+3200/69092	Loss: 158.662
+6400/69092	Loss: 158.364
+9600/69092	Loss: 157.944
+12800/69092	Loss: 158.743
+16000/69092	Loss: 152.852
+19200/69092	Loss: 155.688
+22400/69092	Loss: 159.464
+25600/69092	Loss: 157.648
+28800/69092	Loss: 159.439
+32000/69092	Loss: 157.836
+35200/69092	Loss: 155.836
+38400/69092	Loss: 155.681
+41600/69092	Loss: 157.312
+44800/69092	Loss: 156.431
+48000/69092	Loss: 155.888
+51200/69092	Loss: 159.088
+54400/69092	Loss: 157.676
+57600/69092	Loss: 157.577
+60800/69092	Loss: 158.445
+64000/69092	Loss: 158.900
+67200/69092	Loss: 157.604
+Training time 0:08:18.772524
+Epoch: 188 Average loss: 157.46
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 611)
+0/69092	Loss: 141.056
+3200/69092	Loss: 158.676
+6400/69092	Loss: 157.418
+9600/69092	Loss: 160.080
+12800/69092	Loss: 155.999
+16000/69092	Loss: 157.233
+19200/69092	Loss: 156.699
+22400/69092	Loss: 158.991
+25600/69092	Loss: 155.729
+28800/69092	Loss: 156.248
+32000/69092	Loss: 156.852
+35200/69092	Loss: 156.165
+38400/69092	Loss: 161.924
+41600/69092	Loss: 157.702
+44800/69092	Loss: 157.302
+48000/69092	Loss: 156.972
+51200/69092	Loss: 155.138
+54400/69092	Loss: 157.846
+57600/69092	Loss: 156.043
+60800/69092	Loss: 158.438
+64000/69092	Loss: 158.873
+67200/69092	Loss: 159.367
+Training time 0:07:35.369007
+Epoch: 189 Average loss: 157.61
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 612)
+0/69092	Loss: 146.726
+3200/69092	Loss: 157.415
+6400/69092	Loss: 154.521
+9600/69092	Loss: 158.966
+12800/69092	Loss: 160.788
+16000/69092	Loss: 157.357
+19200/69092	Loss: 159.127
+22400/69092	Loss: 155.891
+25600/69092	Loss: 156.274
+28800/69092	Loss: 156.649
+32000/69092	Loss: 159.500
+35200/69092	Loss: 159.579
+38400/69092	Loss: 159.208
+41600/69092	Loss: 157.265
+44800/69092	Loss: 158.083
+48000/69092	Loss: 159.789
+51200/69092	Loss: 157.382
+54400/69092	Loss: 156.513
+57600/69092	Loss: 155.798
+60800/69092	Loss: 155.259
+64000/69092	Loss: 156.658
+67200/69092	Loss: 157.497
+Training time 0:07:38.211596
+Epoch: 190 Average loss: 157.56
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 613)
+0/69092	Loss: 180.047
+3200/69092	Loss: 157.902
+6400/69092	Loss: 156.048
+9600/69092	Loss: 158.405
+12800/69092	Loss: 157.967
+16000/69092	Loss: 159.044
+19200/69092	Loss: 157.465
+22400/69092	Loss: 157.645
+25600/69092	Loss: 157.444
+28800/69092	Loss: 157.110
+32000/69092	Loss: 155.758
+35200/69092	Loss: 157.546
+38400/69092	Loss: 154.290
+41600/69092	Loss: 158.861
+44800/69092	Loss: 157.067
+48000/69092	Loss: 159.403
+51200/69092	Loss: 158.355
+54400/69092	Loss: 157.282
+57600/69092	Loss: 155.941
+60800/69092	Loss: 158.261
+64000/69092	Loss: 157.084
+67200/69092	Loss: 160.714
+Training time 0:07:43.680654
+Epoch: 191 Average loss: 157.71
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 614)
+0/69092	Loss: 175.190
+3200/69092	Loss: 157.154
+6400/69092	Loss: 156.420
+9600/69092	Loss: 158.191
+12800/69092	Loss: 157.948
+16000/69092	Loss: 158.924
+19200/69092	Loss: 157.251
+22400/69092	Loss: 156.486
+25600/69092	Loss: 158.766
+28800/69092	Loss: 162.113
+32000/69092	Loss: 157.325
+35200/69092	Loss: 155.732
+38400/69092	Loss: 157.225
+41600/69092	Loss: 157.198
+44800/69092	Loss: 157.932
+48000/69092	Loss: 158.251
+51200/69092	Loss: 158.341
+54400/69092	Loss: 159.315
+57600/69092	Loss: 156.826
+60800/69092	Loss: 159.633
+64000/69092	Loss: 158.644
+67200/69092	Loss: 154.937
+Training time 0:07:34.193681
+Epoch: 192 Average loss: 157.77
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 615)
+0/69092	Loss: 147.571
+3200/69092	Loss: 158.004
+6400/69092	Loss: 155.703
+9600/69092	Loss: 159.606
+12800/69092	Loss: 154.389
+16000/69092	Loss: 155.737
+19200/69092	Loss: 156.994
+22400/69092	Loss: 157.846
+25600/69092	Loss: 158.390
+28800/69092	Loss: 157.601
+32000/69092	Loss: 159.340
+35200/69092	Loss: 159.134
+38400/69092	Loss: 158.195
+41600/69092	Loss: 158.419
+44800/69092	Loss: 158.536
+48000/69092	Loss: 158.838
+51200/69092	Loss: 157.131
+54400/69092	Loss: 159.612
+57600/69092	Loss: 154.506
+60800/69092	Loss: 155.223
+64000/69092	Loss: 160.115
+67200/69092	Loss: 158.260
+Training time 0:07:39.476485
+Epoch: 193 Average loss: 157.66
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 616)
+0/69092	Loss: 153.108
+3200/69092	Loss: 159.743
+6400/69092	Loss: 156.046
+9600/69092	Loss: 155.994
+12800/69092	Loss: 155.641
+16000/69092	Loss: 156.978
+19200/69092	Loss: 158.841
+22400/69092	Loss: 159.033
+25600/69092	Loss: 156.887
+28800/69092	Loss: 160.245
+32000/69092	Loss: 155.959
+35200/69092	Loss: 156.779
+38400/69092	Loss: 156.823
+41600/69092	Loss: 159.671
+44800/69092	Loss: 159.073
+48000/69092	Loss: 157.770
+51200/69092	Loss: 157.133
+54400/69092	Loss: 157.473
+57600/69092	Loss: 154.999
+60800/69092	Loss: 157.107
+64000/69092	Loss: 159.923
+67200/69092	Loss: 157.766
+Training time 0:07:37.958284
+Epoch: 194 Average loss: 157.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 617)
+0/69092	Loss: 145.361
+3200/69092	Loss: 158.009
+6400/69092	Loss: 154.777
+9600/69092	Loss: 157.656
+12800/69092	Loss: 160.636
+16000/69092	Loss: 158.539
+19200/69092	Loss: 157.457
+22400/69092	Loss: 155.913
+25600/69092	Loss: 156.222
+28800/69092	Loss: 158.488
+32000/69092	Loss: 156.609
+35200/69092	Loss: 157.812
+38400/69092	Loss: 155.622
+41600/69092	Loss: 159.498
+44800/69092	Loss: 155.850
+48000/69092	Loss: 159.557
+51200/69092	Loss: 159.982
+54400/69092	Loss: 159.749
+57600/69092	Loss: 157.003
+60800/69092	Loss: 155.729
+64000/69092	Loss: 159.356
+67200/69092	Loss: 156.089
+Training time 0:07:49.865886
+Epoch: 195 Average loss: 157.61
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 618)
+0/69092	Loss: 168.732
+3200/69092	Loss: 159.855
+6400/69092	Loss: 154.344
+9600/69092	Loss: 157.099
+12800/69092	Loss: 160.431
+16000/69092	Loss: 158.283
+19200/69092	Loss: 156.780
+22400/69092	Loss: 158.061
+25600/69092	Loss: 155.664
+28800/69092	Loss: 159.731
+32000/69092	Loss: 157.994
+35200/69092	Loss: 154.159
+38400/69092	Loss: 157.570
+41600/69092	Loss: 158.064
+44800/69092	Loss: 156.379
+48000/69092	Loss: 158.322
+51200/69092	Loss: 158.288
+54400/69092	Loss: 157.102
+57600/69092	Loss: 156.673
+60800/69092	Loss: 158.601
+64000/69092	Loss: 156.436
+67200/69092	Loss: 157.286
+Training time 0:07:26.682721
+Epoch: 196 Average loss: 157.52
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 619)
+0/69092	Loss: 158.793
+3200/69092	Loss: 155.976
+6400/69092	Loss: 155.984
+9600/69092	Loss: 158.079
+12800/69092	Loss: 157.242
+16000/69092	Loss: 158.488
+19200/69092	Loss: 155.632
+22400/69092	Loss: 158.625
+25600/69092	Loss: 160.230
+28800/69092	Loss: 158.373
+32000/69092	Loss: 158.051
+35200/69092	Loss: 159.043
+38400/69092	Loss: 155.068
+41600/69092	Loss: 157.542
+44800/69092	Loss: 155.554
+48000/69092	Loss: 157.905
+51200/69092	Loss: 158.387
+54400/69092	Loss: 159.354
+57600/69092	Loss: 155.931
+60800/69092	Loss: 158.576
+64000/69092	Loss: 157.481
+67200/69092	Loss: 157.360
+Training time 0:07:33.628042
+Epoch: 197 Average loss: 157.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 620)
+0/69092	Loss: 141.904
+3200/69092	Loss: 158.869
+6400/69092	Loss: 158.140
+9600/69092	Loss: 153.492
+12800/69092	Loss: 159.395
+16000/69092	Loss: 159.524
+19200/69092	Loss: 159.216
+22400/69092	Loss: 156.895
+25600/69092	Loss: 157.570
+28800/69092	Loss: 156.397
+32000/69092	Loss: 156.194
+35200/69092	Loss: 157.473
+38400/69092	Loss: 159.513
+41600/69092	Loss: 158.500
+44800/69092	Loss: 159.099
+48000/69092	Loss: 156.454
+51200/69092	Loss: 156.345
+54400/69092	Loss: 157.165
+57600/69092	Loss: 157.710
+60800/69092	Loss: 158.507
+64000/69092	Loss: 158.493
+67200/69092	Loss: 155.632
+Training time 0:07:32.436926
+Epoch: 198 Average loss: 157.70
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 621)
+0/69092	Loss: 164.177
+3200/69092	Loss: 156.312
+6400/69092	Loss: 156.298
+9600/69092	Loss: 155.576
+12800/69092	Loss: 155.596
+16000/69092	Loss: 162.446
+19200/69092	Loss: 155.976
+22400/69092	Loss: 154.942
+25600/69092	Loss: 155.946
+28800/69092	Loss: 156.241
+32000/69092	Loss: 156.882
+35200/69092	Loss: 157.430
+38400/69092	Loss: 159.217
+41600/69092	Loss: 159.027
+44800/69092	Loss: 158.796
+48000/69092	Loss: 159.190
+51200/69092	Loss: 158.960
+54400/69092	Loss: 153.885
+57600/69092	Loss: 158.114
+60800/69092	Loss: 156.608
+64000/69092	Loss: 161.150
+67200/69092	Loss: 157.713
+Training time 0:07:42.994815
+Epoch: 199 Average loss: 157.43
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 622)
+0/69092	Loss: 151.057
+3200/69092	Loss: 160.530
+6400/69092	Loss: 156.774
+9600/69092	Loss: 157.654
+12800/69092	Loss: 157.646
+16000/69092	Loss: 157.090
+19200/69092	Loss: 156.094
+22400/69092	Loss: 159.176
+25600/69092	Loss: 156.123
+28800/69092	Loss: 156.407
+32000/69092	Loss: 156.777
+35200/69092	Loss: 156.713
+38400/69092	Loss: 155.698
+41600/69092	Loss: 156.345
+44800/69092	Loss: 160.135
+48000/69092	Loss: 158.960
+51200/69092	Loss: 155.590
+54400/69092	Loss: 157.558
+57600/69092	Loss: 155.968
+60800/69092	Loss: 158.909
+64000/69092	Loss: 159.598
+67200/69092	Loss: 159.320
+Training time 0:07:34.905489
+Epoch: 200 Average loss: 157.69
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 623)
+0/69092	Loss: 175.519
+3200/69092	Loss: 158.075
+6400/69092	Loss: 158.617
+9600/69092	Loss: 157.481
+12800/69092	Loss: 155.900
+16000/69092	Loss: 157.542
+19200/69092	Loss: 158.225
+22400/69092	Loss: 160.189
+25600/69092	Loss: 156.822
+28800/69092	Loss: 160.196
+32000/69092	Loss: 157.383
+35200/69092	Loss: 157.431
+38400/69092	Loss: 158.968
+41600/69092	Loss: 156.870
+44800/69092	Loss: 156.406
+48000/69092	Loss: 158.396
+51200/69092	Loss: 156.479
+54400/69092	Loss: 156.965
+57600/69092	Loss: 157.680
+60800/69092	Loss: 158.387
+64000/69092	Loss: 154.770
+67200/69092	Loss: 158.280
+Training time 0:07:38.496225
+Epoch: 201 Average loss: 157.75
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 624)
+0/69092	Loss: 153.015
+3200/69092	Loss: 156.760
+6400/69092	Loss: 159.202
+9600/69092	Loss: 159.991
+12800/69092	Loss: 157.782
+16000/69092	Loss: 157.568
+19200/69092	Loss: 157.789
+22400/69092	Loss: 154.274
+25600/69092	Loss: 157.496
+28800/69092	Loss: 157.947
+32000/69092	Loss: 155.606
+35200/69092	Loss: 158.124
+38400/69092	Loss: 157.003
+41600/69092	Loss: 155.084
+44800/69092	Loss: 157.436
+48000/69092	Loss: 157.212
+51200/69092	Loss: 158.412
+54400/69092	Loss: 156.959
+57600/69092	Loss: 156.266
+60800/69092	Loss: 158.161
+64000/69092	Loss: 159.983
+67200/69092	Loss: 158.754
+Training time 0:07:39.867830
+Epoch: 202 Average loss: 157.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 625)
+0/69092	Loss: 154.864
+3200/69092	Loss: 159.007
+6400/69092	Loss: 158.854
+9600/69092	Loss: 158.087
+12800/69092	Loss: 159.630
+16000/69092	Loss: 156.095
+19200/69092	Loss: 156.862
+22400/69092	Loss: 156.390
+25600/69092	Loss: 156.392
+28800/69092	Loss: 159.387
+32000/69092	Loss: 155.419
+35200/69092	Loss: 157.499
+38400/69092	Loss: 158.846
+41600/69092	Loss: 155.451
+44800/69092	Loss: 157.738
+48000/69092	Loss: 155.327
+51200/69092	Loss: 157.131
+54400/69092	Loss: 158.595
+57600/69092	Loss: 155.259
+60800/69092	Loss: 157.866
+64000/69092	Loss: 157.081
+67200/69092	Loss: 158.313
+Training time 0:07:40.975488
+Epoch: 203 Average loss: 157.41
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 626)
+0/69092	Loss: 173.770
+3200/69092	Loss: 157.722
+6400/69092	Loss: 155.573
+9600/69092	Loss: 156.457
+12800/69092	Loss: 158.817
+16000/69092	Loss: 159.988
+19200/69092	Loss: 155.019
+22400/69092	Loss: 159.238
+25600/69092	Loss: 158.432
+28800/69092	Loss: 158.066
+32000/69092	Loss: 158.518
+35200/69092	Loss: 158.990
+38400/69092	Loss: 155.104
+41600/69092	Loss: 157.804
+44800/69092	Loss: 155.990
+48000/69092	Loss: 159.481
+51200/69092	Loss: 158.609
+54400/69092	Loss: 158.299
+57600/69092	Loss: 157.616
+60800/69092	Loss: 160.391
+64000/69092	Loss: 158.006
+67200/69092	Loss: 155.921
+Training time 0:07:38.760921
+Epoch: 204 Average loss: 157.82
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 627)
+0/69092	Loss: 181.800
+3200/69092	Loss: 155.916
+6400/69092	Loss: 157.706
+9600/69092	Loss: 156.083
+12800/69092	Loss: 159.041
+16000/69092	Loss: 156.399
+19200/69092	Loss: 159.783
+22400/69092	Loss: 159.092
+25600/69092	Loss: 158.199
+28800/69092	Loss: 156.969
+32000/69092	Loss: 155.250
+35200/69092	Loss: 156.461
+38400/69092	Loss: 158.443
+41600/69092	Loss: 156.895
+44800/69092	Loss: 158.725
+48000/69092	Loss: 157.817
+51200/69092	Loss: 157.491
+54400/69092	Loss: 158.133
+57600/69092	Loss: 158.895
+60800/69092	Loss: 158.319
+64000/69092	Loss: 157.406
+67200/69092	Loss: 157.734
+Training time 0:08:07.703009
+Epoch: 205 Average loss: 157.56
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 628)
+0/69092	Loss: 147.709
+3200/69092	Loss: 154.964
+6400/69092	Loss: 159.075
+9600/69092	Loss: 158.660
+12800/69092	Loss: 156.360
+16000/69092	Loss: 156.506
+19200/69092	Loss: 158.661
+22400/69092	Loss: 157.413
+25600/69092	Loss: 157.526
+28800/69092	Loss: 159.354
+32000/69092	Loss: 156.501
+35200/69092	Loss: 157.939
+38400/69092	Loss: 156.461
+41600/69092	Loss: 158.859
+44800/69092	Loss: 155.435
+48000/69092	Loss: 158.034
+51200/69092	Loss: 158.688
+54400/69092	Loss: 155.043
+57600/69092	Loss: 159.326
+60800/69092	Loss: 158.101
+64000/69092	Loss: 157.895
+67200/69092	Loss: 160.042
+Training time 0:08:40.501933
+Epoch: 206 Average loss: 157.63
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 629)
+0/69092	Loss: 149.379
+3200/69092	Loss: 156.451
+6400/69092	Loss: 162.007
+9600/69092	Loss: 154.785
+12800/69092	Loss: 156.326
+16000/69092	Loss: 158.797
+19200/69092	Loss: 155.302
+22400/69092	Loss: 158.797
+25600/69092	Loss: 158.475
+28800/69092	Loss: 156.845
+32000/69092	Loss: 158.263
+35200/69092	Loss: 158.897
+38400/69092	Loss: 160.416
+41600/69092	Loss: 157.644
+44800/69092	Loss: 158.725
+48000/69092	Loss: 158.818
+51200/69092	Loss: 156.397
+54400/69092	Loss: 156.142
+57600/69092	Loss: 156.123
+60800/69092	Loss: 156.385
+64000/69092	Loss: 155.916
+67200/69092	Loss: 158.422
+Training time 0:07:35.869309
+Epoch: 207 Average loss: 157.66
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 630)
+0/69092	Loss: 161.830
+3200/69092	Loss: 157.200
+6400/69092	Loss: 159.562
+9600/69092	Loss: 156.876
+12800/69092	Loss: 157.110
+16000/69092	Loss: 159.913
+19200/69092	Loss: 158.115
+22400/69092	Loss: 160.568
+25600/69092	Loss: 158.243
+28800/69092	Loss: 159.737
+32000/69092	Loss: 157.197
+35200/69092	Loss: 154.088
+38400/69092	Loss: 155.213
+41600/69092	Loss: 156.872
+44800/69092	Loss: 155.931
+48000/69092	Loss: 156.351
+51200/69092	Loss: 157.343
+54400/69092	Loss: 159.157
+57600/69092	Loss: 158.354
+60800/69092	Loss: 156.326
+64000/69092	Loss: 159.202
+67200/69092	Loss: 158.062
+Training time 0:07:34.592295
+Epoch: 208 Average loss: 157.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 631)
+0/69092	Loss: 167.264
+3200/69092	Loss: 155.962
+6400/69092	Loss: 159.347
+9600/69092	Loss: 158.574
+12800/69092	Loss: 155.356
+16000/69092	Loss: 158.029
+19200/69092	Loss: 160.409
+22400/69092	Loss: 158.317
+25600/69092	Loss: 160.273
+28800/69092	Loss: 161.428
+32000/69092	Loss: 158.356
+35200/69092	Loss: 155.940
+38400/69092	Loss: 156.851
+41600/69092	Loss: 156.007
+44800/69092	Loss: 158.827
+48000/69092	Loss: 156.510
+51200/69092	Loss: 157.872
+54400/69092	Loss: 156.139
+57600/69092	Loss: 155.908
+60800/69092	Loss: 156.345
+64000/69092	Loss: 157.051
+67200/69092	Loss: 154.484
+Training time 0:07:32.710867
+Epoch: 209 Average loss: 157.53
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 632)
+0/69092	Loss: 156.012
+3200/69092	Loss: 158.887
+6400/69092	Loss: 155.052
+9600/69092	Loss: 154.760
+12800/69092	Loss: 156.522
+16000/69092	Loss: 157.577
+19200/69092	Loss: 156.028
+22400/69092	Loss: 157.146
+25600/69092	Loss: 157.063
+28800/69092	Loss: 157.054
+32000/69092	Loss: 158.659
+35200/69092	Loss: 155.841
+38400/69092	Loss: 158.155
+41600/69092	Loss: 159.075
+44800/69092	Loss: 156.631
+48000/69092	Loss: 158.785
+51200/69092	Loss: 158.876
+54400/69092	Loss: 158.567
+57600/69092	Loss: 159.628
+60800/69092	Loss: 157.635
+64000/69092	Loss: 158.806
+67200/69092	Loss: 157.916
+Training time 0:09:21.159502
+Epoch: 210 Average loss: 157.59
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 633)
+0/69092	Loss: 149.434
+3200/69092	Loss: 156.384
+6400/69092	Loss: 155.799
+9600/69092	Loss: 156.483
+12800/69092	Loss: 155.343
+16000/69092	Loss: 159.804
+19200/69092	Loss: 160.305
+22400/69092	Loss: 154.660
+25600/69092	Loss: 157.097
+28800/69092	Loss: 155.317
+32000/69092	Loss: 158.126
+35200/69092	Loss: 158.762
+38400/69092	Loss: 155.186
+41600/69092	Loss: 161.378
+44800/69092	Loss: 157.198
+48000/69092	Loss: 157.813
+51200/69092	Loss: 158.939
+54400/69092	Loss: 158.631
+57600/69092	Loss: 156.800
+60800/69092	Loss: 158.036
+64000/69092	Loss: 156.362
+67200/69092	Loss: 156.562
+Training time 0:08:02.469975
+Epoch: 211 Average loss: 157.38
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 634)
+0/69092	Loss: 171.673
+3200/69092	Loss: 159.009
+6400/69092	Loss: 159.309
+9600/69092	Loss: 158.129
+12800/69092	Loss: 156.129
+16000/69092	Loss: 158.394
+19200/69092	Loss: 159.815
+22400/69092	Loss: 155.188
+25600/69092	Loss: 158.333
+28800/69092	Loss: 156.852
+32000/69092	Loss: 156.943
+35200/69092	Loss: 156.836
+38400/69092	Loss: 159.630
+41600/69092	Loss: 158.213
+44800/69092	Loss: 158.314
+48000/69092	Loss: 158.386
+51200/69092	Loss: 156.015
+54400/69092	Loss: 156.358
+57600/69092	Loss: 154.555
+60800/69092	Loss: 158.991
+64000/69092	Loss: 157.958
+67200/69092	Loss: 157.672
+Training time 0:07:34.827391
+Epoch: 212 Average loss: 157.73
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 635)
+0/69092	Loss: 164.967
+3200/69092	Loss: 157.399
+6400/69092	Loss: 156.897
+9600/69092	Loss: 157.779
+12800/69092	Loss: 159.042
+16000/69092	Loss: 156.097
+19200/69092	Loss: 156.920
+22400/69092	Loss: 159.080
+25600/69092	Loss: 156.531
+28800/69092	Loss: 159.148
+32000/69092	Loss: 158.062
+35200/69092	Loss: 158.928
+38400/69092	Loss: 157.210
+41600/69092	Loss: 157.960
+44800/69092	Loss: 160.283
+48000/69092	Loss: 158.575
+51200/69092	Loss: 156.386
+54400/69092	Loss: 154.536
+57600/69092	Loss: 158.317
+60800/69092	Loss: 155.755
+64000/69092	Loss: 158.907
+67200/69092	Loss: 156.247
+Training time 0:07:38.126465
+Epoch: 213 Average loss: 157.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 636)
+0/69092	Loss: 155.418
+3200/69092	Loss: 156.562
+6400/69092	Loss: 155.872
+9600/69092	Loss: 158.804
+12800/69092	Loss: 155.374
+16000/69092	Loss: 161.571
+19200/69092	Loss: 155.028
+22400/69092	Loss: 157.048
+25600/69092	Loss: 161.181
+28800/69092	Loss: 158.956
+32000/69092	Loss: 157.274
+35200/69092	Loss: 159.582
+38400/69092	Loss: 156.870
+41600/69092	Loss: 155.474
+44800/69092	Loss: 158.835
+48000/69092	Loss: 155.290
+51200/69092	Loss: 156.300
+54400/69092	Loss: 158.695
+57600/69092	Loss: 160.743
+60800/69092	Loss: 158.966
+64000/69092	Loss: 159.325
+67200/69092	Loss: 157.103
+Training time 0:07:43.581868
+Epoch: 214 Average loss: 157.74
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 637)
+0/69092	Loss: 169.926
+3200/69092	Loss: 159.784
+6400/69092	Loss: 154.882
+9600/69092	Loss: 158.005
+12800/69092	Loss: 158.423
+16000/69092	Loss: 156.531
+19200/69092	Loss: 157.812
+22400/69092	Loss: 160.198
+25600/69092	Loss: 157.394
+28800/69092	Loss: 155.889
+32000/69092	Loss: 158.388
+35200/69092	Loss: 158.960
+38400/69092	Loss: 157.061
+41600/69092	Loss: 156.178
+44800/69092	Loss: 157.984
+48000/69092	Loss: 159.153
+51200/69092	Loss: 159.307
+54400/69092	Loss: 157.805
+57600/69092	Loss: 155.050
+60800/69092	Loss: 157.670
+64000/69092	Loss: 156.737
+67200/69092	Loss: 157.288
+Training time 0:07:37.038836
+Epoch: 215 Average loss: 157.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 638)
+0/69092	Loss: 131.219
+3200/69092	Loss: 156.208
+6400/69092	Loss: 154.055
+9600/69092	Loss: 158.885
+12800/69092	Loss: 157.732
+16000/69092	Loss: 155.100
+19200/69092	Loss: 155.972
+22400/69092	Loss: 156.878
+25600/69092	Loss: 157.127
+28800/69092	Loss: 159.192
+32000/69092	Loss: 155.335
+35200/69092	Loss: 158.400
+38400/69092	Loss: 160.318
+41600/69092	Loss: 157.896
+44800/69092	Loss: 158.552
+48000/69092	Loss: 160.066
+51200/69092	Loss: 159.652
+54400/69092	Loss: 159.627
+57600/69092	Loss: 154.927
+60800/69092	Loss: 158.691
+64000/69092	Loss: 158.396
+67200/69092	Loss: 158.281
+Training time 0:07:26.769823
+Epoch: 216 Average loss: 157.72
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 639)
+0/69092	Loss: 165.630
+3200/69092	Loss: 157.758
+6400/69092	Loss: 158.962
+9600/69092	Loss: 157.403
+12800/69092	Loss: 160.079
+16000/69092	Loss: 158.076
+19200/69092	Loss: 157.829
+22400/69092	Loss: 156.869
+25600/69092	Loss: 155.839
+28800/69092	Loss: 157.018
+32000/69092	Loss: 157.180
+35200/69092	Loss: 156.363
+38400/69092	Loss: 156.714
+41600/69092	Loss: 158.279
+44800/69092	Loss: 159.396
+48000/69092	Loss: 156.562
+51200/69092	Loss: 154.892
+54400/69092	Loss: 159.854
+57600/69092	Loss: 158.474
+60800/69092	Loss: 157.075
+64000/69092	Loss: 158.667
+67200/69092	Loss: 159.407
+Training time 0:07:30.917387
+Epoch: 217 Average loss: 157.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 640)
+0/69092	Loss: 150.273
+3200/69092	Loss: 157.732
+6400/69092	Loss: 156.981
+9600/69092	Loss: 157.096
+12800/69092	Loss: 155.246
+16000/69092	Loss: 157.502
+19200/69092	Loss: 159.538
+22400/69092	Loss: 158.878
+25600/69092	Loss: 154.627
+28800/69092	Loss: 158.307
+32000/69092	Loss: 153.297
+35200/69092	Loss: 156.225
+38400/69092	Loss: 158.003
+41600/69092	Loss: 160.492
+44800/69092	Loss: 157.817
+48000/69092	Loss: 154.894
+51200/69092	Loss: 157.154
+54400/69092	Loss: 158.653
+57600/69092	Loss: 156.552
+60800/69092	Loss: 157.712
+64000/69092	Loss: 157.656
+67200/69092	Loss: 157.510
+Training time 0:07:54.328914
+Epoch: 218 Average loss: 157.22
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 641)
+0/69092	Loss: 162.638
+3200/69092	Loss: 161.718
+6400/69092	Loss: 155.650
+9600/69092	Loss: 159.514
+12800/69092	Loss: 158.213
+16000/69092	Loss: 154.755
+19200/69092	Loss: 158.405
+22400/69092	Loss: 155.158
+25600/69092	Loss: 156.802
+28800/69092	Loss: 157.383
+32000/69092	Loss: 157.675
+35200/69092	Loss: 158.821
+38400/69092	Loss: 156.335
+41600/69092	Loss: 156.381
+44800/69092	Loss: 157.550
+48000/69092	Loss: 158.135
+51200/69092	Loss: 158.909
+54400/69092	Loss: 157.901
+57600/69092	Loss: 157.998
+60800/69092	Loss: 155.305
+64000/69092	Loss: 158.089
+67200/69092	Loss: 160.339
+Training time 0:07:49.090733
+Epoch: 219 Average loss: 157.69
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 642)
+0/69092	Loss: 163.415
+3200/69092	Loss: 156.735
+6400/69092	Loss: 158.633
+9600/69092	Loss: 158.713
+12800/69092	Loss: 156.107
+16000/69092	Loss: 159.507
+19200/69092	Loss: 157.209
+22400/69092	Loss: 157.614
+25600/69092	Loss: 155.762
+28800/69092	Loss: 157.695
+32000/69092	Loss: 159.135
+35200/69092	Loss: 156.995
+38400/69092	Loss: 156.430
+41600/69092	Loss: 153.220
+44800/69092	Loss: 157.828
+48000/69092	Loss: 156.284
+51200/69092	Loss: 157.853
+54400/69092	Loss: 155.137
+57600/69092	Loss: 158.350
+60800/69092	Loss: 157.934
+64000/69092	Loss: 159.661
+67200/69092	Loss: 158.552
+Training time 0:07:40.269336
+Epoch: 220 Average loss: 157.38
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 643)
+0/69092	Loss: 153.594
+3200/69092	Loss: 154.537
+6400/69092	Loss: 160.754
+9600/69092	Loss: 155.823
+12800/69092	Loss: 160.722
+16000/69092	Loss: 158.272
+19200/69092	Loss: 157.110
+22400/69092	Loss: 157.591
+25600/69092	Loss: 156.688
+28800/69092	Loss: 157.240
+32000/69092	Loss: 157.917
+35200/69092	Loss: 157.478
+38400/69092	Loss: 158.463
+41600/69092	Loss: 155.253
+44800/69092	Loss: 157.915
+48000/69092	Loss: 160.178
+51200/69092	Loss: 156.033
+54400/69092	Loss: 159.377
+57600/69092	Loss: 155.823
+60800/69092	Loss: 158.618
+64000/69092	Loss: 158.516
+67200/69092	Loss: 156.348
+Training time 0:07:29.057146
+Epoch: 221 Average loss: 157.61
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 644)
+0/69092	Loss: 165.422
+3200/69092	Loss: 156.695
+6400/69092	Loss: 158.539
+9600/69092	Loss: 157.992
+12800/69092	Loss: 157.688
+16000/69092	Loss: 159.195
+19200/69092	Loss: 158.279
+22400/69092	Loss: 156.324
+25600/69092	Loss: 157.026
+28800/69092	Loss: 157.665
+32000/69092	Loss: 157.597
+35200/69092	Loss: 155.522
+38400/69092	Loss: 155.558
+41600/69092	Loss: 159.187
+44800/69092	Loss: 155.394
+48000/69092	Loss: 159.829
+51200/69092	Loss: 158.002
+54400/69092	Loss: 159.767
+57600/69092	Loss: 159.285
+60800/69092	Loss: 155.716
+64000/69092	Loss: 158.566
+67200/69092	Loss: 156.444
+Training time 0:08:31.135405
+Epoch: 222 Average loss: 157.66
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 645)
+0/69092	Loss: 168.154
+3200/69092	Loss: 157.900
+6400/69092	Loss: 156.841
+9600/69092	Loss: 160.198
+12800/69092	Loss: 158.099
+16000/69092	Loss: 158.207
+19200/69092	Loss: 157.919
+22400/69092	Loss: 158.184
+25600/69092	Loss: 156.459
+28800/69092	Loss: 155.513
+32000/69092	Loss: 158.063
+35200/69092	Loss: 157.210
+38400/69092	Loss: 154.747
+41600/69092	Loss: 158.105
+44800/69092	Loss: 154.578
+48000/69092	Loss: 157.065
+51200/69092	Loss: 158.454
+54400/69092	Loss: 158.166
+57600/69092	Loss: 154.526
+60800/69092	Loss: 158.770
+64000/69092	Loss: 158.475
+67200/69092	Loss: 158.743
+Training time 0:08:34.548517
+Epoch: 223 Average loss: 157.41
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 646)
+0/69092	Loss: 165.393
+3200/69092	Loss: 156.250
+6400/69092	Loss: 158.106
+9600/69092	Loss: 156.820
+12800/69092	Loss: 159.785
+16000/69092	Loss: 159.302
+19200/69092	Loss: 157.720
+22400/69092	Loss: 156.442
+25600/69092	Loss: 154.447
+28800/69092	Loss: 157.395
+32000/69092	Loss: 155.199
+35200/69092	Loss: 157.014
+38400/69092	Loss: 156.051
+41600/69092	Loss: 160.226
+44800/69092	Loss: 155.608
+48000/69092	Loss: 158.439
+51200/69092	Loss: 157.160
+54400/69092	Loss: 160.060
+57600/69092	Loss: 156.248
+60800/69092	Loss: 159.355
+64000/69092	Loss: 158.188
+67200/69092	Loss: 158.642
+Training time 0:07:23.080956
+Epoch: 224 Average loss: 157.54
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 647)
+0/69092	Loss: 152.752
+3200/69092	Loss: 157.439
+6400/69092	Loss: 158.802
+9600/69092	Loss: 158.109
+12800/69092	Loss: 158.069
+16000/69092	Loss: 159.496
+19200/69092	Loss: 156.509
+22400/69092	Loss: 156.898
+25600/69092	Loss: 159.133
+28800/69092	Loss: 159.639
+32000/69092	Loss: 157.353
+35200/69092	Loss: 155.471
+38400/69092	Loss: 156.690
+41600/69092	Loss: 153.811
+44800/69092	Loss: 157.616
+48000/69092	Loss: 155.397
+51200/69092	Loss: 158.626
+54400/69092	Loss: 157.483
+57600/69092	Loss: 159.738
+60800/69092	Loss: 159.406
+64000/69092	Loss: 159.305
+67200/69092	Loss: 156.101
+Training time 0:07:28.639905
+Epoch: 225 Average loss: 157.58
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 648)
+0/69092	Loss: 165.204
+3200/69092	Loss: 156.710
+6400/69092	Loss: 156.687
+9600/69092	Loss: 153.931
+12800/69092	Loss: 158.072
+16000/69092	Loss: 160.193
+19200/69092	Loss: 158.714
+22400/69092	Loss: 155.951
+25600/69092	Loss: 159.136
+28800/69092	Loss: 153.546
+32000/69092	Loss: 157.509
+35200/69092	Loss: 158.651
+38400/69092	Loss: 158.493
+41600/69092	Loss: 156.138
+44800/69092	Loss: 155.734
+48000/69092	Loss: 156.357
+51200/69092	Loss: 157.247
+54400/69092	Loss: 157.459
+57600/69092	Loss: 157.807
+60800/69092	Loss: 159.110
+64000/69092	Loss: 162.848
+67200/69092	Loss: 158.559
+Training time 0:07:30.555783
+Epoch: 226 Average loss: 157.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 649)
+0/69092	Loss: 159.436
+3200/69092	Loss: 157.789
+6400/69092	Loss: 160.089
+9600/69092	Loss: 156.628
+12800/69092	Loss: 158.362
+16000/69092	Loss: 155.360
+19200/69092	Loss: 155.078
+22400/69092	Loss: 158.432
+25600/69092	Loss: 156.425
+28800/69092	Loss: 158.673
+32000/69092	Loss: 153.432
+35200/69092	Loss: 159.404
+38400/69092	Loss: 159.359
+41600/69092	Loss: 157.259
+44800/69092	Loss: 155.562
+48000/69092	Loss: 157.404
+51200/69092	Loss: 155.964
+54400/69092	Loss: 160.147
+57600/69092	Loss: 155.106
+60800/69092	Loss: 161.558
+64000/69092	Loss: 157.674
+67200/69092	Loss: 156.519
+Training time 0:07:27.343898
+Epoch: 227 Average loss: 157.45
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 650)
+0/69092	Loss: 149.842
+3200/69092	Loss: 158.026
+6400/69092	Loss: 158.612
+9600/69092	Loss: 156.117
+12800/69092	Loss: 154.649
+16000/69092	Loss: 158.555
+19200/69092	Loss: 158.747
+22400/69092	Loss: 161.806
+25600/69092	Loss: 158.291
+28800/69092	Loss: 158.494
+32000/69092	Loss: 154.675
+35200/69092	Loss: 156.707
+38400/69092	Loss: 156.160
+41600/69092	Loss: 157.002
+44800/69092	Loss: 155.868
+48000/69092	Loss: 156.845
+51200/69092	Loss: 156.971
+54400/69092	Loss: 156.629
+57600/69092	Loss: 157.007
+60800/69092	Loss: 159.208
+64000/69092	Loss: 159.291
+67200/69092	Loss: 157.110
+Training time 0:09:27.067758
+Epoch: 228 Average loss: 157.44
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 651)
+0/69092	Loss: 159.460
+3200/69092	Loss: 158.683
+6400/69092	Loss: 155.711
+9600/69092	Loss: 156.483
+12800/69092	Loss: 159.359
+16000/69092	Loss: 156.764
+19200/69092	Loss: 156.813
+22400/69092	Loss: 158.229
+25600/69092	Loss: 156.143
+28800/69092	Loss: 159.128
+32000/69092	Loss: 159.613
+35200/69092	Loss: 157.953
+38400/69092	Loss: 156.959
+41600/69092	Loss: 157.033
+44800/69092	Loss: 155.479
+48000/69092	Loss: 157.104
+51200/69092	Loss: 158.896
+54400/69092	Loss: 155.478
+57600/69092	Loss: 157.954
+60800/69092	Loss: 159.093
+64000/69092	Loss: 155.458
+67200/69092	Loss: 157.690
+Training time 0:07:39.063601
+Epoch: 229 Average loss: 157.44
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 652)
+0/69092	Loss: 147.211
+3200/69092	Loss: 156.889
+6400/69092	Loss: 158.873
+9600/69092	Loss: 154.357
+12800/69092	Loss: 157.826
+16000/69092	Loss: 160.319
+19200/69092	Loss: 156.137
+22400/69092	Loss: 155.428
+25600/69092	Loss: 159.530
+28800/69092	Loss: 158.142
+32000/69092	Loss: 158.270
+35200/69092	Loss: 155.916
+38400/69092	Loss: 158.390
+41600/69092	Loss: 158.231
+44800/69092	Loss: 157.584
+48000/69092	Loss: 160.831
+51200/69092	Loss: 157.718
+54400/69092	Loss: 158.864
+57600/69092	Loss: 155.941
+60800/69092	Loss: 159.108
+64000/69092	Loss: 156.228
+67200/69092	Loss: 158.341
+Training time 0:07:40.237119
+Epoch: 230 Average loss: 157.79
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 653)
+0/69092	Loss: 165.612
+3200/69092	Loss: 157.404
+6400/69092	Loss: 159.238
+9600/69092	Loss: 159.448
+12800/69092	Loss: 157.142
+16000/69092	Loss: 157.463
+19200/69092	Loss: 158.130
+22400/69092	Loss: 156.421
+25600/69092	Loss: 156.434
+28800/69092	Loss: 157.084
+32000/69092	Loss: 158.176
+35200/69092	Loss: 159.090
+38400/69092	Loss: 156.300
+41600/69092	Loss: 157.593
+44800/69092	Loss: 157.062
+48000/69092	Loss: 157.326
+51200/69092	Loss: 159.395
+54400/69092	Loss: 157.943
+57600/69092	Loss: 156.873
+60800/69092	Loss: 159.478
+64000/69092	Loss: 159.483
+67200/69092	Loss: 154.997
+Training time 0:07:35.400742
+Epoch: 231 Average loss: 157.71
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 654)
+0/69092	Loss: 135.142
+3200/69092	Loss: 156.664
+6400/69092	Loss: 159.073
+9600/69092	Loss: 158.802
+12800/69092	Loss: 157.453
+16000/69092	Loss: 156.378
+19200/69092	Loss: 158.038
+22400/69092	Loss: 159.764
+25600/69092	Loss: 157.333
+28800/69092	Loss: 156.931
+32000/69092	Loss: 155.577
+35200/69092	Loss: 158.228
+38400/69092	Loss: 160.355
+41600/69092	Loss: 155.534
+44800/69092	Loss: 156.046
+48000/69092	Loss: 157.863
+51200/69092	Loss: 156.395
+54400/69092	Loss: 162.240
+57600/69092	Loss: 158.858
+60800/69092	Loss: 158.871
+64000/69092	Loss: 154.907
+67200/69092	Loss: 157.596
+Training time 0:07:33.701474
+Epoch: 232 Average loss: 157.69
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 655)
+0/69092	Loss: 166.783
+3200/69092	Loss: 156.038
+6400/69092	Loss: 157.812
+9600/69092	Loss: 160.981
+12800/69092	Loss: 157.212
+16000/69092	Loss: 156.838
+19200/69092	Loss: 157.642
+22400/69092	Loss: 157.276
+25600/69092	Loss: 155.770
+28800/69092	Loss: 159.388
+32000/69092	Loss: 156.635
+35200/69092	Loss: 155.745
+38400/69092	Loss: 156.889
+41600/69092	Loss: 159.764
+44800/69092	Loss: 158.597
+48000/69092	Loss: 158.640
+51200/69092	Loss: 157.284
+54400/69092	Loss: 154.917
+57600/69092	Loss: 156.581
+60800/69092	Loss: 158.896
+64000/69092	Loss: 157.990
+67200/69092	Loss: 155.136
+Training time 0:07:34.924746
+Epoch: 233 Average loss: 157.43
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 656)
+0/69092	Loss: 152.277
+3200/69092	Loss: 161.199
+6400/69092	Loss: 156.836
+9600/69092	Loss: 156.624
+12800/69092	Loss: 157.327
+16000/69092	Loss: 158.385
+19200/69092	Loss: 160.872
+22400/69092	Loss: 154.521
+25600/69092	Loss: 157.786
+28800/69092	Loss: 157.276
+32000/69092	Loss: 158.574
+35200/69092	Loss: 156.062
+38400/69092	Loss: 157.278
+41600/69092	Loss: 155.273
+44800/69092	Loss: 158.205
+48000/69092	Loss: 161.003
+51200/69092	Loss: 158.045
+54400/69092	Loss: 154.989
+57600/69092	Loss: 156.540
+60800/69092	Loss: 156.320
+64000/69092	Loss: 159.063
+67200/69092	Loss: 158.782
+Training time 0:07:32.283646
+Epoch: 234 Average loss: 157.63
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 657)
+0/69092	Loss: 169.157
+3200/69092	Loss: 158.112
+6400/69092	Loss: 157.902
+9600/69092	Loss: 157.054
+12800/69092	Loss: 157.195
+16000/69092	Loss: 157.924
+19200/69092	Loss: 156.349
+22400/69092	Loss: 157.939
+25600/69092	Loss: 157.406
+28800/69092	Loss: 156.426
+32000/69092	Loss: 157.339
+35200/69092	Loss: 159.729
+38400/69092	Loss: 159.014
+41600/69092	Loss: 158.079
+44800/69092	Loss: 157.769
+48000/69092	Loss: 157.675
+51200/69092	Loss: 158.435
+54400/69092	Loss: 159.091
+57600/69092	Loss: 156.783
+60800/69092	Loss: 156.545
+64000/69092	Loss: 155.534
+67200/69092	Loss: 154.316
+Training time 0:07:39.845884
+Epoch: 235 Average loss: 157.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 658)
+0/69092	Loss: 167.230
+3200/69092	Loss: 156.155
+6400/69092	Loss: 156.916
+9600/69092	Loss: 156.587
+12800/69092	Loss: 158.048
+16000/69092	Loss: 156.720
+19200/69092	Loss: 160.000
+22400/69092	Loss: 157.109
+25600/69092	Loss: 158.094
+28800/69092	Loss: 157.775
+32000/69092	Loss: 161.040
+35200/69092	Loss: 157.586
+38400/69092	Loss: 159.437
+41600/69092	Loss: 158.170
+44800/69092	Loss: 157.498
+48000/69092	Loss: 156.832
+51200/69092	Loss: 156.972
+54400/69092	Loss: 157.212
+57600/69092	Loss: 154.557
+60800/69092	Loss: 156.061
+64000/69092	Loss: 159.269
+67200/69092	Loss: 154.682
+Training time 0:07:58.555641
+Epoch: 236 Average loss: 157.39
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 659)
+0/69092	Loss: 163.321
+3200/69092	Loss: 156.580
+6400/69092	Loss: 159.103
+9600/69092	Loss: 156.652
+12800/69092	Loss: 161.733
+16000/69092	Loss: 158.861
+19200/69092	Loss: 157.690
+22400/69092	Loss: 159.509
+25600/69092	Loss: 154.750
+28800/69092	Loss: 156.892
+32000/69092	Loss: 154.900
+35200/69092	Loss: 158.736
+38400/69092	Loss: 159.680
+41600/69092	Loss: 156.126
+44800/69092	Loss: 157.815
+48000/69092	Loss: 155.897
+51200/69092	Loss: 156.146
+54400/69092	Loss: 156.602
+57600/69092	Loss: 159.568
+60800/69092	Loss: 158.433
+64000/69092	Loss: 156.584
+67200/69092	Loss: 156.818
+Training time 0:07:47.349364
+Epoch: 237 Average loss: 157.57
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 660)
+0/69092	Loss: 157.487
+3200/69092	Loss: 158.543
+6400/69092	Loss: 156.723
+9600/69092	Loss: 158.471
+12800/69092	Loss: 157.595
+16000/69092	Loss: 156.657
+19200/69092	Loss: 154.597
+22400/69092	Loss: 156.592
+25600/69092	Loss: 157.666
+28800/69092	Loss: 157.409
+32000/69092	Loss: 158.694
+35200/69092	Loss: 156.536
+38400/69092	Loss: 157.915
+41600/69092	Loss: 157.884
+44800/69092	Loss: 160.490
+48000/69092	Loss: 158.963
+51200/69092	Loss: 153.950
+54400/69092	Loss: 158.040
+57600/69092	Loss: 157.445
+60800/69092	Loss: 158.193
+64000/69092	Loss: 156.619
+67200/69092	Loss: 159.141
+Training time 0:07:38.576687
+Epoch: 238 Average loss: 157.61
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 661)
+0/69092	Loss: 140.434
+3200/69092	Loss: 157.503
+6400/69092	Loss: 158.362
+9600/69092	Loss: 159.353
+12800/69092	Loss: 157.157
+16000/69092	Loss: 155.927
+19200/69092	Loss: 157.459
+22400/69092	Loss: 159.925
+25600/69092	Loss: 156.135
+28800/69092	Loss: 159.938
+32000/69092	Loss: 159.392
+35200/69092	Loss: 155.249
+38400/69092	Loss: 157.386
+41600/69092	Loss: 155.197
+44800/69092	Loss: 157.951
+48000/69092	Loss: 154.863
+51200/69092	Loss: 157.671
+54400/69092	Loss: 156.218
+57600/69092	Loss: 160.190
+60800/69092	Loss: 157.629
+64000/69092	Loss: 160.046
+67200/69092	Loss: 159.282
+Training time 0:07:32.733046
+Epoch: 239 Average loss: 157.65
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 662)
+0/69092	Loss: 170.820
+3200/69092	Loss: 157.957
+6400/69092	Loss: 155.316
+9600/69092	Loss: 159.614
+12800/69092	Loss: 159.481
+16000/69092	Loss: 158.384
+19200/69092	Loss: 158.038
+22400/69092	Loss: 157.481
+25600/69092	Loss: 159.728
+28800/69092	Loss: 157.422
+32000/69092	Loss: 158.377
+35200/69092	Loss: 158.576
+38400/69092	Loss: 156.419
+41600/69092	Loss: 157.921
+44800/69092	Loss: 157.281
+48000/69092	Loss: 154.419
+51200/69092	Loss: 154.820
+54400/69092	Loss: 154.779
+57600/69092	Loss: 155.158
+60800/69092	Loss: 157.255
+64000/69092	Loss: 159.551
+67200/69092	Loss: 158.003
+Training time 0:07:43.609744
+Epoch: 240 Average loss: 157.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 663)
+0/69092	Loss: 178.682
+3200/69092	Loss: 156.709
+6400/69092	Loss: 156.846
+9600/69092	Loss: 157.574
+12800/69092	Loss: 155.808
+16000/69092	Loss: 157.887
+19200/69092	Loss: 157.215
+22400/69092	Loss: 156.989
+25600/69092	Loss: 157.277
+28800/69092	Loss: 158.370
+32000/69092	Loss: 156.660
+35200/69092	Loss: 159.573
+38400/69092	Loss: 160.505
+41600/69092	Loss: 157.373
+44800/69092	Loss: 157.142
+48000/69092	Loss: 157.022
+51200/69092	Loss: 156.562
+54400/69092	Loss: 155.457
+57600/69092	Loss: 157.330
+60800/69092	Loss: 158.825
+64000/69092	Loss: 157.376
+67200/69092	Loss: 156.851
+Training time 0:07:41.978073
+Epoch: 241 Average loss: 157.48
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 664)
+0/69092	Loss: 159.727
+3200/69092	Loss: 157.929
+6400/69092	Loss: 159.463
+9600/69092	Loss: 157.586
+12800/69092	Loss: 155.757
+16000/69092	Loss: 160.154
+19200/69092	Loss: 156.907
+22400/69092	Loss: 156.835
+25600/69092	Loss: 158.434
+28800/69092	Loss: 158.155
+32000/69092	Loss: 156.614
+35200/69092	Loss: 158.101
+38400/69092	Loss: 156.382
+41600/69092	Loss: 157.202
+44800/69092	Loss: 156.553
+48000/69092	Loss: 158.516
+51200/69092	Loss: 157.882
+54400/69092	Loss: 157.532
+57600/69092	Loss: 159.226
+60800/69092	Loss: 157.566
+64000/69092	Loss: 156.436
+67200/69092	Loss: 155.050
+Training time 0:07:36.172927
+Epoch: 242 Average loss: 157.58
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 665)
+0/69092	Loss: 164.934
+3200/69092	Loss: 159.192
+6400/69092	Loss: 157.854
+9600/69092	Loss: 155.690
+12800/69092	Loss: 156.738
+16000/69092	Loss: 157.358
+19200/69092	Loss: 158.618
+22400/69092	Loss: 156.325
+25600/69092	Loss: 154.404
+28800/69092	Loss: 158.225
+32000/69092	Loss: 157.006
+35200/69092	Loss: 156.456
+38400/69092	Loss: 159.631
+41600/69092	Loss: 156.939
+44800/69092	Loss: 158.114
+48000/69092	Loss: 157.912
+51200/69092	Loss: 154.870
+54400/69092	Loss: 159.142
+57600/69092	Loss: 160.029
+60800/69092	Loss: 155.246
+64000/69092	Loss: 160.011
+67200/69092	Loss: 157.988
+Training time 0:07:33.959249
+Epoch: 243 Average loss: 157.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 666)
+0/69092	Loss: 165.088
+3200/69092	Loss: 155.538
+6400/69092	Loss: 157.139
+9600/69092	Loss: 157.152
+12800/69092	Loss: 158.106
+16000/69092	Loss: 156.606
+19200/69092	Loss: 156.542
+22400/69092	Loss: 155.602
+25600/69092	Loss: 157.769
+28800/69092	Loss: 155.845
+32000/69092	Loss: 161.616
+35200/69092	Loss: 158.078
+38400/69092	Loss: 154.961
+41600/69092	Loss: 159.019
+44800/69092	Loss: 158.107
+48000/69092	Loss: 157.880
+51200/69092	Loss: 159.080
+54400/69092	Loss: 156.839
+57600/69092	Loss: 158.698
+60800/69092	Loss: 156.394
+64000/69092	Loss: 157.126
+67200/69092	Loss: 159.301
+Training time 0:07:32.989240
+Epoch: 244 Average loss: 157.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 667)
+0/69092	Loss: 152.444
+3200/69092	Loss: 157.637
+6400/69092	Loss: 156.684
+9600/69092	Loss: 154.209
+12800/69092	Loss: 156.289
+16000/69092	Loss: 158.931
+19200/69092	Loss: 159.552
+22400/69092	Loss: 155.623
+25600/69092	Loss: 159.546
+28800/69092	Loss: 155.009
+32000/69092	Loss: 157.174
+35200/69092	Loss: 158.050
+38400/69092	Loss: 158.391
+41600/69092	Loss: 155.482
+44800/69092	Loss: 156.941
+48000/69092	Loss: 156.623
+51200/69092	Loss: 158.083
+54400/69092	Loss: 161.623
+57600/69092	Loss: 155.900
+60800/69092	Loss: 157.517
+64000/69092	Loss: 157.320
+67200/69092	Loss: 159.660
+Training time 0:07:43.657413
+Epoch: 245 Average loss: 157.43
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 668)
+0/69092	Loss: 152.707
+3200/69092	Loss: 158.502
+6400/69092	Loss: 157.934
+9600/69092	Loss: 156.288
+12800/69092	Loss: 159.421
+16000/69092	Loss: 156.261
+19200/69092	Loss: 157.577
+22400/69092	Loss: 156.986
+25600/69092	Loss: 154.865
+28800/69092	Loss: 158.829
+32000/69092	Loss: 156.027
+35200/69092	Loss: 157.017
+38400/69092	Loss: 154.530
+41600/69092	Loss: 155.374
+44800/69092	Loss: 159.311
+48000/69092	Loss: 157.567
+51200/69092	Loss: 160.210
+54400/69092	Loss: 158.580
+57600/69092	Loss: 159.976
+60800/69092	Loss: 160.003
+64000/69092	Loss: 156.852
+67200/69092	Loss: 155.587
+Training time 0:07:36.121956
+Epoch: 246 Average loss: 157.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 669)
+0/69092	Loss: 181.860
+3200/69092	Loss: 157.105
+6400/69092	Loss: 155.907
+9600/69092	Loss: 156.386
+12800/69092	Loss: 157.277
+16000/69092	Loss: 156.455
+19200/69092	Loss: 156.895
+22400/69092	Loss: 157.734
+25600/69092	Loss: 157.851
+28800/69092	Loss: 158.176
+32000/69092	Loss: 156.525
+35200/69092	Loss: 154.914
+38400/69092	Loss: 157.737
+41600/69092	Loss: 157.862
+44800/69092	Loss: 158.928
+48000/69092	Loss: 159.542
+51200/69092	Loss: 157.113
+54400/69092	Loss: 158.738
+57600/69092	Loss: 156.704
+60800/69092	Loss: 157.582
+64000/69092	Loss: 159.843
+67200/69092	Loss: 157.081
+Training time 0:07:36.995088
+Epoch: 247 Average loss: 157.61
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 670)
+0/69092	Loss: 152.530
+3200/69092	Loss: 156.265
+6400/69092	Loss: 155.189
+9600/69092	Loss: 156.064
+12800/69092	Loss: 158.366
+16000/69092	Loss: 159.182
+19200/69092	Loss: 157.137
+22400/69092	Loss: 156.787
+25600/69092	Loss: 160.494
+28800/69092	Loss: 155.822
+32000/69092	Loss: 156.550
+35200/69092	Loss: 155.756
+38400/69092	Loss: 155.000
+41600/69092	Loss: 155.665
+44800/69092	Loss: 160.296
+48000/69092	Loss: 159.049
+51200/69092	Loss: 159.516
+54400/69092	Loss: 161.067
+57600/69092	Loss: 154.574
+60800/69092	Loss: 159.237
+64000/69092	Loss: 157.746
+67200/69092	Loss: 160.311
+Training time 0:07:35.345169
+Epoch: 248 Average loss: 157.58
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 671)
+0/69092	Loss: 162.783
+3200/69092	Loss: 157.681
+6400/69092	Loss: 158.285
+9600/69092	Loss: 159.105
+12800/69092	Loss: 157.653
+16000/69092	Loss: 158.883
+19200/69092	Loss: 153.858
+22400/69092	Loss: 156.370
+25600/69092	Loss: 157.553
+28800/69092	Loss: 155.266
+32000/69092	Loss: 154.497
+35200/69092	Loss: 159.008
+38400/69092	Loss: 156.035
+41600/69092	Loss: 157.882
+44800/69092	Loss: 158.786
+48000/69092	Loss: 156.896
+51200/69092	Loss: 157.845
+54400/69092	Loss: 157.316
+57600/69092	Loss: 158.213
+60800/69092	Loss: 156.744
+64000/69092	Loss: 155.998
+67200/69092	Loss: 159.556
+Training time 0:07:43.588049
+Epoch: 249 Average loss: 157.24
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 672)
+0/69092	Loss: 145.406
+3200/69092	Loss: 158.839
+6400/69092	Loss: 156.912
+9600/69092	Loss: 159.930
+12800/69092	Loss: 157.382
+16000/69092	Loss: 154.219
+19200/69092	Loss: 159.020
+22400/69092	Loss: 156.271
+25600/69092	Loss: 154.495
+28800/69092	Loss: 157.481
+32000/69092	Loss: 158.202
+35200/69092	Loss: 158.609
+38400/69092	Loss: 155.990
+41600/69092	Loss: 155.685
+44800/69092	Loss: 158.223
+48000/69092	Loss: 157.648
+51200/69092	Loss: 158.530
+54400/69092	Loss: 156.836
+57600/69092	Loss: 156.824
+60800/69092	Loss: 157.565
+64000/69092	Loss: 158.570
+67200/69092	Loss: 159.140
+Training time 0:07:39.737410
+Epoch: 250 Average loss: 157.53
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 673)
+0/69092	Loss: 157.635
+3200/69092	Loss: 158.552
+6400/69092	Loss: 156.030
+9600/69092	Loss: 160.073
+12800/69092	Loss: 157.446
+16000/69092	Loss: 159.477
+19200/69092	Loss: 155.846
+22400/69092	Loss: 156.788
+25600/69092	Loss: 157.874
+28800/69092	Loss: 158.564
+32000/69092	Loss: 156.002
+35200/69092	Loss: 153.275
+38400/69092	Loss: 155.809
+41600/69092	Loss: 157.106
+44800/69092	Loss: 158.700
+48000/69092	Loss: 156.193
+51200/69092	Loss: 157.711
+54400/69092	Loss: 155.676
+57600/69092	Loss: 158.656
+60800/69092	Loss: 158.858
+64000/69092	Loss: 160.502
+67200/69092	Loss: 158.877
+Training time 0:07:49.189809
+Epoch: 251 Average loss: 157.56
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 674)
+0/69092	Loss: 167.217
+3200/69092	Loss: 157.839
+6400/69092	Loss: 158.193
+9600/69092	Loss: 154.776
+12800/69092	Loss: 155.872
+16000/69092	Loss: 158.835
+19200/69092	Loss: 156.828
+22400/69092	Loss: 159.803
+25600/69092	Loss: 158.849
+28800/69092	Loss: 156.283
+32000/69092	Loss: 155.758
+35200/69092	Loss: 158.542
+38400/69092	Loss: 158.298
+41600/69092	Loss: 157.600
+44800/69092	Loss: 159.154
+48000/69092	Loss: 155.967
+51200/69092	Loss: 156.936
+54400/69092	Loss: 159.248
+57600/69092	Loss: 157.138
+60800/69092	Loss: 157.816
+64000/69092	Loss: 155.210
+67200/69092	Loss: 159.220
+Training time 0:07:33.072866
+Epoch: 252 Average loss: 157.60
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 675)
+0/69092	Loss: 159.543
+3200/69092	Loss: 158.999
+6400/69092	Loss: 157.556
+9600/69092	Loss: 156.440
+12800/69092	Loss: 159.147
+16000/69092	Loss: 157.413
+19200/69092	Loss: 161.325
+22400/69092	Loss: 157.194
+25600/69092	Loss: 155.274
+28800/69092	Loss: 155.720
+32000/69092	Loss: 156.870
+35200/69092	Loss: 160.702
+38400/69092	Loss: 157.420
+41600/69092	Loss: 157.496
+44800/69092	Loss: 158.645
+48000/69092	Loss: 156.718
+51200/69092	Loss: 156.572
+54400/69092	Loss: 156.028
+57600/69092	Loss: 158.541
+60800/69092	Loss: 155.314
+64000/69092	Loss: 157.135
+67200/69092	Loss: 157.360
+Training time 0:07:37.136717
+Epoch: 253 Average loss: 157.42
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 676)
+0/69092	Loss: 139.126
+3200/69092	Loss: 158.090
+6400/69092	Loss: 158.715
+9600/69092	Loss: 154.786
+12800/69092	Loss: 156.779
+16000/69092	Loss: 159.865
+19200/69092	Loss: 155.037
+22400/69092	Loss: 158.391
+25600/69092	Loss: 161.238
+28800/69092	Loss: 157.620
+32000/69092	Loss: 156.057
+35200/69092	Loss: 160.585
+38400/69092	Loss: 154.940
+41600/69092	Loss: 156.335
+44800/69092	Loss: 160.514
+48000/69092	Loss: 158.022
+51200/69092	Loss: 161.697
+54400/69092	Loss: 156.325
+57600/69092	Loss: 155.433
+60800/69092	Loss: 155.553
+64000/69092	Loss: 158.572
+67200/69092	Loss: 155.470
+Training time 0:07:32.710693
+Epoch: 254 Average loss: 157.66
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 677)
+0/69092	Loss: 165.030
+3200/69092	Loss: 157.949
+6400/69092	Loss: 158.148
+9600/69092	Loss: 158.408
+12800/69092	Loss: 157.474
+16000/69092	Loss: 158.042
+19200/69092	Loss: 156.091
+22400/69092	Loss: 156.129
+25600/69092	Loss: 157.499
+28800/69092	Loss: 158.058
+32000/69092	Loss: 158.349
+35200/69092	Loss: 157.292
+38400/69092	Loss: 155.642
+41600/69092	Loss: 159.201
+44800/69092	Loss: 157.683
+48000/69092	Loss: 154.592
+51200/69092	Loss: 158.938
+54400/69092	Loss: 159.736
+57600/69092	Loss: 156.224
+60800/69092	Loss: 158.542
+64000/69092	Loss: 158.136
+67200/69092	Loss: 156.483
+Training time 0:07:42.830556
+Epoch: 255 Average loss: 157.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 678)
+0/69092	Loss: 137.903
+3200/69092	Loss: 159.199
+6400/69092	Loss: 157.636
+9600/69092	Loss: 156.664
+12800/69092	Loss: 156.465
+16000/69092	Loss: 160.921
+19200/69092	Loss: 159.267
+22400/69092	Loss: 155.399
+25600/69092	Loss: 156.110
+28800/69092	Loss: 159.375
+32000/69092	Loss: 156.961
+35200/69092	Loss: 157.206
+38400/69092	Loss: 157.490
+41600/69092	Loss: 155.517
+44800/69092	Loss: 158.413
+48000/69092	Loss: 155.593
+51200/69092	Loss: 157.942
+54400/69092	Loss: 159.012
+57600/69092	Loss: 156.682
+60800/69092	Loss: 159.408
+64000/69092	Loss: 154.027
+67200/69092	Loss: 160.148
+Training time 0:07:37.489644
+Epoch: 256 Average loss: 157.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 679)
+0/69092	Loss: 140.880
+3200/69092	Loss: 156.649
+6400/69092	Loss: 158.730
+9600/69092	Loss: 156.898
+12800/69092	Loss: 158.728
+16000/69092	Loss: 157.619
+19200/69092	Loss: 158.391
+22400/69092	Loss: 158.116
+25600/69092	Loss: 161.976
+28800/69092	Loss: 156.874
+32000/69092	Loss: 158.399
+35200/69092	Loss: 157.130
+38400/69092	Loss: 157.954
+41600/69092	Loss: 156.492
+44800/69092	Loss: 155.536
+48000/69092	Loss: 155.078
+51200/69092	Loss: 156.746
+54400/69092	Loss: 158.005
+57600/69092	Loss: 156.873
+60800/69092	Loss: 153.324
+64000/69092	Loss: 157.212
+67200/69092	Loss: 156.518
+Training time 0:08:41.812492
+Epoch: 257 Average loss: 157.36
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 680)
+0/69092	Loss: 138.184
+3200/69092	Loss: 156.718
+6400/69092	Loss: 158.124
+9600/69092	Loss: 154.938
+12800/69092	Loss: 158.232
+16000/69092	Loss: 156.993
+19200/69092	Loss: 159.702
+22400/69092	Loss: 157.015
+25600/69092	Loss: 159.666
+28800/69092	Loss: 159.700
+32000/69092	Loss: 157.899
+35200/69092	Loss: 156.194
+38400/69092	Loss: 159.429
+41600/69092	Loss: 157.223
+44800/69092	Loss: 157.274
+48000/69092	Loss: 160.449
+51200/69092	Loss: 155.574
+54400/69092	Loss: 155.937
+57600/69092	Loss: 157.231
+60800/69092	Loss: 158.693
+64000/69092	Loss: 156.158
+67200/69092	Loss: 157.720
+Training time 0:07:40.897864
+Epoch: 258 Average loss: 157.49
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 681)
+0/69092	Loss: 124.902
+3200/69092	Loss: 158.009
+6400/69092	Loss: 160.588
+9600/69092	Loss: 155.904
+12800/69092	Loss: 155.931
+16000/69092	Loss: 156.695
+19200/69092	Loss: 156.970
+22400/69092	Loss: 157.453
+25600/69092	Loss: 156.306
+28800/69092	Loss: 157.191
+32000/69092	Loss: 160.078
+35200/69092	Loss: 158.584
+38400/69092	Loss: 155.771
+41600/69092	Loss: 157.530
+44800/69092	Loss: 156.359
+48000/69092	Loss: 158.986
+51200/69092	Loss: 157.743
+54400/69092	Loss: 160.276
+57600/69092	Loss: 156.841
+60800/69092	Loss: 156.391
+64000/69092	Loss: 158.078
+67200/69092	Loss: 155.318
+Training time 0:07:41.677996
+Epoch: 259 Average loss: 157.45
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 682)
+0/69092	Loss: 150.735
+3200/69092	Loss: 157.969
+6400/69092	Loss: 157.329
+9600/69092	Loss: 158.551
+12800/69092	Loss: 159.620
+16000/69092	Loss: 157.743
+19200/69092	Loss: 159.034
+22400/69092	Loss: 156.136
+25600/69092	Loss: 155.416
+28800/69092	Loss: 155.967
+32000/69092	Loss: 155.474
+35200/69092	Loss: 159.902
+38400/69092	Loss: 157.254
+41600/69092	Loss: 157.093
+44800/69092	Loss: 157.005
+48000/69092	Loss: 156.092
+51200/69092	Loss: 158.366
+54400/69092	Loss: 158.418
+57600/69092	Loss: 157.654
+60800/69092	Loss: 155.939
+64000/69092	Loss: 158.255
+67200/69092	Loss: 159.384
+Training time 0:07:35.529990
+Epoch: 260 Average loss: 157.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 683)
+0/69092	Loss: 150.084
+3200/69092	Loss: 156.844
+6400/69092	Loss: 156.512
+9600/69092	Loss: 156.607
+12800/69092	Loss: 156.718
+16000/69092	Loss: 157.412
+19200/69092	Loss: 157.445
+22400/69092	Loss: 157.137
+25600/69092	Loss: 157.410
+28800/69092	Loss: 156.848
+32000/69092	Loss: 157.330
+35200/69092	Loss: 157.259
+38400/69092	Loss: 159.093
+41600/69092	Loss: 157.905
+44800/69092	Loss: 155.528
+48000/69092	Loss: 156.322
+51200/69092	Loss: 158.055
+54400/69092	Loss: 158.270
+57600/69092	Loss: 159.768
+60800/69092	Loss: 157.772
+64000/69092	Loss: 159.548
+67200/69092	Loss: 158.298
+Training time 0:07:28.478459
+Epoch: 261 Average loss: 157.50
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 684)
+0/69092	Loss: 171.561
+3200/69092	Loss: 157.923
+6400/69092	Loss: 159.139
+9600/69092	Loss: 156.244
+12800/69092	Loss: 161.067
+16000/69092	Loss: 158.863
+19200/69092	Loss: 160.395
+22400/69092	Loss: 155.792
+25600/69092	Loss: 157.610
+28800/69092	Loss: 158.492
+32000/69092	Loss: 157.127
+35200/69092	Loss: 156.017
+38400/69092	Loss: 157.327
+41600/69092	Loss: 156.312
+44800/69092	Loss: 157.014
+48000/69092	Loss: 155.458
+51200/69092	Loss: 154.266
+54400/69092	Loss: 162.097
+57600/69092	Loss: 159.459
+60800/69092	Loss: 156.189
+64000/69092	Loss: 155.786
+67200/69092	Loss: 158.530
+Training time 0:07:43.058545
+Epoch: 262 Average loss: 157.62
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 685)
+0/69092	Loss: 167.708
+3200/69092	Loss: 158.033
+6400/69092	Loss: 157.344
+9600/69092	Loss: 157.700
+12800/69092	Loss: 155.776
+16000/69092	Loss: 158.295
+19200/69092	Loss: 159.296
+22400/69092	Loss: 159.852
+25600/69092	Loss: 157.460
+28800/69092	Loss: 158.619
+32000/69092	Loss: 157.040
+35200/69092	Loss: 156.105
+38400/69092	Loss: 156.671
+41600/69092	Loss: 157.075
+44800/69092	Loss: 158.154
+48000/69092	Loss: 154.487
+51200/69092	Loss: 155.113
+54400/69092	Loss: 160.538
+57600/69092	Loss: 155.589
+60800/69092	Loss: 157.508
+64000/69092	Loss: 160.337
+67200/69092	Loss: 154.938
+Training time 0:07:31.899714
+Epoch: 263 Average loss: 157.46
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 686)
+0/69092	Loss: 137.668
+3200/69092	Loss: 157.111
+6400/69092	Loss: 160.522
+9600/69092	Loss: 157.502
+12800/69092	Loss: 156.576
+16000/69092	Loss: 157.174
+19200/69092	Loss: 156.528
+22400/69092	Loss: 155.604
+25600/69092	Loss: 158.396
+28800/69092	Loss: 162.261
+32000/69092	Loss: 156.578
+35200/69092	Loss: 154.026
+38400/69092	Loss: 157.737
+41600/69092	Loss: 159.060
+44800/69092	Loss: 157.753
+48000/69092	Loss: 158.761
+51200/69092	Loss: 157.040
+54400/69092	Loss: 158.709
+57600/69092	Loss: 154.255
+60800/69092	Loss: 156.416
+64000/69092	Loss: 160.261
+67200/69092	Loss: 158.212
+Training time 0:07:34.499681
+Epoch: 264 Average loss: 157.54
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 687)
+0/69092	Loss: 164.637
+3200/69092	Loss: 156.188
+6400/69092	Loss: 157.435
+9600/69092	Loss: 160.656
+12800/69092	Loss: 157.974
+16000/69092	Loss: 157.627
+19200/69092	Loss: 155.596
+22400/69092	Loss: 158.257
+25600/69092	Loss: 158.706
+28800/69092	Loss: 157.658
+32000/69092	Loss: 155.946
+35200/69092	Loss: 156.116
+38400/69092	Loss: 157.252
+41600/69092	Loss: 158.349
+44800/69092	Loss: 156.059
+48000/69092	Loss: 156.505
+51200/69092	Loss: 159.020
+54400/69092	Loss: 156.486
+57600/69092	Loss: 159.544
+60800/69092	Loss: 157.354
+64000/69092	Loss: 159.575
+67200/69092	Loss: 159.196
+Training time 0:07:38.920540
+Epoch: 265 Average loss: 157.64
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 688)
+0/69092	Loss: 149.948
+3200/69092	Loss: 155.691
+6400/69092	Loss: 154.476
+9600/69092	Loss: 158.929
+12800/69092	Loss: 157.492
+16000/69092	Loss: 154.655
+19200/69092	Loss: 156.833
+22400/69092	Loss: 157.460
+25600/69092	Loss: 156.317
+28800/69092	Loss: 160.404
+32000/69092	Loss: 157.536
+35200/69092	Loss: 158.176
+38400/69092	Loss: 158.255
+41600/69092	Loss: 159.151
+44800/69092	Loss: 159.288
+48000/69092	Loss: 156.109
+51200/69092	Loss: 158.000
+54400/69092	Loss: 158.139
+57600/69092	Loss: 160.240
+60800/69092	Loss: 156.146
+64000/69092	Loss: 158.478
+67200/69092	Loss: 156.057
+Training time 0:07:41.304395
+Epoch: 266 Average loss: 157.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 689)
+0/69092	Loss: 154.804
+3200/69092	Loss: 157.990
+6400/69092	Loss: 159.491
+9600/69092	Loss: 157.213
+12800/69092	Loss: 158.820
+16000/69092	Loss: 157.402
+19200/69092	Loss: 157.387
+22400/69092	Loss: 154.706
+25600/69092	Loss: 155.631
+28800/69092	Loss: 157.437
+32000/69092	Loss: 155.631
+35200/69092	Loss: 157.743
+38400/69092	Loss: 158.059
+41600/69092	Loss: 157.678
+44800/69092	Loss: 158.915
+48000/69092	Loss: 159.970
+51200/69092	Loss: 158.124
+54400/69092	Loss: 157.595
+57600/69092	Loss: 158.616
+60800/69092	Loss: 156.601
+64000/69092	Loss: 157.488
+67200/69092	Loss: 158.032
+Training time 0:07:35.257852
+Epoch: 267 Average loss: 157.72
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 690)
+0/69092	Loss: 151.060
+3200/69092	Loss: 156.749
+6400/69092	Loss: 151.717
+9600/69092	Loss: 157.937
+12800/69092	Loss: 157.876
+16000/69092	Loss: 157.827
+19200/69092	Loss: 158.120
+22400/69092	Loss: 157.076
+25600/69092	Loss: 157.360
+28800/69092	Loss: 158.850
+32000/69092	Loss: 160.067
+35200/69092	Loss: 157.814
+38400/69092	Loss: 156.714
+41600/69092	Loss: 155.541
+44800/69092	Loss: 157.782
+48000/69092	Loss: 158.179
+51200/69092	Loss: 158.315
+54400/69092	Loss: 158.555
+57600/69092	Loss: 157.713
+60800/69092	Loss: 157.374
+64000/69092	Loss: 158.540
+67200/69092	Loss: 155.107
+Training time 0:07:36.847943
+Epoch: 268 Average loss: 157.38
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 691)
+0/69092	Loss: 146.647
+3200/69092	Loss: 160.471
+6400/69092	Loss: 157.051
+9600/69092	Loss: 158.092
+12800/69092	Loss: 157.591
+16000/69092	Loss: 157.686
+19200/69092	Loss: 151.771
+22400/69092	Loss: 158.309
+25600/69092	Loss: 157.546
+28800/69092	Loss: 159.462
+32000/69092	Loss: 158.719
+35200/69092	Loss: 157.994
+38400/69092	Loss: 155.524
+41600/69092	Loss: 154.891
+44800/69092	Loss: 158.220
+48000/69092	Loss: 160.938
+51200/69092	Loss: 159.594
+54400/69092	Loss: 156.666
+57600/69092	Loss: 155.518
+60800/69092	Loss: 157.903
+64000/69092	Loss: 158.688
+67200/69092	Loss: 155.682
+Training time 0:07:41.583010
+Epoch: 269 Average loss: 157.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 692)
+0/69092	Loss: 156.220
+3200/69092	Loss: 153.789
+6400/69092	Loss: 156.208
+9600/69092	Loss: 156.981
+12800/69092	Loss: 156.991
+16000/69092	Loss: 159.575
+19200/69092	Loss: 157.275
+22400/69092	Loss: 159.398
+25600/69092	Loss: 156.132
+28800/69092	Loss: 158.873
+32000/69092	Loss: 156.328
+35200/69092	Loss: 157.530
+38400/69092	Loss: 155.022
+41600/69092	Loss: 157.293
+44800/69092	Loss: 156.530
+48000/69092	Loss: 159.617
+51200/69092	Loss: 157.754
+54400/69092	Loss: 155.890
+57600/69092	Loss: 160.574
+60800/69092	Loss: 159.995
+64000/69092	Loss: 157.530
+67200/69092	Loss: 156.858
+Training time 0:07:41.562144
+Epoch: 270 Average loss: 157.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 693)
+0/69092	Loss: 172.112
+3200/69092	Loss: 160.308
+6400/69092	Loss: 162.254
+9600/69092	Loss: 160.804
+12800/69092	Loss: 156.522
+16000/69092	Loss: 157.060
+19200/69092	Loss: 157.016
+22400/69092	Loss: 156.770
+25600/69092	Loss: 157.280
+28800/69092	Loss: 158.316
+32000/69092	Loss: 160.076
+35200/69092	Loss: 156.920
+38400/69092	Loss: 155.420
+41600/69092	Loss: 160.004
+44800/69092	Loss: 155.001
+48000/69092	Loss: 157.122
+51200/69092	Loss: 155.133
+54400/69092	Loss: 154.623
+57600/69092	Loss: 159.797
+60800/69092	Loss: 156.337
+64000/69092	Loss: 157.381
+67200/69092	Loss: 155.793
+Training time 0:07:30.729852
+Epoch: 271 Average loss: 157.58
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 694)
+0/69092	Loss: 167.680
+3200/69092	Loss: 156.980
+6400/69092	Loss: 155.884
+9600/69092	Loss: 159.285
+12800/69092	Loss: 158.853
+16000/69092	Loss: 161.585
+19200/69092	Loss: 158.043
+22400/69092	Loss: 156.746
+25600/69092	Loss: 158.053
+28800/69092	Loss: 157.132
+32000/69092	Loss: 153.829
+35200/69092	Loss: 156.670
+38400/69092	Loss: 158.647
+41600/69092	Loss: 155.072
+44800/69092	Loss: 160.985
+48000/69092	Loss: 157.775
+51200/69092	Loss: 154.770
+54400/69092	Loss: 157.964
+57600/69092	Loss: 157.510
+60800/69092	Loss: 157.228
+64000/69092	Loss: 156.659
+67200/69092	Loss: 157.305
+Training time 0:07:43.524459
+Epoch: 272 Average loss: 157.49
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 695)
+0/69092	Loss: 167.797
+3200/69092	Loss: 158.578
+6400/69092	Loss: 154.811
+9600/69092	Loss: 160.185
+12800/69092	Loss: 155.726
+16000/69092	Loss: 159.100
+19200/69092	Loss: 158.056
+22400/69092	Loss: 161.618
+25600/69092	Loss: 159.943
+28800/69092	Loss: 156.218
+32000/69092	Loss: 158.256
+35200/69092	Loss: 153.625
+38400/69092	Loss: 156.100
+41600/69092	Loss: 155.861
+44800/69092	Loss: 157.910
+48000/69092	Loss: 159.175
+51200/69092	Loss: 157.337
+54400/69092	Loss: 157.381
+57600/69092	Loss: 156.793
+60800/69092	Loss: 156.070
+64000/69092	Loss: 157.054
+67200/69092	Loss: 159.082
+Training time 0:07:35.160484
+Epoch: 273 Average loss: 157.58
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 696)
+0/69092	Loss: 146.389
+3200/69092	Loss: 157.123
+6400/69092	Loss: 159.981
+9600/69092	Loss: 157.355
+12800/69092	Loss: 156.907
+16000/69092	Loss: 156.149
+19200/69092	Loss: 157.529
+22400/69092	Loss: 158.127
+25600/69092	Loss: 159.885
+28800/69092	Loss: 155.712
+32000/69092	Loss: 157.550
+35200/69092	Loss: 155.854
+38400/69092	Loss: 156.630
+41600/69092	Loss: 158.318
+44800/69092	Loss: 157.748
+48000/69092	Loss: 160.435
+51200/69092	Loss: 158.422
+54400/69092	Loss: 156.895
+57600/69092	Loss: 155.758
+60800/69092	Loss: 158.355
+64000/69092	Loss: 155.057
+67200/69092	Loss: 157.523
+Training time 0:07:50.876576
+Epoch: 274 Average loss: 157.45
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 697)
+0/69092	Loss: 142.083
+3200/69092	Loss: 159.597
+6400/69092	Loss: 157.307
+9600/69092	Loss: 151.973
+12800/69092	Loss: 158.961
+16000/69092	Loss: 158.612
+19200/69092	Loss: 156.589
+22400/69092	Loss: 158.650
+25600/69092	Loss: 158.789
+28800/69092	Loss: 155.355
+32000/69092	Loss: 156.042
+35200/69092	Loss: 158.158
+38400/69092	Loss: 157.172
+41600/69092	Loss: 159.512
+44800/69092	Loss: 160.031
+48000/69092	Loss: 158.648
+51200/69092	Loss: 159.265
+54400/69092	Loss: 158.366
+57600/69092	Loss: 158.198
+60800/69092	Loss: 156.951
+64000/69092	Loss: 156.118
+67200/69092	Loss: 155.880
+Training time 0:07:33.697046
+Epoch: 275 Average loss: 157.63
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 698)
+0/69092	Loss: 171.321
+3200/69092	Loss: 155.661
+6400/69092	Loss: 155.586
+9600/69092	Loss: 157.672
+12800/69092	Loss: 154.750
+16000/69092	Loss: 157.793
+19200/69092	Loss: 158.272
+22400/69092	Loss: 157.810
+25600/69092	Loss: 160.113
+28800/69092	Loss: 158.394
+32000/69092	Loss: 158.593
+35200/69092	Loss: 155.887
+38400/69092	Loss: 160.003
+41600/69092	Loss: 154.201
+44800/69092	Loss: 158.239
+48000/69092	Loss: 157.998
+51200/69092	Loss: 156.685
+54400/69092	Loss: 156.268
+57600/69092	Loss: 157.000
+60800/69092	Loss: 157.273
+64000/69092	Loss: 158.987
+67200/69092	Loss: 157.873
+Training time 0:07:36.726057
+Epoch: 276 Average loss: 157.49
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 699)
+0/69092	Loss: 167.596
+3200/69092	Loss: 157.971
+6400/69092	Loss: 156.976
+9600/69092	Loss: 155.775
+12800/69092	Loss: 157.938
+16000/69092	Loss: 156.099
+19200/69092	Loss: 157.671
+22400/69092	Loss: 158.223
+25600/69092	Loss: 156.549
+28800/69092	Loss: 157.698
+32000/69092	Loss: 158.130
+35200/69092	Loss: 158.142
+38400/69092	Loss: 156.906
+41600/69092	Loss: 158.899
+44800/69092	Loss: 155.386
+48000/69092	Loss: 160.891
+51200/69092	Loss: 157.796
+54400/69092	Loss: 154.575
+57600/69092	Loss: 156.941
+60800/69092	Loss: 156.318
+64000/69092	Loss: 158.514
+67200/69092	Loss: 159.779
+Training time 0:07:37.367831
+Epoch: 277 Average loss: 157.55
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 700)
+0/69092	Loss: 165.296
+3200/69092	Loss: 160.373
+6400/69092	Loss: 157.965
+9600/69092	Loss: 157.980
+12800/69092	Loss: 157.789
+16000/69092	Loss: 157.404
+19200/69092	Loss: 159.235
+22400/69092	Loss: 157.438
+25600/69092	Loss: 156.843
+28800/69092	Loss: 156.713
+32000/69092	Loss: 155.818
+35200/69092	Loss: 156.167
+38400/69092	Loss: 155.093
+41600/69092	Loss: 157.651
+44800/69092	Loss: 160.103
+48000/69092	Loss: 155.808
+51200/69092	Loss: 157.302
+54400/69092	Loss: 159.865
+57600/69092	Loss: 158.357
+60800/69092	Loss: 155.599
+64000/69092	Loss: 156.140
+67200/69092	Loss: 154.441
+Training time 0:07:38.408207
+Epoch: 278 Average loss: 157.40
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 701)
+0/69092	Loss: 147.480
+3200/69092	Loss: 157.266
+6400/69092	Loss: 154.348
+9600/69092	Loss: 158.170
+12800/69092	Loss: 156.369
+16000/69092	Loss: 157.915
+19200/69092	Loss: 159.682
+22400/69092	Loss: 156.452
+25600/69092	Loss: 156.686
+28800/69092	Loss: 157.188
+32000/69092	Loss: 158.046
+35200/69092	Loss: 158.989
+38400/69092	Loss: 157.229
+41600/69092	Loss: 155.170
+44800/69092	Loss: 161.901
+48000/69092	Loss: 156.488
+51200/69092	Loss: 158.907
+54400/69092	Loss: 156.270
+57600/69092	Loss: 156.652
+60800/69092	Loss: 157.642
+64000/69092	Loss: 158.532
+67200/69092	Loss: 158.501
+Training time 0:07:36.663876
+Epoch: 279 Average loss: 157.45
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 702)
+0/69092	Loss: 152.062
+3200/69092	Loss: 157.108
+6400/69092	Loss: 156.663
+9600/69092	Loss: 157.127
+12800/69092	Loss: 158.631
+16000/69092	Loss: 159.611
+19200/69092	Loss: 158.040
+22400/69092	Loss: 159.395
+25600/69092	Loss: 156.501
+28800/69092	Loss: 155.584
+32000/69092	Loss: 156.305
+35200/69092	Loss: 153.902
+38400/69092	Loss: 160.102
+41600/69092	Loss: 159.699
+44800/69092	Loss: 156.850
+48000/69092	Loss: 157.765
+51200/69092	Loss: 156.288
+54400/69092	Loss: 158.632
+57600/69092	Loss: 159.344
+60800/69092	Loss: 158.614
+64000/69092	Loss: 155.630
+67200/69092	Loss: 154.872
+Training time 0:07:33.220694
+Epoch: 280 Average loss: 157.51
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 703)
+0/69092	Loss: 131.567
+3200/69092	Loss: 158.315
+6400/69092	Loss: 158.409
+9600/69092	Loss: 156.568
+12800/69092	Loss: 156.065
+16000/69092	Loss: 156.406
+19200/69092	Loss: 156.014
+22400/69092	Loss: 157.036
+25600/69092	Loss: 155.302
+28800/69092	Loss: 157.809
+32000/69092	Loss: 158.977
+35200/69092	Loss: 161.593
+38400/69092	Loss: 158.303
+41600/69092	Loss: 159.882
+44800/69092	Loss: 160.027
+48000/69092	Loss: 156.316
+51200/69092	Loss: 158.364
+54400/69092	Loss: 158.806
+57600/69092	Loss: 155.088
+60800/69092	Loss: 155.857
+64000/69092	Loss: 155.195
+67200/69092	Loss: 158.472
+Training time 0:08:06.428184
+Epoch: 281 Average loss: 157.63
+=> saved checkpoint 'trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last' (iter 704)
+0/69092	Loss: 154.389
+3200/69092	Loss: 153.969
diff --git a/OAR.2073652.stderr b/OAR.2073652.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..dbc93daec1078dca62d7b6d8b3d9de249fee0417
--- /dev/null
+++ b/OAR.2073652.stderr
@@ -0,0 +1,3 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+## OAR [2020-07-06 17:08:45] Job 2073652 KILLED ##
diff --git a/OAR.2073652.stdout b/OAR.2073652.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..6a569987b3b07bb6b39c1500394b839098652d16
--- /dev/null
+++ b/OAR.2073652.stdout
@@ -0,0 +1,4535 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64_ls_5', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=5, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+Tesla K80
+Tesla K80
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=10, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=5, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 761485
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last (iter 469)'
+0/69092	Loss: 135.538
+3200/69092	Loss: 135.969
+6400/69092	Loss: 137.192
+9600/69092	Loss: 140.028
+12800/69092	Loss: 138.366
+16000/69092	Loss: 137.522
+19200/69092	Loss: 139.420
+22400/69092	Loss: 135.316
+25600/69092	Loss: 138.027
+28800/69092	Loss: 137.690
+32000/69092	Loss: 138.593
+35200/69092	Loss: 136.212
+38400/69092	Loss: 139.847
+41600/69092	Loss: 138.461
+44800/69092	Loss: 133.852
+48000/69092	Loss: 139.049
+51200/69092	Loss: 138.220
+54400/69092	Loss: 138.660
+57600/69092	Loss: 137.624
+60800/69092	Loss: 139.481
+64000/69092	Loss: 139.207
+67200/69092	Loss: 139.778
+Training time 0:10:50.309535
+Epoch: 1 Average loss: 138.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 470)
+0/69092	Loss: 155.394
+3200/69092	Loss: 139.534
+6400/69092	Loss: 137.487
+9600/69092	Loss: 138.845
+12800/69092	Loss: 136.582
+16000/69092	Loss: 136.198
+19200/69092	Loss: 136.659
+22400/69092	Loss: 139.602
+25600/69092	Loss: 137.535
+28800/69092	Loss: 137.933
+32000/69092	Loss: 138.951
+35200/69092	Loss: 138.145
+38400/69092	Loss: 137.581
+41600/69092	Loss: 139.672
+44800/69092	Loss: 138.085
+48000/69092	Loss: 139.772
+51200/69092	Loss: 136.350
+54400/69092	Loss: 135.653
+57600/69092	Loss: 138.363
+60800/69092	Loss: 137.155
+64000/69092	Loss: 139.792
+67200/69092	Loss: 137.502
+Training time 0:07:01.490429
+Epoch: 2 Average loss: 138.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 471)
+0/69092	Loss: 143.459
+3200/69092	Loss: 138.368
+6400/69092	Loss: 138.595
+9600/69092	Loss: 139.335
+12800/69092	Loss: 139.312
+16000/69092	Loss: 135.976
+19200/69092	Loss: 137.318
+22400/69092	Loss: 139.115
+25600/69092	Loss: 135.847
+28800/69092	Loss: 136.129
+32000/69092	Loss: 137.623
+35200/69092	Loss: 140.500
+38400/69092	Loss: 138.070
+41600/69092	Loss: 137.363
+44800/69092	Loss: 139.157
+48000/69092	Loss: 135.501
+51200/69092	Loss: 138.347
+54400/69092	Loss: 135.000
+57600/69092	Loss: 140.670
+60800/69092	Loss: 137.951
+64000/69092	Loss: 136.888
+67200/69092	Loss: 139.456
+Training time 0:06:58.555305
+Epoch: 3 Average loss: 137.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 472)
+0/69092	Loss: 154.152
+3200/69092	Loss: 140.272
+6400/69092	Loss: 140.132
+9600/69092	Loss: 136.916
+12800/69092	Loss: 139.042
+16000/69092	Loss: 138.926
+19200/69092	Loss: 136.476
+22400/69092	Loss: 140.618
+25600/69092	Loss: 138.422
+28800/69092	Loss: 138.851
+32000/69092	Loss: 138.223
+35200/69092	Loss: 136.512
+38400/69092	Loss: 136.162
+41600/69092	Loss: 134.734
+44800/69092	Loss: 137.555
+48000/69092	Loss: 139.731
+51200/69092	Loss: 138.669
+54400/69092	Loss: 138.437
+57600/69092	Loss: 134.274
+60800/69092	Loss: 136.031
+64000/69092	Loss: 138.654
+67200/69092	Loss: 138.006
+Training time 0:06:57.863673
+Epoch: 4 Average loss: 137.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 473)
+0/69092	Loss: 142.500
+3200/69092	Loss: 139.406
+6400/69092	Loss: 137.681
+9600/69092	Loss: 140.452
+12800/69092	Loss: 137.902
+16000/69092	Loss: 135.751
+19200/69092	Loss: 137.053
+22400/69092	Loss: 136.416
+25600/69092	Loss: 140.289
+28800/69092	Loss: 139.878
+32000/69092	Loss: 137.293
+35200/69092	Loss: 137.235
+38400/69092	Loss: 137.941
+41600/69092	Loss: 136.962
+44800/69092	Loss: 135.903
+48000/69092	Loss: 136.330
+51200/69092	Loss: 136.389
+54400/69092	Loss: 138.160
+57600/69092	Loss: 138.806
+60800/69092	Loss: 135.389
+64000/69092	Loss: 140.278
+67200/69092	Loss: 134.762
+Training time 0:07:07.191231
+Epoch: 5 Average loss: 137.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 474)
+0/69092	Loss: 163.450
+3200/69092	Loss: 138.333
+6400/69092	Loss: 136.438
+9600/69092	Loss: 138.390
+12800/69092	Loss: 135.661
+16000/69092	Loss: 140.131
+19200/69092	Loss: 136.901
+22400/69092	Loss: 138.080
+25600/69092	Loss: 137.564
+28800/69092	Loss: 136.841
+32000/69092	Loss: 136.598
+35200/69092	Loss: 134.516
+38400/69092	Loss: 136.094
+41600/69092	Loss: 139.794
+44800/69092	Loss: 138.222
+48000/69092	Loss: 140.596
+51200/69092	Loss: 139.941
+54400/69092	Loss: 138.913
+57600/69092	Loss: 138.568
+60800/69092	Loss: 137.476
+64000/69092	Loss: 135.877
+67200/69092	Loss: 137.592
+Training time 0:07:00.265324
+Epoch: 6 Average loss: 137.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 475)
+0/69092	Loss: 135.322
+3200/69092	Loss: 139.732
+6400/69092	Loss: 137.752
+9600/69092	Loss: 138.996
+12800/69092	Loss: 136.109
+16000/69092	Loss: 137.023
+19200/69092	Loss: 139.149
+22400/69092	Loss: 136.605
+25600/69092	Loss: 138.289
+28800/69092	Loss: 138.671
+32000/69092	Loss: 137.409
+35200/69092	Loss: 138.425
+38400/69092	Loss: 137.661
+41600/69092	Loss: 136.906
+44800/69092	Loss: 135.966
+48000/69092	Loss: 136.983
+51200/69092	Loss: 138.004
+54400/69092	Loss: 140.625
+57600/69092	Loss: 137.241
+60800/69092	Loss: 138.695
+64000/69092	Loss: 137.038
+67200/69092	Loss: 137.401
+Training time 0:07:01.052617
+Epoch: 7 Average loss: 137.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 476)
+0/69092	Loss: 140.550
+3200/69092	Loss: 137.219
+6400/69092	Loss: 136.599
+9600/69092	Loss: 138.418
+12800/69092	Loss: 137.820
+16000/69092	Loss: 138.161
+19200/69092	Loss: 136.275
+22400/69092	Loss: 138.910
+25600/69092	Loss: 138.868
+28800/69092	Loss: 138.601
+32000/69092	Loss: 137.357
+35200/69092	Loss: 136.010
+38400/69092	Loss: 139.330
+41600/69092	Loss: 139.147
+44800/69092	Loss: 139.498
+48000/69092	Loss: 137.385
+51200/69092	Loss: 139.710
+54400/69092	Loss: 137.604
+57600/69092	Loss: 138.456
+60800/69092	Loss: 135.592
+64000/69092	Loss: 138.117
+67200/69092	Loss: 137.439
+Training time 0:07:05.456969
+Epoch: 8 Average loss: 137.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 477)
+0/69092	Loss: 142.035
+3200/69092	Loss: 136.773
+6400/69092	Loss: 137.671
+9600/69092	Loss: 138.018
+12800/69092	Loss: 137.208
+16000/69092	Loss: 137.811
+19200/69092	Loss: 140.344
+22400/69092	Loss: 137.280
+25600/69092	Loss: 139.148
+28800/69092	Loss: 136.744
+32000/69092	Loss: 136.831
+35200/69092	Loss: 139.722
+38400/69092	Loss: 136.057
+41600/69092	Loss: 136.985
+44800/69092	Loss: 140.392
+48000/69092	Loss: 135.353
+51200/69092	Loss: 136.677
+54400/69092	Loss: 138.782
+57600/69092	Loss: 139.880
+60800/69092	Loss: 134.946
+64000/69092	Loss: 138.305
+67200/69092	Loss: 139.392
+Training time 0:06:54.722586
+Epoch: 9 Average loss: 137.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 478)
+0/69092	Loss: 156.420
+3200/69092	Loss: 138.104
+6400/69092	Loss: 137.494
+9600/69092	Loss: 140.361
+12800/69092	Loss: 138.221
+16000/69092	Loss: 138.535
+19200/69092	Loss: 135.744
+22400/69092	Loss: 137.266
+25600/69092	Loss: 139.176
+28800/69092	Loss: 137.927
+32000/69092	Loss: 137.005
+35200/69092	Loss: 137.042
+38400/69092	Loss: 140.307
+41600/69092	Loss: 138.017
+44800/69092	Loss: 136.913
+48000/69092	Loss: 136.648
+51200/69092	Loss: 136.431
+54400/69092	Loss: 135.853
+57600/69092	Loss: 137.992
+60800/69092	Loss: 137.899
+64000/69092	Loss: 138.182
+67200/69092	Loss: 138.591
+Training time 0:07:06.654254
+Epoch: 10 Average loss: 137.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 479)
+0/69092	Loss: 131.433
+3200/69092	Loss: 137.231
+6400/69092	Loss: 137.407
+9600/69092	Loss: 139.768
+12800/69092	Loss: 136.075
+16000/69092	Loss: 141.442
+19200/69092	Loss: 136.680
+22400/69092	Loss: 138.213
+25600/69092	Loss: 138.272
+28800/69092	Loss: 136.384
+32000/69092	Loss: 135.571
+35200/69092	Loss: 137.978
+38400/69092	Loss: 136.812
+41600/69092	Loss: 138.179
+44800/69092	Loss: 139.828
+48000/69092	Loss: 135.621
+51200/69092	Loss: 137.073
+54400/69092	Loss: 141.089
+57600/69092	Loss: 140.331
+60800/69092	Loss: 135.769
+64000/69092	Loss: 137.641
+67200/69092	Loss: 137.875
+Training time 0:07:04.261148
+Epoch: 11 Average loss: 137.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 480)
+0/69092	Loss: 134.601
+3200/69092	Loss: 138.650
+6400/69092	Loss: 137.956
+9600/69092	Loss: 137.617
+12800/69092	Loss: 137.608
+16000/69092	Loss: 139.375
+19200/69092	Loss: 136.245
+22400/69092	Loss: 136.381
+25600/69092	Loss: 138.684
+28800/69092	Loss: 137.402
+32000/69092	Loss: 136.254
+35200/69092	Loss: 136.883
+38400/69092	Loss: 138.386
+41600/69092	Loss: 136.286
+44800/69092	Loss: 138.285
+48000/69092	Loss: 138.132
+51200/69092	Loss: 138.041
+54400/69092	Loss: 135.941
+57600/69092	Loss: 136.807
+60800/69092	Loss: 139.531
+64000/69092	Loss: 139.166
+67200/69092	Loss: 137.075
+Training time 0:07:01.311718
+Epoch: 12 Average loss: 137.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 481)
+0/69092	Loss: 128.250
+3200/69092	Loss: 138.738
+6400/69092	Loss: 138.729
+9600/69092	Loss: 140.347
+12800/69092	Loss: 137.426
+16000/69092	Loss: 138.766
+19200/69092	Loss: 140.406
+22400/69092	Loss: 138.809
+25600/69092	Loss: 138.751
+28800/69092	Loss: 137.504
+32000/69092	Loss: 135.517
+35200/69092	Loss: 136.866
+38400/69092	Loss: 137.263
+41600/69092	Loss: 138.687
+44800/69092	Loss: 135.410
+48000/69092	Loss: 136.019
+51200/69092	Loss: 136.740
+54400/69092	Loss: 137.201
+57600/69092	Loss: 137.202
+60800/69092	Loss: 135.423
+64000/69092	Loss: 141.050
+67200/69092	Loss: 138.124
+Training time 0:06:57.452872
+Epoch: 13 Average loss: 137.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 482)
+0/69092	Loss: 134.031
+3200/69092	Loss: 137.000
+6400/69092	Loss: 138.101
+9600/69092	Loss: 137.382
+12800/69092	Loss: 138.721
+16000/69092	Loss: 140.975
+19200/69092	Loss: 135.436
+22400/69092	Loss: 138.318
+25600/69092	Loss: 136.755
+28800/69092	Loss: 134.939
+32000/69092	Loss: 138.207
+35200/69092	Loss: 137.167
+38400/69092	Loss: 136.249
+41600/69092	Loss: 140.590
+44800/69092	Loss: 138.143
+48000/69092	Loss: 138.473
+51200/69092	Loss: 138.471
+54400/69092	Loss: 137.825
+57600/69092	Loss: 138.982
+60800/69092	Loss: 139.645
+64000/69092	Loss: 140.508
+67200/69092	Loss: 135.137
+Training time 0:07:04.747622
+Epoch: 14 Average loss: 137.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 483)
+0/69092	Loss: 134.364
+3200/69092	Loss: 138.819
+6400/69092	Loss: 139.875
+9600/69092	Loss: 136.636
+12800/69092	Loss: 136.994
+16000/69092	Loss: 137.671
+19200/69092	Loss: 137.005
+22400/69092	Loss: 135.962
+25600/69092	Loss: 136.993
+28800/69092	Loss: 138.914
+32000/69092	Loss: 136.734
+35200/69092	Loss: 139.739
+38400/69092	Loss: 138.756
+41600/69092	Loss: 138.678
+44800/69092	Loss: 137.802
+48000/69092	Loss: 136.255
+51200/69092	Loss: 138.719
+54400/69092	Loss: 137.163
+57600/69092	Loss: 138.531
+60800/69092	Loss: 138.056
+64000/69092	Loss: 138.240
+67200/69092	Loss: 137.816
+Training time 0:07:02.619884
+Epoch: 15 Average loss: 137.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 484)
+0/69092	Loss: 130.591
+3200/69092	Loss: 135.814
+6400/69092	Loss: 137.769
+9600/69092	Loss: 139.067
+12800/69092	Loss: 137.024
+16000/69092	Loss: 140.110
+19200/69092	Loss: 138.100
+22400/69092	Loss: 138.436
+25600/69092	Loss: 136.819
+28800/69092	Loss: 139.371
+32000/69092	Loss: 138.212
+35200/69092	Loss: 139.354
+38400/69092	Loss: 137.879
+41600/69092	Loss: 135.298
+44800/69092	Loss: 138.339
+48000/69092	Loss: 136.152
+51200/69092	Loss: 137.304
+54400/69092	Loss: 138.269
+57600/69092	Loss: 137.205
+60800/69092	Loss: 139.723
+64000/69092	Loss: 137.535
+67200/69092	Loss: 135.891
+Training time 0:07:06.325899
+Epoch: 16 Average loss: 137.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 485)
+0/69092	Loss: 153.949
+3200/69092	Loss: 137.512
+6400/69092	Loss: 136.370
+9600/69092	Loss: 138.023
+12800/69092	Loss: 139.123
+16000/69092	Loss: 139.771
+19200/69092	Loss: 137.606
+22400/69092	Loss: 137.496
+25600/69092	Loss: 138.650
+28800/69092	Loss: 137.624
+32000/69092	Loss: 134.798
+35200/69092	Loss: 137.695
+38400/69092	Loss: 137.180
+41600/69092	Loss: 137.319
+44800/69092	Loss: 139.709
+48000/69092	Loss: 139.760
+51200/69092	Loss: 137.800
+54400/69092	Loss: 140.595
+57600/69092	Loss: 137.833
+60800/69092	Loss: 137.849
+64000/69092	Loss: 135.956
+67200/69092	Loss: 137.918
+Training time 0:06:52.729540
+Epoch: 17 Average loss: 137.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 486)
+0/69092	Loss: 143.657
+3200/69092	Loss: 139.495
+6400/69092	Loss: 137.900
+9600/69092	Loss: 136.746
+12800/69092	Loss: 139.124
+16000/69092	Loss: 138.296
+19200/69092	Loss: 137.774
+22400/69092	Loss: 137.939
+25600/69092	Loss: 139.711
+28800/69092	Loss: 135.610
+32000/69092	Loss: 136.860
+35200/69092	Loss: 140.280
+38400/69092	Loss: 137.544
+41600/69092	Loss: 136.297
+44800/69092	Loss: 138.012
+48000/69092	Loss: 138.512
+51200/69092	Loss: 136.697
+54400/69092	Loss: 135.357
+57600/69092	Loss: 137.625
+60800/69092	Loss: 138.354
+64000/69092	Loss: 138.413
+67200/69092	Loss: 139.840
+Training time 0:07:03.484406
+Epoch: 18 Average loss: 137.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 487)
+0/69092	Loss: 146.916
+3200/69092	Loss: 138.893
+6400/69092	Loss: 137.044
+9600/69092	Loss: 138.878
+12800/69092	Loss: 136.918
+16000/69092	Loss: 138.940
+19200/69092	Loss: 138.577
+22400/69092	Loss: 137.356
+25600/69092	Loss: 136.841
+28800/69092	Loss: 138.899
+32000/69092	Loss: 136.852
+35200/69092	Loss: 138.547
+38400/69092	Loss: 137.640
+41600/69092	Loss: 137.772
+44800/69092	Loss: 135.953
+48000/69092	Loss: 137.126
+51200/69092	Loss: 138.391
+54400/69092	Loss: 137.549
+57600/69092	Loss: 139.612
+60800/69092	Loss: 136.264
+64000/69092	Loss: 138.256
+67200/69092	Loss: 140.513
+Training time 0:07:06.743195
+Epoch: 19 Average loss: 138.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 488)
+0/69092	Loss: 131.284
+3200/69092	Loss: 137.073
+6400/69092	Loss: 139.271
+9600/69092	Loss: 138.538
+12800/69092	Loss: 137.825
+16000/69092	Loss: 138.829
+19200/69092	Loss: 136.523
+22400/69092	Loss: 137.389
+25600/69092	Loss: 138.327
+28800/69092	Loss: 138.541
+32000/69092	Loss: 136.764
+35200/69092	Loss: 140.385
+38400/69092	Loss: 140.119
+41600/69092	Loss: 136.867
+44800/69092	Loss: 136.307
+48000/69092	Loss: 136.365
+51200/69092	Loss: 137.000
+54400/69092	Loss: 136.374
+57600/69092	Loss: 139.761
+60800/69092	Loss: 138.985
+64000/69092	Loss: 137.728
+67200/69092	Loss: 136.531
+Training time 0:07:02.595521
+Epoch: 20 Average loss: 137.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 489)
+0/69092	Loss: 162.236
+3200/69092	Loss: 139.635
+6400/69092	Loss: 140.383
+9600/69092	Loss: 135.864
+12800/69092	Loss: 141.550
+16000/69092	Loss: 140.037
+19200/69092	Loss: 134.787
+22400/69092	Loss: 136.238
+25600/69092	Loss: 140.205
+28800/69092	Loss: 138.215
+32000/69092	Loss: 139.026
+35200/69092	Loss: 137.655
+38400/69092	Loss: 136.322
+41600/69092	Loss: 137.637
+44800/69092	Loss: 137.705
+48000/69092	Loss: 138.172
+51200/69092	Loss: 133.882
+54400/69092	Loss: 137.191
+57600/69092	Loss: 137.514
+60800/69092	Loss: 136.976
+64000/69092	Loss: 138.046
+67200/69092	Loss: 137.329
+Training time 0:07:07.352591
+Epoch: 21 Average loss: 137.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 490)
+0/69092	Loss: 146.004
+3200/69092	Loss: 136.571
+6400/69092	Loss: 139.675
+9600/69092	Loss: 139.546
+12800/69092	Loss: 138.232
+16000/69092	Loss: 137.708
+19200/69092	Loss: 139.274
+22400/69092	Loss: 139.376
+25600/69092	Loss: 138.302
+28800/69092	Loss: 137.745
+32000/69092	Loss: 137.433
+35200/69092	Loss: 136.729
+38400/69092	Loss: 137.717
+41600/69092	Loss: 139.863
+44800/69092	Loss: 138.989
+48000/69092	Loss: 134.990
+51200/69092	Loss: 135.932
+54400/69092	Loss: 136.971
+57600/69092	Loss: 137.550
+60800/69092	Loss: 137.848
+64000/69092	Loss: 139.054
+67200/69092	Loss: 137.098
+Training time 0:07:02.895443
+Epoch: 22 Average loss: 137.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 491)
+0/69092	Loss: 135.403
+3200/69092	Loss: 136.966
+6400/69092	Loss: 138.980
+9600/69092	Loss: 138.646
+12800/69092	Loss: 136.820
+16000/69092	Loss: 137.652
+19200/69092	Loss: 138.463
+22400/69092	Loss: 136.304
+25600/69092	Loss: 135.184
+28800/69092	Loss: 139.519
+32000/69092	Loss: 139.038
+35200/69092	Loss: 137.822
+38400/69092	Loss: 138.698
+41600/69092	Loss: 140.412
+44800/69092	Loss: 138.412
+48000/69092	Loss: 136.333
+51200/69092	Loss: 137.155
+54400/69092	Loss: 136.986
+57600/69092	Loss: 139.806
+60800/69092	Loss: 137.012
+64000/69092	Loss: 136.808
+67200/69092	Loss: 137.106
+Training time 0:07:00.968394
+Epoch: 23 Average loss: 137.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 492)
+0/69092	Loss: 137.671
+3200/69092	Loss: 135.745
+6400/69092	Loss: 139.610
+9600/69092	Loss: 137.444
+12800/69092	Loss: 138.104
+16000/69092	Loss: 138.220
+19200/69092	Loss: 135.945
+22400/69092	Loss: 135.883
+25600/69092	Loss: 139.367
+28800/69092	Loss: 135.597
+32000/69092	Loss: 136.769
+35200/69092	Loss: 139.386
+38400/69092	Loss: 138.976
+41600/69092	Loss: 136.854
+44800/69092	Loss: 137.840
+48000/69092	Loss: 136.606
+51200/69092	Loss: 138.986
+54400/69092	Loss: 138.557
+57600/69092	Loss: 135.918
+60800/69092	Loss: 136.905
+64000/69092	Loss: 138.176
+67200/69092	Loss: 137.706
+Training time 0:06:54.330350
+Epoch: 24 Average loss: 137.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 493)
+0/69092	Loss: 147.244
+3200/69092	Loss: 136.999
+6400/69092	Loss: 135.600
+9600/69092	Loss: 136.782
+12800/69092	Loss: 137.357
+16000/69092	Loss: 140.511
+19200/69092	Loss: 134.866
+22400/69092	Loss: 138.362
+25600/69092	Loss: 137.678
+28800/69092	Loss: 137.437
+32000/69092	Loss: 139.303
+35200/69092	Loss: 138.194
+38400/69092	Loss: 139.673
+41600/69092	Loss: 138.194
+44800/69092	Loss: 138.635
+48000/69092	Loss: 139.580
+51200/69092	Loss: 137.809
+54400/69092	Loss: 136.677
+57600/69092	Loss: 138.228
+60800/69092	Loss: 138.599
+64000/69092	Loss: 137.098
+67200/69092	Loss: 138.084
+Training time 0:07:06.224142
+Epoch: 25 Average loss: 137.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 494)
+0/69092	Loss: 145.884
+3200/69092	Loss: 137.833
+6400/69092	Loss: 139.946
+9600/69092	Loss: 138.231
+12800/69092	Loss: 139.096
+16000/69092	Loss: 137.879
+19200/69092	Loss: 139.538
+22400/69092	Loss: 135.020
+25600/69092	Loss: 137.740
+28800/69092	Loss: 140.483
+32000/69092	Loss: 137.300
+35200/69092	Loss: 135.826
+38400/69092	Loss: 136.030
+41600/69092	Loss: 137.316
+44800/69092	Loss: 137.415
+48000/69092	Loss: 136.516
+51200/69092	Loss: 136.661
+54400/69092	Loss: 137.909
+57600/69092	Loss: 137.383
+60800/69092	Loss: 140.074
+64000/69092	Loss: 137.497
+67200/69092	Loss: 139.075
+Training time 0:07:04.068573
+Epoch: 26 Average loss: 137.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 495)
+0/69092	Loss: 140.699
+3200/69092	Loss: 137.284
+6400/69092	Loss: 138.597
+9600/69092	Loss: 135.982
+12800/69092	Loss: 138.419
+16000/69092	Loss: 140.320
+19200/69092	Loss: 139.080
+22400/69092	Loss: 137.104
+25600/69092	Loss: 140.962
+28800/69092	Loss: 135.913
+32000/69092	Loss: 137.032
+35200/69092	Loss: 138.945
+38400/69092	Loss: 136.823
+41600/69092	Loss: 135.606
+44800/69092	Loss: 138.557
+48000/69092	Loss: 138.760
+51200/69092	Loss: 138.996
+54400/69092	Loss: 135.676
+57600/69092	Loss: 138.658
+60800/69092	Loss: 138.095
+64000/69092	Loss: 138.345
+67200/69092	Loss: 136.971
+Training time 0:06:56.399288
+Epoch: 27 Average loss: 137.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 496)
+0/69092	Loss: 115.512
+3200/69092	Loss: 136.271
+6400/69092	Loss: 138.992
+9600/69092	Loss: 138.047
+12800/69092	Loss: 137.607
+16000/69092	Loss: 136.805
+19200/69092	Loss: 134.689
+22400/69092	Loss: 138.379
+25600/69092	Loss: 138.592
+28800/69092	Loss: 137.339
+32000/69092	Loss: 137.184
+35200/69092	Loss: 138.024
+38400/69092	Loss: 138.656
+41600/69092	Loss: 139.167
+44800/69092	Loss: 137.078
+48000/69092	Loss: 136.658
+51200/69092	Loss: 138.379
+54400/69092	Loss: 140.630
+57600/69092	Loss: 138.030
+60800/69092	Loss: 137.213
+64000/69092	Loss: 140.150
+67200/69092	Loss: 137.913
+Training time 0:07:05.156402
+Epoch: 28 Average loss: 137.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 497)
+0/69092	Loss: 136.829
+3200/69092	Loss: 137.586
+6400/69092	Loss: 138.480
+9600/69092	Loss: 139.421
+12800/69092	Loss: 137.439
+16000/69092	Loss: 136.789
+19200/69092	Loss: 139.326
+22400/69092	Loss: 137.935
+25600/69092	Loss: 137.735
+28800/69092	Loss: 136.976
+32000/69092	Loss: 136.138
+35200/69092	Loss: 138.369
+38400/69092	Loss: 137.832
+41600/69092	Loss: 137.840
+44800/69092	Loss: 137.448
+48000/69092	Loss: 138.248
+51200/69092	Loss: 137.705
+54400/69092	Loss: 139.648
+57600/69092	Loss: 137.724
+60800/69092	Loss: 138.256
+64000/69092	Loss: 137.954
+67200/69092	Loss: 135.624
+Training time 0:07:02.959445
+Epoch: 29 Average loss: 137.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 498)
+0/69092	Loss: 148.699
+3200/69092	Loss: 138.626
+6400/69092	Loss: 138.177
+9600/69092	Loss: 134.916
+12800/69092	Loss: 141.545
+16000/69092	Loss: 138.944
+19200/69092	Loss: 136.307
+22400/69092	Loss: 136.933
+25600/69092	Loss: 135.945
+28800/69092	Loss: 139.178
+32000/69092	Loss: 139.542
+35200/69092	Loss: 140.472
+38400/69092	Loss: 140.343
+41600/69092	Loss: 137.611
+44800/69092	Loss: 135.697
+48000/69092	Loss: 136.818
+51200/69092	Loss: 135.153
+54400/69092	Loss: 138.267
+57600/69092	Loss: 136.700
+60800/69092	Loss: 135.267
+64000/69092	Loss: 140.111
+67200/69092	Loss: 138.103
+Training time 0:07:01.777559
+Epoch: 30 Average loss: 137.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 499)
+0/69092	Loss: 138.174
+3200/69092	Loss: 136.863
+6400/69092	Loss: 135.318
+9600/69092	Loss: 140.547
+12800/69092	Loss: 136.954
+16000/69092	Loss: 137.483
+19200/69092	Loss: 136.848
+22400/69092	Loss: 139.032
+25600/69092	Loss: 136.222
+28800/69092	Loss: 140.349
+32000/69092	Loss: 136.035
+35200/69092	Loss: 135.756
+38400/69092	Loss: 139.787
+41600/69092	Loss: 138.942
+44800/69092	Loss: 139.784
+48000/69092	Loss: 137.893
+51200/69092	Loss: 138.659
+54400/69092	Loss: 136.508
+57600/69092	Loss: 137.505
+60800/69092	Loss: 135.906
+64000/69092	Loss: 139.654
+67200/69092	Loss: 137.160
+Training time 0:07:06.187611
+Epoch: 31 Average loss: 137.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 500)
+0/69092	Loss: 132.505
+3200/69092	Loss: 137.910
+6400/69092	Loss: 139.389
+9600/69092	Loss: 137.022
+12800/69092	Loss: 137.312
+16000/69092	Loss: 137.938
+19200/69092	Loss: 138.513
+22400/69092	Loss: 136.744
+25600/69092	Loss: 138.571
+28800/69092	Loss: 135.996
+32000/69092	Loss: 137.202
+35200/69092	Loss: 137.741
+38400/69092	Loss: 138.387
+41600/69092	Loss: 138.127
+44800/69092	Loss: 140.409
+48000/69092	Loss: 138.029
+51200/69092	Loss: 139.933
+54400/69092	Loss: 136.371
+57600/69092	Loss: 136.599
+60800/69092	Loss: 136.376
+64000/69092	Loss: 138.295
+67200/69092	Loss: 139.085
+Training time 0:07:04.941644
+Epoch: 32 Average loss: 137.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 501)
+0/69092	Loss: 135.643
+3200/69092	Loss: 137.645
+6400/69092	Loss: 134.643
+9600/69092	Loss: 136.881
+12800/69092	Loss: 137.471
+16000/69092	Loss: 138.874
+19200/69092	Loss: 132.499
+22400/69092	Loss: 136.963
+25600/69092	Loss: 136.635
+28800/69092	Loss: 138.121
+32000/69092	Loss: 138.604
+35200/69092	Loss: 138.182
+38400/69092	Loss: 139.011
+41600/69092	Loss: 136.696
+44800/69092	Loss: 140.720
+48000/69092	Loss: 138.175
+51200/69092	Loss: 136.353
+54400/69092	Loss: 138.719
+57600/69092	Loss: 138.004
+60800/69092	Loss: 141.862
+64000/69092	Loss: 139.660
+67200/69092	Loss: 136.846
+Training time 0:06:59.691644
+Epoch: 33 Average loss: 137.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 502)
+0/69092	Loss: 126.075
+3200/69092	Loss: 136.895
+6400/69092	Loss: 137.659
+9600/69092	Loss: 138.619
+12800/69092	Loss: 136.089
+16000/69092	Loss: 138.117
+19200/69092	Loss: 139.553
+22400/69092	Loss: 137.674
+25600/69092	Loss: 140.538
+28800/69092	Loss: 140.381
+32000/69092	Loss: 136.142
+35200/69092	Loss: 134.840
+38400/69092	Loss: 139.442
+41600/69092	Loss: 136.942
+44800/69092	Loss: 135.879
+48000/69092	Loss: 138.041
+51200/69092	Loss: 137.564
+54400/69092	Loss: 136.315
+57600/69092	Loss: 137.969
+60800/69092	Loss: 138.995
+64000/69092	Loss: 137.394
+67200/69092	Loss: 137.720
+Training time 0:07:01.024297
+Epoch: 34 Average loss: 137.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 503)
+0/69092	Loss: 144.575
+3200/69092	Loss: 138.659
+6400/69092	Loss: 138.809
+9600/69092	Loss: 137.383
+12800/69092	Loss: 136.302
+16000/69092	Loss: 136.964
+19200/69092	Loss: 139.088
+22400/69092	Loss: 138.777
+25600/69092	Loss: 138.084
+28800/69092	Loss: 134.621
+32000/69092	Loss: 138.316
+35200/69092	Loss: 134.286
+38400/69092	Loss: 135.775
+41600/69092	Loss: 139.274
+44800/69092	Loss: 137.957
+48000/69092	Loss: 135.652
+51200/69092	Loss: 139.497
+54400/69092	Loss: 138.435
+57600/69092	Loss: 136.949
+60800/69092	Loss: 139.390
+64000/69092	Loss: 140.080
+67200/69092	Loss: 136.108
+Training time 0:07:05.065905
+Epoch: 35 Average loss: 137.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 504)
+0/69092	Loss: 121.560
+3200/69092	Loss: 137.566
+6400/69092	Loss: 137.235
+9600/69092	Loss: 138.813
+12800/69092	Loss: 136.578
+16000/69092	Loss: 138.724
+19200/69092	Loss: 138.039
+22400/69092	Loss: 138.079
+25600/69092	Loss: 135.014
+28800/69092	Loss: 137.224
+32000/69092	Loss: 140.537
+35200/69092	Loss: 137.283
+38400/69092	Loss: 138.640
+41600/69092	Loss: 138.021
+44800/69092	Loss: 140.429
+48000/69092	Loss: 136.650
+51200/69092	Loss: 138.638
+54400/69092	Loss: 139.000
+57600/69092	Loss: 136.472
+60800/69092	Loss: 134.800
+64000/69092	Loss: 137.553
+67200/69092	Loss: 136.365
+Training time 0:07:00.347058
+Epoch: 36 Average loss: 137.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 505)
+0/69092	Loss: 146.177
+3200/69092	Loss: 138.979
+6400/69092	Loss: 138.357
+9600/69092	Loss: 138.181
+12800/69092	Loss: 136.630
+16000/69092	Loss: 136.378
+19200/69092	Loss: 135.355
+22400/69092	Loss: 136.688
+25600/69092	Loss: 138.704
+28800/69092	Loss: 137.912
+32000/69092	Loss: 135.932
+35200/69092	Loss: 139.310
+38400/69092	Loss: 135.275
+41600/69092	Loss: 141.664
+44800/69092	Loss: 139.711
+48000/69092	Loss: 138.493
+51200/69092	Loss: 134.268
+54400/69092	Loss: 137.496
+57600/69092	Loss: 137.696
+60800/69092	Loss: 138.044
+64000/69092	Loss: 136.808
+67200/69092	Loss: 137.897
+Training time 0:07:01.900965
+Epoch: 37 Average loss: 137.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 506)
+0/69092	Loss: 138.810
+3200/69092	Loss: 137.992
+6400/69092	Loss: 135.522
+9600/69092	Loss: 138.569
+12800/69092	Loss: 137.007
+16000/69092	Loss: 134.937
+19200/69092	Loss: 141.835
+22400/69092	Loss: 137.075
+25600/69092	Loss: 136.678
+28800/69092	Loss: 138.376
+32000/69092	Loss: 134.648
+35200/69092	Loss: 138.038
+38400/69092	Loss: 137.639
+41600/69092	Loss: 138.311
+44800/69092	Loss: 137.402
+48000/69092	Loss: 138.298
+51200/69092	Loss: 137.503
+54400/69092	Loss: 136.560
+57600/69092	Loss: 136.374
+60800/69092	Loss: 139.926
+64000/69092	Loss: 137.719
+67200/69092	Loss: 139.287
+Training time 0:06:56.977291
+Epoch: 38 Average loss: 137.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 507)
+0/69092	Loss: 119.955
+3200/69092	Loss: 136.947
+6400/69092	Loss: 136.439
+9600/69092	Loss: 137.138
+12800/69092	Loss: 137.199
+16000/69092	Loss: 138.448
+19200/69092	Loss: 135.113
+22400/69092	Loss: 135.365
+25600/69092	Loss: 138.161
+28800/69092	Loss: 139.437
+32000/69092	Loss: 137.729
+35200/69092	Loss: 137.470
+38400/69092	Loss: 137.529
+41600/69092	Loss: 138.389
+44800/69092	Loss: 137.138
+48000/69092	Loss: 140.068
+51200/69092	Loss: 136.523
+54400/69092	Loss: 138.969
+57600/69092	Loss: 137.777
+60800/69092	Loss: 137.163
+64000/69092	Loss: 138.577
+67200/69092	Loss: 137.471
+Training time 0:07:04.552540
+Epoch: 39 Average loss: 137.57
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 508)
+0/69092	Loss: 147.175
+3200/69092	Loss: 139.263
+6400/69092	Loss: 135.882
+9600/69092	Loss: 138.091
+12800/69092	Loss: 138.563
+16000/69092	Loss: 137.328
+19200/69092	Loss: 138.584
+22400/69092	Loss: 137.365
+25600/69092	Loss: 135.899
+28800/69092	Loss: 136.745
+32000/69092	Loss: 139.435
+35200/69092	Loss: 138.578
+38400/69092	Loss: 135.058
+41600/69092	Loss: 141.671
+44800/69092	Loss: 135.672
+48000/69092	Loss: 136.277
+51200/69092	Loss: 137.343
+54400/69092	Loss: 137.395
+57600/69092	Loss: 138.986
+60800/69092	Loss: 137.981
+64000/69092	Loss: 138.809
+67200/69092	Loss: 136.888
+Training time 0:07:03.281877
+Epoch: 40 Average loss: 137.70
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 509)
+0/69092	Loss: 119.979
+3200/69092	Loss: 138.596
+6400/69092	Loss: 139.334
+9600/69092	Loss: 135.155
+12800/69092	Loss: 137.896
+16000/69092	Loss: 137.723
+19200/69092	Loss: 138.001
+22400/69092	Loss: 137.038
+25600/69092	Loss: 136.184
+28800/69092	Loss: 137.785
+32000/69092	Loss: 137.832
+35200/69092	Loss: 135.757
+38400/69092	Loss: 138.039
+41600/69092	Loss: 139.494
+44800/69092	Loss: 139.978
+48000/69092	Loss: 138.500
+51200/69092	Loss: 137.876
+54400/69092	Loss: 137.800
+57600/69092	Loss: 136.846
+60800/69092	Loss: 137.360
+64000/69092	Loss: 136.780
+67200/69092	Loss: 138.590
+Training time 0:07:13.055270
+Epoch: 41 Average loss: 137.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 510)
+0/69092	Loss: 137.640
+3200/69092	Loss: 136.118
+6400/69092	Loss: 138.151
+9600/69092	Loss: 140.964
+12800/69092	Loss: 139.533
+16000/69092	Loss: 134.925
+19200/69092	Loss: 137.509
+22400/69092	Loss: 135.128
+25600/69092	Loss: 137.342
+28800/69092	Loss: 139.950
+32000/69092	Loss: 138.564
+35200/69092	Loss: 136.999
+38400/69092	Loss: 140.443
+41600/69092	Loss: 136.472
+44800/69092	Loss: 136.612
+48000/69092	Loss: 136.450
+51200/69092	Loss: 139.945
+54400/69092	Loss: 138.345
+57600/69092	Loss: 136.962
+60800/69092	Loss: 134.722
+64000/69092	Loss: 140.230
+67200/69092	Loss: 137.780
+Training time 0:07:04.672645
+Epoch: 42 Average loss: 137.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 511)
+0/69092	Loss: 130.017
+3200/69092	Loss: 136.665
+6400/69092	Loss: 136.609
+9600/69092	Loss: 135.911
+12800/69092	Loss: 138.876
+16000/69092	Loss: 138.727
+19200/69092	Loss: 140.467
+22400/69092	Loss: 140.810
+25600/69092	Loss: 138.040
+28800/69092	Loss: 137.460
+32000/69092	Loss: 138.559
+35200/69092	Loss: 136.843
+38400/69092	Loss: 135.188
+41600/69092	Loss: 139.180
+44800/69092	Loss: 135.626
+48000/69092	Loss: 136.853
+51200/69092	Loss: 138.186
+54400/69092	Loss: 136.407
+57600/69092	Loss: 136.348
+60800/69092	Loss: 139.426
+64000/69092	Loss: 136.452
+67200/69092	Loss: 136.897
+Training time 0:07:02.960620
+Epoch: 43 Average loss: 137.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 512)
+0/69092	Loss: 134.933
+3200/69092	Loss: 139.770
+6400/69092	Loss: 136.481
+9600/69092	Loss: 139.190
+12800/69092	Loss: 135.540
+16000/69092	Loss: 136.850
+19200/69092	Loss: 137.719
+22400/69092	Loss: 136.341
+25600/69092	Loss: 139.162
+28800/69092	Loss: 136.772
+32000/69092	Loss: 137.789
+35200/69092	Loss: 135.881
+38400/69092	Loss: 138.286
+41600/69092	Loss: 138.363
+44800/69092	Loss: 137.530
+48000/69092	Loss: 138.415
+51200/69092	Loss: 138.944
+54400/69092	Loss: 135.499
+57600/69092	Loss: 139.076
+60800/69092	Loss: 135.097
+64000/69092	Loss: 137.392
+67200/69092	Loss: 139.681
+Training time 0:06:55.148428
+Epoch: 44 Average loss: 137.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 513)
+0/69092	Loss: 130.399
+3200/69092	Loss: 138.850
+6400/69092	Loss: 137.576
+9600/69092	Loss: 135.583
+12800/69092	Loss: 138.504
+16000/69092	Loss: 136.553
+19200/69092	Loss: 137.286
+22400/69092	Loss: 139.198
+25600/69092	Loss: 137.541
+28800/69092	Loss: 137.728
+32000/69092	Loss: 137.078
+35200/69092	Loss: 140.543
+38400/69092	Loss: 135.320
+41600/69092	Loss: 135.699
+44800/69092	Loss: 136.210
+48000/69092	Loss: 138.436
+51200/69092	Loss: 136.330
+54400/69092	Loss: 140.190
+57600/69092	Loss: 137.050
+60800/69092	Loss: 139.002
+64000/69092	Loss: 137.549
+67200/69092	Loss: 137.547
+Training time 0:07:00.340881
+Epoch: 45 Average loss: 137.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 514)
+0/69092	Loss: 141.976
+3200/69092	Loss: 137.152
+6400/69092	Loss: 139.066
+9600/69092	Loss: 139.171
+12800/69092	Loss: 135.295
+16000/69092	Loss: 137.704
+19200/69092	Loss: 136.804
+22400/69092	Loss: 136.364
+25600/69092	Loss: 139.625
+28800/69092	Loss: 136.614
+32000/69092	Loss: 138.083
+35200/69092	Loss: 137.483
+38400/69092	Loss: 135.783
+41600/69092	Loss: 137.815
+44800/69092	Loss: 139.363
+48000/69092	Loss: 141.434
+51200/69092	Loss: 137.406
+54400/69092	Loss: 138.294
+57600/69092	Loss: 137.910
+60800/69092	Loss: 137.519
+64000/69092	Loss: 136.174
+67200/69092	Loss: 136.904
+Training time 0:07:02.238480
+Epoch: 46 Average loss: 137.73
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 515)
+0/69092	Loss: 123.691
+3200/69092	Loss: 136.906
+6400/69092	Loss: 139.665
+9600/69092	Loss: 136.445
+12800/69092	Loss: 138.131
+16000/69092	Loss: 137.985
+19200/69092	Loss: 137.283
+22400/69092	Loss: 139.800
+25600/69092	Loss: 135.622
+28800/69092	Loss: 139.264
+32000/69092	Loss: 135.670
+35200/69092	Loss: 137.351
+38400/69092	Loss: 138.966
+41600/69092	Loss: 136.448
+44800/69092	Loss: 137.496
+48000/69092	Loss: 139.326
+51200/69092	Loss: 138.607
+54400/69092	Loss: 136.220
+57600/69092	Loss: 138.064
+60800/69092	Loss: 140.213
+64000/69092	Loss: 137.907
+67200/69092	Loss: 136.407
+Training time 0:07:06.345103
+Epoch: 47 Average loss: 137.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 516)
+0/69092	Loss: 154.327
+3200/69092	Loss: 132.135
+6400/69092	Loss: 137.770
+9600/69092	Loss: 137.531
+12800/69092	Loss: 138.767
+16000/69092	Loss: 137.809
+19200/69092	Loss: 139.891
+22400/69092	Loss: 136.485
+25600/69092	Loss: 136.954
+28800/69092	Loss: 137.544
+32000/69092	Loss: 137.797
+35200/69092	Loss: 137.638
+38400/69092	Loss: 138.251
+41600/69092	Loss: 138.169
+44800/69092	Loss: 138.844
+48000/69092	Loss: 141.044
+51200/69092	Loss: 139.041
+54400/69092	Loss: 136.660
+57600/69092	Loss: 137.281
+60800/69092	Loss: 138.270
+64000/69092	Loss: 137.551
+67200/69092	Loss: 134.805
+Training time 0:07:04.534222
+Epoch: 48 Average loss: 137.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 517)
+0/69092	Loss: 128.199
+3200/69092	Loss: 138.579
+6400/69092	Loss: 139.881
+9600/69092	Loss: 135.242
+12800/69092	Loss: 136.722
+16000/69092	Loss: 137.077
+19200/69092	Loss: 138.179
+22400/69092	Loss: 139.228
+25600/69092	Loss: 139.307
+28800/69092	Loss: 137.431
+32000/69092	Loss: 139.082
+35200/69092	Loss: 138.168
+38400/69092	Loss: 137.206
+41600/69092	Loss: 138.147
+44800/69092	Loss: 135.886
+48000/69092	Loss: 135.795
+51200/69092	Loss: 137.107
+54400/69092	Loss: 139.295
+57600/69092	Loss: 138.465
+60800/69092	Loss: 137.090
+64000/69092	Loss: 137.417
+67200/69092	Loss: 137.876
+Training time 0:07:03.969488
+Epoch: 49 Average loss: 137.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 518)
+0/69092	Loss: 128.941
+3200/69092	Loss: 136.698
+6400/69092	Loss: 138.476
+9600/69092	Loss: 139.067
+12800/69092	Loss: 137.637
+16000/69092	Loss: 135.453
+19200/69092	Loss: 138.238
+22400/69092	Loss: 139.762
+25600/69092	Loss: 138.018
+28800/69092	Loss: 137.134
+32000/69092	Loss: 139.403
+35200/69092	Loss: 139.139
+38400/69092	Loss: 138.088
+41600/69092	Loss: 136.212
+44800/69092	Loss: 138.857
+48000/69092	Loss: 137.188
+51200/69092	Loss: 137.930
+54400/69092	Loss: 138.027
+57600/69092	Loss: 135.335
+60800/69092	Loss: 137.301
+64000/69092	Loss: 136.898
+67200/69092	Loss: 136.456
+Training time 0:07:02.207466
+Epoch: 50 Average loss: 137.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 519)
+0/69092	Loss: 168.541
+3200/69092	Loss: 136.037
+6400/69092	Loss: 140.787
+9600/69092	Loss: 137.187
+12800/69092	Loss: 138.907
+16000/69092	Loss: 137.830
+19200/69092	Loss: 140.766
+22400/69092	Loss: 138.146
+25600/69092	Loss: 136.387
+28800/69092	Loss: 136.816
+32000/69092	Loss: 137.602
+35200/69092	Loss: 132.961
+38400/69092	Loss: 138.636
+41600/69092	Loss: 136.946
+44800/69092	Loss: 138.107
+48000/69092	Loss: 135.676
+51200/69092	Loss: 134.695
+54400/69092	Loss: 136.433
+57600/69092	Loss: 139.019
+60800/69092	Loss: 137.588
+64000/69092	Loss: 138.237
+67200/69092	Loss: 136.772
+Training time 0:07:01.494565
+Epoch: 51 Average loss: 137.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 520)
+0/69092	Loss: 147.427
+3200/69092	Loss: 139.834
+6400/69092	Loss: 135.416
+9600/69092	Loss: 134.528
+12800/69092	Loss: 136.580
+16000/69092	Loss: 137.651
+19200/69092	Loss: 138.634
+22400/69092	Loss: 139.115
+25600/69092	Loss: 136.687
+28800/69092	Loss: 137.274
+32000/69092	Loss: 140.194
+35200/69092	Loss: 136.983
+38400/69092	Loss: 137.479
+41600/69092	Loss: 139.535
+44800/69092	Loss: 139.277
+48000/69092	Loss: 136.736
+51200/69092	Loss: 136.939
+54400/69092	Loss: 138.289
+57600/69092	Loss: 138.807
+60800/69092	Loss: 134.891
+64000/69092	Loss: 136.719
+67200/69092	Loss: 136.676
+Training time 0:07:03.352130
+Epoch: 52 Average loss: 137.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 521)
+0/69092	Loss: 136.834
+3200/69092	Loss: 137.353
+6400/69092	Loss: 138.259
+9600/69092	Loss: 142.192
+12800/69092	Loss: 136.419
+16000/69092	Loss: 134.710
+19200/69092	Loss: 137.924
+22400/69092	Loss: 137.576
+25600/69092	Loss: 138.453
+28800/69092	Loss: 136.414
+32000/69092	Loss: 135.665
+35200/69092	Loss: 139.402
+38400/69092	Loss: 138.213
+41600/69092	Loss: 137.055
+44800/69092	Loss: 140.782
+48000/69092	Loss: 135.127
+51200/69092	Loss: 137.406
+54400/69092	Loss: 140.239
+57600/69092	Loss: 136.793
+60800/69092	Loss: 134.970
+64000/69092	Loss: 135.725
+67200/69092	Loss: 137.956
+Training time 0:07:04.745543
+Epoch: 53 Average loss: 137.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 522)
+0/69092	Loss: 166.699
+3200/69092	Loss: 139.538
+6400/69092	Loss: 137.013
+9600/69092	Loss: 134.144
+12800/69092	Loss: 140.789
+16000/69092	Loss: 135.582
+19200/69092	Loss: 140.997
+22400/69092	Loss: 138.317
+25600/69092	Loss: 136.617
+28800/69092	Loss: 135.932
+32000/69092	Loss: 139.898
+35200/69092	Loss: 136.469
+38400/69092	Loss: 138.120
+41600/69092	Loss: 137.900
+44800/69092	Loss: 138.062
+48000/69092	Loss: 137.348
+51200/69092	Loss: 137.745
+54400/69092	Loss: 136.591
+57600/69092	Loss: 137.110
+60800/69092	Loss: 136.202
+64000/69092	Loss: 140.011
+67200/69092	Loss: 137.366
+Training time 0:07:04.055063
+Epoch: 54 Average loss: 137.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 523)
+0/69092	Loss: 144.750
+3200/69092	Loss: 141.765
+6400/69092	Loss: 138.016
+9600/69092	Loss: 137.052
+12800/69092	Loss: 137.433
+16000/69092	Loss: 138.204
+19200/69092	Loss: 141.255
+22400/69092	Loss: 138.737
+25600/69092	Loss: 135.503
+28800/69092	Loss: 138.431
+32000/69092	Loss: 139.289
+35200/69092	Loss: 134.503
+38400/69092	Loss: 137.153
+41600/69092	Loss: 137.387
+44800/69092	Loss: 137.637
+48000/69092	Loss: 136.963
+51200/69092	Loss: 136.481
+54400/69092	Loss: 137.667
+57600/69092	Loss: 139.008
+60800/69092	Loss: 136.330
+64000/69092	Loss: 137.579
+67200/69092	Loss: 135.602
+Training time 0:06:54.653184
+Epoch: 55 Average loss: 137.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 524)
+0/69092	Loss: 125.789
+3200/69092	Loss: 134.851
+6400/69092	Loss: 138.762
+9600/69092	Loss: 134.859
+12800/69092	Loss: 137.029
+16000/69092	Loss: 138.106
+19200/69092	Loss: 139.637
+22400/69092	Loss: 136.917
+25600/69092	Loss: 139.254
+28800/69092	Loss: 138.989
+32000/69092	Loss: 137.919
+35200/69092	Loss: 138.351
+38400/69092	Loss: 138.085
+41600/69092	Loss: 138.531
+44800/69092	Loss: 136.643
+48000/69092	Loss: 138.666
+51200/69092	Loss: 136.811
+54400/69092	Loss: 136.477
+57600/69092	Loss: 136.051
+60800/69092	Loss: 139.355
+64000/69092	Loss: 138.676
+67200/69092	Loss: 136.746
+Training time 0:06:58.673029
+Epoch: 56 Average loss: 137.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 525)
+0/69092	Loss: 138.498
+3200/69092	Loss: 136.203
+6400/69092	Loss: 136.941
+9600/69092	Loss: 140.046
+12800/69092	Loss: 137.781
+16000/69092	Loss: 137.961
+19200/69092	Loss: 137.407
+22400/69092	Loss: 139.167
+25600/69092	Loss: 140.466
+28800/69092	Loss: 137.333
+32000/69092	Loss: 136.595
+35200/69092	Loss: 137.601
+38400/69092	Loss: 137.662
+41600/69092	Loss: 140.061
+44800/69092	Loss: 136.220
+48000/69092	Loss: 135.749
+51200/69092	Loss: 136.377
+54400/69092	Loss: 137.084
+57600/69092	Loss: 137.287
+60800/69092	Loss: 138.743
+64000/69092	Loss: 139.111
+67200/69092	Loss: 135.550
+Training time 0:07:04.328802
+Epoch: 57 Average loss: 137.70
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 526)
+0/69092	Loss: 142.367
+3200/69092	Loss: 135.086
+6400/69092	Loss: 136.702
+9600/69092	Loss: 137.410
+12800/69092	Loss: 135.978
+16000/69092	Loss: 140.835
+19200/69092	Loss: 138.124
+22400/69092	Loss: 136.413
+25600/69092	Loss: 136.763
+28800/69092	Loss: 138.470
+32000/69092	Loss: 134.816
+35200/69092	Loss: 134.723
+38400/69092	Loss: 139.062
+41600/69092	Loss: 139.040
+44800/69092	Loss: 136.292
+48000/69092	Loss: 138.080
+51200/69092	Loss: 140.008
+54400/69092	Loss: 140.091
+57600/69092	Loss: 138.074
+60800/69092	Loss: 135.817
+64000/69092	Loss: 137.358
+67200/69092	Loss: 139.547
+Training time 0:07:02.833754
+Epoch: 58 Average loss: 137.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 527)
+0/69092	Loss: 137.641
+3200/69092	Loss: 134.733
+6400/69092	Loss: 135.880
+9600/69092	Loss: 138.089
+12800/69092	Loss: 138.002
+16000/69092	Loss: 139.355
+19200/69092	Loss: 133.663
+22400/69092	Loss: 137.193
+25600/69092	Loss: 138.649
+28800/69092	Loss: 139.570
+32000/69092	Loss: 137.813
+35200/69092	Loss: 138.393
+38400/69092	Loss: 139.018
+41600/69092	Loss: 138.609
+44800/69092	Loss: 136.289
+48000/69092	Loss: 137.658
+51200/69092	Loss: 136.251
+54400/69092	Loss: 138.707
+57600/69092	Loss: 137.481
+60800/69092	Loss: 136.812
+64000/69092	Loss: 139.564
+67200/69092	Loss: 136.137
+Training time 0:07:02.024226
+Epoch: 59 Average loss: 137.54
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 528)
+0/69092	Loss: 134.721
+3200/69092	Loss: 136.548
+6400/69092	Loss: 139.715
+9600/69092	Loss: 140.183
+12800/69092	Loss: 139.944
+16000/69092	Loss: 134.130
+19200/69092	Loss: 136.630
+22400/69092	Loss: 136.396
+25600/69092	Loss: 140.036
+28800/69092	Loss: 139.068
+32000/69092	Loss: 137.237
+35200/69092	Loss: 138.329
+38400/69092	Loss: 137.938
+41600/69092	Loss: 137.570
+44800/69092	Loss: 137.797
+48000/69092	Loss: 138.152
+51200/69092	Loss: 138.618
+54400/69092	Loss: 138.076
+57600/69092	Loss: 135.196
+60800/69092	Loss: 136.452
+64000/69092	Loss: 137.453
+67200/69092	Loss: 139.294
+Training time 0:07:00.654833
+Epoch: 60 Average loss: 137.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 529)
+0/69092	Loss: 133.738
+3200/69092	Loss: 134.620
+6400/69092	Loss: 136.579
+9600/69092	Loss: 137.426
+12800/69092	Loss: 136.900
+16000/69092	Loss: 138.678
+19200/69092	Loss: 136.932
+22400/69092	Loss: 139.108
+25600/69092	Loss: 141.420
+28800/69092	Loss: 138.590
+32000/69092	Loss: 139.324
+35200/69092	Loss: 138.050
+38400/69092	Loss: 137.274
+41600/69092	Loss: 135.879
+44800/69092	Loss: 138.038
+48000/69092	Loss: 138.510
+51200/69092	Loss: 137.849
+54400/69092	Loss: 138.459
+57600/69092	Loss: 139.892
+60800/69092	Loss: 137.455
+64000/69092	Loss: 134.658
+67200/69092	Loss: 138.404
+Training time 0:07:01.776946
+Epoch: 61 Average loss: 137.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 530)
+0/69092	Loss: 131.982
+3200/69092	Loss: 137.668
+6400/69092	Loss: 137.471
+9600/69092	Loss: 136.770
+12800/69092	Loss: 139.134
+16000/69092	Loss: 141.195
+19200/69092	Loss: 138.329
+22400/69092	Loss: 135.135
+25600/69092	Loss: 134.654
+28800/69092	Loss: 136.185
+32000/69092	Loss: 138.731
+35200/69092	Loss: 137.706
+38400/69092	Loss: 137.493
+41600/69092	Loss: 135.834
+44800/69092	Loss: 139.042
+48000/69092	Loss: 137.341
+51200/69092	Loss: 140.636
+54400/69092	Loss: 135.522
+57600/69092	Loss: 140.762
+60800/69092	Loss: 138.525
+64000/69092	Loss: 136.137
+67200/69092	Loss: 135.286
+Training time 0:07:04.396612
+Epoch: 62 Average loss: 137.54
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 531)
+0/69092	Loss: 147.962
+3200/69092	Loss: 137.432
+6400/69092	Loss: 138.314
+9600/69092	Loss: 138.730
+12800/69092	Loss: 137.900
+16000/69092	Loss: 137.458
+19200/69092	Loss: 137.012
+22400/69092	Loss: 138.890
+25600/69092	Loss: 137.425
+28800/69092	Loss: 137.010
+32000/69092	Loss: 136.620
+35200/69092	Loss: 135.696
+38400/69092	Loss: 137.132
+41600/69092	Loss: 137.827
+44800/69092	Loss: 140.106
+48000/69092	Loss: 137.971
+51200/69092	Loss: 139.247
+54400/69092	Loss: 137.742
+57600/69092	Loss: 136.288
+60800/69092	Loss: 135.685
+64000/69092	Loss: 138.932
+67200/69092	Loss: 135.521
+Training time 0:07:03.659487
+Epoch: 63 Average loss: 137.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 532)
+0/69092	Loss: 134.156
+3200/69092	Loss: 136.139
+6400/69092	Loss: 137.592
+9600/69092	Loss: 136.251
+12800/69092	Loss: 138.407
+16000/69092	Loss: 137.472
+19200/69092	Loss: 138.438
+22400/69092	Loss: 137.726
+25600/69092	Loss: 138.266
+28800/69092	Loss: 137.411
+32000/69092	Loss: 135.423
+35200/69092	Loss: 137.246
+38400/69092	Loss: 137.855
+41600/69092	Loss: 139.475
+44800/69092	Loss: 135.943
+48000/69092	Loss: 138.440
+51200/69092	Loss: 137.155
+54400/69092	Loss: 137.327
+57600/69092	Loss: 138.256
+60800/69092	Loss: 136.962
+64000/69092	Loss: 139.903
+67200/69092	Loss: 138.186
+Training time 0:07:05.191189
+Epoch: 64 Average loss: 137.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 533)
+0/69092	Loss: 124.054
+3200/69092	Loss: 136.502
+6400/69092	Loss: 141.074
+9600/69092	Loss: 134.042
+12800/69092	Loss: 137.907
+16000/69092	Loss: 137.449
+19200/69092	Loss: 135.489
+22400/69092	Loss: 135.537
+25600/69092	Loss: 136.524
+28800/69092	Loss: 136.355
+32000/69092	Loss: 139.597
+35200/69092	Loss: 138.198
+38400/69092	Loss: 138.527
+41600/69092	Loss: 137.848
+44800/69092	Loss: 140.554
+48000/69092	Loss: 138.021
+51200/69092	Loss: 138.652
+54400/69092	Loss: 137.813
+57600/69092	Loss: 137.666
+60800/69092	Loss: 140.141
+64000/69092	Loss: 137.083
+67200/69092	Loss: 135.227
+Training time 0:06:54.458840
+Epoch: 65 Average loss: 137.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 534)
+0/69092	Loss: 137.015
+3200/69092	Loss: 136.242
+6400/69092	Loss: 140.350
+9600/69092	Loss: 139.246
+12800/69092	Loss: 136.612
+16000/69092	Loss: 135.598
+19200/69092	Loss: 137.091
+22400/69092	Loss: 138.767
+25600/69092	Loss: 138.182
+28800/69092	Loss: 140.170
+32000/69092	Loss: 136.821
+35200/69092	Loss: 138.787
+38400/69092	Loss: 135.316
+41600/69092	Loss: 137.165
+44800/69092	Loss: 139.105
+48000/69092	Loss: 133.906
+51200/69092	Loss: 139.122
+54400/69092	Loss: 137.000
+57600/69092	Loss: 139.575
+60800/69092	Loss: 137.270
+64000/69092	Loss: 136.107
+67200/69092	Loss: 136.899
+Training time 0:07:06.320470
+Epoch: 66 Average loss: 137.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 535)
+0/69092	Loss: 146.985
+3200/69092	Loss: 137.832
+6400/69092	Loss: 138.364
+9600/69092	Loss: 137.299
+12800/69092	Loss: 139.044
+16000/69092	Loss: 136.803
+19200/69092	Loss: 134.321
+22400/69092	Loss: 137.928
+25600/69092	Loss: 139.011
+28800/69092	Loss: 138.325
+32000/69092	Loss: 140.722
+35200/69092	Loss: 137.246
+38400/69092	Loss: 136.651
+41600/69092	Loss: 137.173
+44800/69092	Loss: 135.233
+48000/69092	Loss: 139.961
+51200/69092	Loss: 137.752
+54400/69092	Loss: 136.899
+57600/69092	Loss: 136.269
+60800/69092	Loss: 136.405
+64000/69092	Loss: 137.252
+67200/69092	Loss: 138.098
+Training time 0:07:04.457213
+Epoch: 67 Average loss: 137.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 536)
+0/69092	Loss: 129.011
+3200/69092	Loss: 137.573
+6400/69092	Loss: 137.191
+9600/69092	Loss: 141.068
+12800/69092	Loss: 138.971
+16000/69092	Loss: 138.117
+19200/69092	Loss: 138.117
+22400/69092	Loss: 136.850
+25600/69092	Loss: 138.008
+28800/69092	Loss: 137.175
+32000/69092	Loss: 137.631
+35200/69092	Loss: 137.360
+38400/69092	Loss: 137.711
+41600/69092	Loss: 136.729
+44800/69092	Loss: 136.005
+48000/69092	Loss: 136.628
+51200/69092	Loss: 137.807
+54400/69092	Loss: 138.695
+57600/69092	Loss: 137.904
+60800/69092	Loss: 136.777
+64000/69092	Loss: 136.034
+67200/69092	Loss: 140.012
+Training time 0:07:04.965682
+Epoch: 68 Average loss: 137.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 537)
+0/69092	Loss: 141.391
+3200/69092	Loss: 136.493
+6400/69092	Loss: 136.826
+9600/69092	Loss: 139.758
+12800/69092	Loss: 137.859
+16000/69092	Loss: 139.534
+19200/69092	Loss: 137.995
+22400/69092	Loss: 136.955
+25600/69092	Loss: 138.184
+28800/69092	Loss: 135.643
+32000/69092	Loss: 139.137
+35200/69092	Loss: 135.635
+38400/69092	Loss: 136.678
+41600/69092	Loss: 137.716
+44800/69092	Loss: 139.362
+48000/69092	Loss: 135.075
+51200/69092	Loss: 136.632
+54400/69092	Loss: 138.942
+57600/69092	Loss: 137.750
+60800/69092	Loss: 136.229
+64000/69092	Loss: 138.707
+67200/69092	Loss: 137.402
+Training time 0:07:05.773331
+Epoch: 69 Average loss: 137.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 538)
+0/69092	Loss: 132.675
+3200/69092	Loss: 139.153
+6400/69092	Loss: 137.262
+9600/69092	Loss: 138.699
+12800/69092	Loss: 138.882
+16000/69092	Loss: 137.230
+19200/69092	Loss: 139.617
+22400/69092	Loss: 135.763
+25600/69092	Loss: 136.216
+28800/69092	Loss: 138.813
+32000/69092	Loss: 136.103
+35200/69092	Loss: 139.341
+38400/69092	Loss: 137.215
+41600/69092	Loss: 137.807
+44800/69092	Loss: 136.433
+48000/69092	Loss: 139.641
+51200/69092	Loss: 136.837
+54400/69092	Loss: 137.899
+57600/69092	Loss: 137.815
+60800/69092	Loss: 135.573
+64000/69092	Loss: 136.348
+67200/69092	Loss: 137.919
+Training time 0:07:07.113460
+Epoch: 70 Average loss: 137.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 539)
+0/69092	Loss: 137.722
+3200/69092	Loss: 138.064
+6400/69092	Loss: 137.198
+9600/69092	Loss: 137.575
+12800/69092	Loss: 138.126
+16000/69092	Loss: 138.735
+19200/69092	Loss: 136.503
+22400/69092	Loss: 136.620
+25600/69092	Loss: 138.162
+28800/69092	Loss: 135.542
+32000/69092	Loss: 137.914
+35200/69092	Loss: 137.214
+38400/69092	Loss: 139.343
+41600/69092	Loss: 138.743
+44800/69092	Loss: 136.413
+48000/69092	Loss: 139.115
+51200/69092	Loss: 136.331
+54400/69092	Loss: 141.294
+57600/69092	Loss: 135.827
+60800/69092	Loss: 137.709
+64000/69092	Loss: 137.452
+67200/69092	Loss: 137.671
+Training time 0:07:04.002163
+Epoch: 71 Average loss: 137.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 540)
+0/69092	Loss: 146.278
+3200/69092	Loss: 138.465
+6400/69092	Loss: 140.116
+9600/69092	Loss: 140.039
+12800/69092	Loss: 135.496
+16000/69092	Loss: 139.682
+19200/69092	Loss: 138.132
+22400/69092	Loss: 138.879
+25600/69092	Loss: 137.383
+28800/69092	Loss: 139.102
+32000/69092	Loss: 138.673
+35200/69092	Loss: 136.501
+38400/69092	Loss: 138.235
+41600/69092	Loss: 136.648
+44800/69092	Loss: 138.070
+48000/69092	Loss: 136.777
+51200/69092	Loss: 134.959
+54400/69092	Loss: 134.498
+57600/69092	Loss: 138.037
+60800/69092	Loss: 135.301
+64000/69092	Loss: 135.833
+67200/69092	Loss: 137.134
+Training time 0:07:06.368706
+Epoch: 72 Average loss: 137.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 541)
+0/69092	Loss: 134.704
+3200/69092	Loss: 136.283
+6400/69092	Loss: 138.422
+9600/69092	Loss: 139.223
+12800/69092	Loss: 137.487
+16000/69092	Loss: 137.320
+19200/69092	Loss: 134.204
+22400/69092	Loss: 136.798
+25600/69092	Loss: 138.050
+28800/69092	Loss: 139.559
+32000/69092	Loss: 139.027
+35200/69092	Loss: 136.201
+38400/69092	Loss: 136.249
+41600/69092	Loss: 138.951
+44800/69092	Loss: 137.797
+48000/69092	Loss: 138.274
+51200/69092	Loss: 135.830
+54400/69092	Loss: 137.948
+57600/69092	Loss: 137.533
+60800/69092	Loss: 137.335
+64000/69092	Loss: 138.393
+67200/69092	Loss: 139.176
+Training time 0:07:06.181894
+Epoch: 73 Average loss: 137.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 542)
+0/69092	Loss: 137.732
+3200/69092	Loss: 136.832
+6400/69092	Loss: 138.588
+9600/69092	Loss: 136.945
+12800/69092	Loss: 140.044
+16000/69092	Loss: 135.502
+19200/69092	Loss: 137.359
+22400/69092	Loss: 138.095
+25600/69092	Loss: 136.973
+28800/69092	Loss: 139.356
+32000/69092	Loss: 137.808
+35200/69092	Loss: 139.502
+38400/69092	Loss: 133.384
+41600/69092	Loss: 138.016
+44800/69092	Loss: 137.544
+48000/69092	Loss: 138.299
+51200/69092	Loss: 136.221
+54400/69092	Loss: 137.073
+57600/69092	Loss: 138.430
+60800/69092	Loss: 137.821
+64000/69092	Loss: 138.034
+67200/69092	Loss: 137.031
+Training time 0:07:02.802141
+Epoch: 74 Average loss: 137.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 543)
+0/69092	Loss: 136.364
+3200/69092	Loss: 138.296
+6400/69092	Loss: 136.257
+9600/69092	Loss: 134.057
+12800/69092	Loss: 142.354
+16000/69092	Loss: 136.352
+19200/69092	Loss: 136.649
+22400/69092	Loss: 139.360
+25600/69092	Loss: 137.896
+28800/69092	Loss: 136.553
+32000/69092	Loss: 136.027
+35200/69092	Loss: 137.389
+38400/69092	Loss: 138.050
+41600/69092	Loss: 140.393
+44800/69092	Loss: 134.139
+48000/69092	Loss: 138.650
+51200/69092	Loss: 139.890
+54400/69092	Loss: 136.628
+57600/69092	Loss: 137.681
+60800/69092	Loss: 138.793
+64000/69092	Loss: 138.470
+67200/69092	Loss: 136.232
+Training time 0:07:01.680507
+Epoch: 75 Average loss: 137.57
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 544)
+0/69092	Loss: 125.191
+3200/69092	Loss: 137.333
+6400/69092	Loss: 135.552
+9600/69092	Loss: 138.416
+12800/69092	Loss: 137.268
+16000/69092	Loss: 135.030
+19200/69092	Loss: 135.297
+22400/69092	Loss: 137.474
+25600/69092	Loss: 136.799
+28800/69092	Loss: 136.738
+32000/69092	Loss: 137.581
+35200/69092	Loss: 139.706
+38400/69092	Loss: 138.981
+41600/69092	Loss: 136.269
+44800/69092	Loss: 139.274
+48000/69092	Loss: 138.364
+51200/69092	Loss: 137.796
+54400/69092	Loss: 140.602
+57600/69092	Loss: 135.647
+60800/69092	Loss: 138.991
+64000/69092	Loss: 136.970
+67200/69092	Loss: 136.869
+Training time 0:06:58.093453
+Epoch: 76 Average loss: 137.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 545)
+0/69092	Loss: 125.852
+3200/69092	Loss: 136.450
+6400/69092	Loss: 137.021
+9600/69092	Loss: 137.864
+12800/69092	Loss: 138.058
+16000/69092	Loss: 136.353
+19200/69092	Loss: 136.587
+22400/69092	Loss: 137.971
+25600/69092	Loss: 137.872
+28800/69092	Loss: 138.742
+32000/69092	Loss: 134.550
+35200/69092	Loss: 137.788
+38400/69092	Loss: 138.389
+41600/69092	Loss: 137.276
+44800/69092	Loss: 139.970
+48000/69092	Loss: 135.863
+51200/69092	Loss: 138.710
+54400/69092	Loss: 137.339
+57600/69092	Loss: 138.083
+60800/69092	Loss: 137.885
+64000/69092	Loss: 137.185
+67200/69092	Loss: 139.148
+Training time 0:07:03.920571
+Epoch: 77 Average loss: 137.53
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 546)
+0/69092	Loss: 161.990
+3200/69092	Loss: 136.146
+6400/69092	Loss: 138.216
+9600/69092	Loss: 135.178
+12800/69092	Loss: 135.306
+16000/69092	Loss: 136.543
+19200/69092	Loss: 135.063
+22400/69092	Loss: 138.407
+25600/69092	Loss: 136.919
+28800/69092	Loss: 137.144
+32000/69092	Loss: 136.522
+35200/69092	Loss: 136.766
+38400/69092	Loss: 140.572
+41600/69092	Loss: 137.852
+44800/69092	Loss: 138.701
+48000/69092	Loss: 138.720
+51200/69092	Loss: 138.819
+54400/69092	Loss: 139.186
+57600/69092	Loss: 138.005
+60800/69092	Loss: 138.772
+64000/69092	Loss: 138.366
+67200/69092	Loss: 137.476
+Training time 0:06:56.971770
+Epoch: 78 Average loss: 137.57
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 547)
+0/69092	Loss: 141.074
+3200/69092	Loss: 139.399
+6400/69092	Loss: 137.958
+9600/69092	Loss: 138.489
+12800/69092	Loss: 137.715
+16000/69092	Loss: 137.938
+19200/69092	Loss: 138.239
+22400/69092	Loss: 136.519
+25600/69092	Loss: 139.257
+28800/69092	Loss: 136.344
+32000/69092	Loss: 137.667
+35200/69092	Loss: 140.520
+38400/69092	Loss: 136.957
+41600/69092	Loss: 135.409
+44800/69092	Loss: 135.888
+48000/69092	Loss: 137.466
+51200/69092	Loss: 136.651
+54400/69092	Loss: 135.856
+57600/69092	Loss: 137.655
+60800/69092	Loss: 135.088
+64000/69092	Loss: 139.647
+67200/69092	Loss: 135.757
+Training time 0:07:00.840281
+Epoch: 79 Average loss: 137.50
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 548)
+0/69092	Loss: 149.243
+3200/69092	Loss: 139.325
+6400/69092	Loss: 139.568
+9600/69092	Loss: 135.900
+12800/69092	Loss: 139.758
+16000/69092	Loss: 138.489
+19200/69092	Loss: 138.312
+22400/69092	Loss: 137.502
+25600/69092	Loss: 137.839
+28800/69092	Loss: 136.501
+32000/69092	Loss: 136.782
+35200/69092	Loss: 139.818
+38400/69092	Loss: 137.017
+41600/69092	Loss: 137.361
+44800/69092	Loss: 137.869
+48000/69092	Loss: 136.965
+51200/69092	Loss: 133.913
+54400/69092	Loss: 137.194
+57600/69092	Loss: 138.555
+60800/69092	Loss: 136.755
+64000/69092	Loss: 137.439
+67200/69092	Loss: 137.417
+Training time 0:06:57.353549
+Epoch: 80 Average loss: 137.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 549)
+0/69092	Loss: 132.335
+3200/69092	Loss: 139.265
+6400/69092	Loss: 138.750
+9600/69092	Loss: 136.960
+12800/69092	Loss: 135.726
+16000/69092	Loss: 135.547
+19200/69092	Loss: 137.831
+22400/69092	Loss: 136.656
+25600/69092	Loss: 138.579
+28800/69092	Loss: 136.462
+32000/69092	Loss: 137.076
+35200/69092	Loss: 136.259
+38400/69092	Loss: 137.406
+41600/69092	Loss: 139.879
+44800/69092	Loss: 135.638
+48000/69092	Loss: 138.535
+51200/69092	Loss: 137.206
+54400/69092	Loss: 137.075
+57600/69092	Loss: 139.439
+60800/69092	Loss: 135.773
+64000/69092	Loss: 138.865
+67200/69092	Loss: 135.904
+Training time 0:07:06.864559
+Epoch: 81 Average loss: 137.39
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 550)
+0/69092	Loss: 140.866
+3200/69092	Loss: 138.285
+6400/69092	Loss: 137.761
+9600/69092	Loss: 138.304
+12800/69092	Loss: 136.499
+16000/69092	Loss: 136.480
+19200/69092	Loss: 137.838
+22400/69092	Loss: 136.413
+25600/69092	Loss: 138.573
+28800/69092	Loss: 137.139
+32000/69092	Loss: 137.225
+35200/69092	Loss: 138.421
+38400/69092	Loss: 138.919
+41600/69092	Loss: 140.307
+44800/69092	Loss: 137.387
+48000/69092	Loss: 136.456
+51200/69092	Loss: 136.025
+54400/69092	Loss: 138.313
+57600/69092	Loss: 137.266
+60800/69092	Loss: 135.909
+64000/69092	Loss: 138.932
+67200/69092	Loss: 138.496
+Training time 0:07:03.108912
+Epoch: 82 Average loss: 137.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 551)
+0/69092	Loss: 138.206
+3200/69092	Loss: 136.312
+6400/69092	Loss: 138.770
+9600/69092	Loss: 137.582
+12800/69092	Loss: 135.256
+16000/69092	Loss: 138.786
+19200/69092	Loss: 136.986
+22400/69092	Loss: 137.961
+25600/69092	Loss: 138.398
+28800/69092	Loss: 138.428
+32000/69092	Loss: 135.836
+35200/69092	Loss: 140.026
+38400/69092	Loss: 135.707
+41600/69092	Loss: 137.970
+44800/69092	Loss: 135.689
+48000/69092	Loss: 137.163
+51200/69092	Loss: 136.484
+54400/69092	Loss: 138.279
+57600/69092	Loss: 139.650
+60800/69092	Loss: 137.564
+64000/69092	Loss: 135.245
+67200/69092	Loss: 140.726
+Training time 0:07:06.806562
+Epoch: 83 Average loss: 137.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 552)
+0/69092	Loss: 131.151
+3200/69092	Loss: 137.296
+6400/69092	Loss: 136.788
+9600/69092	Loss: 137.007
+12800/69092	Loss: 135.409
+16000/69092	Loss: 136.729
+19200/69092	Loss: 137.991
+22400/69092	Loss: 137.267
+25600/69092	Loss: 137.817
+28800/69092	Loss: 138.888
+32000/69092	Loss: 136.990
+35200/69092	Loss: 138.637
+38400/69092	Loss: 138.642
+41600/69092	Loss: 139.335
+44800/69092	Loss: 136.833
+48000/69092	Loss: 137.181
+51200/69092	Loss: 134.951
+54400/69092	Loss: 135.855
+57600/69092	Loss: 137.864
+60800/69092	Loss: 139.015
+64000/69092	Loss: 139.076
+67200/69092	Loss: 136.954
+Training time 0:06:58.165180
+Epoch: 84 Average loss: 137.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 553)
+0/69092	Loss: 128.627
+3200/69092	Loss: 137.839
+6400/69092	Loss: 137.927
+9600/69092	Loss: 139.172
+12800/69092	Loss: 138.357
+16000/69092	Loss: 136.370
+19200/69092	Loss: 138.608
+22400/69092	Loss: 136.235
+25600/69092	Loss: 139.559
+28800/69092	Loss: 139.278
+32000/69092	Loss: 138.273
+35200/69092	Loss: 135.888
+38400/69092	Loss: 134.735
+41600/69092	Loss: 138.573
+44800/69092	Loss: 136.297
+48000/69092	Loss: 138.128
+51200/69092	Loss: 137.511
+54400/69092	Loss: 139.101
+57600/69092	Loss: 137.825
+60800/69092	Loss: 137.810
+64000/69092	Loss: 136.620
+67200/69092	Loss: 138.309
+Training time 0:06:53.044736
+Epoch: 85 Average loss: 137.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 554)
+0/69092	Loss: 126.152
+3200/69092	Loss: 138.757
+6400/69092	Loss: 136.294
+9600/69092	Loss: 137.299
+12800/69092	Loss: 139.085
+16000/69092	Loss: 137.252
+19200/69092	Loss: 137.421
+22400/69092	Loss: 137.717
+25600/69092	Loss: 137.043
+28800/69092	Loss: 138.315
+32000/69092	Loss: 138.541
+35200/69092	Loss: 138.473
+38400/69092	Loss: 138.167
+41600/69092	Loss: 138.028
+44800/69092	Loss: 139.404
+48000/69092	Loss: 138.695
+51200/69092	Loss: 134.336
+54400/69092	Loss: 137.189
+57600/69092	Loss: 136.152
+60800/69092	Loss: 137.611
+64000/69092	Loss: 137.438
+67200/69092	Loss: 137.775
+Training time 0:06:59.588228
+Epoch: 86 Average loss: 137.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 555)
+0/69092	Loss: 128.985
+3200/69092	Loss: 135.065
+6400/69092	Loss: 137.790
+9600/69092	Loss: 137.883
+12800/69092	Loss: 137.759
+16000/69092	Loss: 138.017
+19200/69092	Loss: 135.312
+22400/69092	Loss: 140.561
+25600/69092	Loss: 137.315
+28800/69092	Loss: 138.699
+32000/69092	Loss: 139.333
+35200/69092	Loss: 137.230
+38400/69092	Loss: 135.823
+41600/69092	Loss: 141.030
+44800/69092	Loss: 136.194
+48000/69092	Loss: 139.118
+51200/69092	Loss: 137.136
+54400/69092	Loss: 135.964
+57600/69092	Loss: 137.980
+60800/69092	Loss: 139.524
+64000/69092	Loss: 137.985
+67200/69092	Loss: 136.004
+Training time 0:07:03.033365
+Epoch: 87 Average loss: 137.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 556)
+0/69092	Loss: 134.932
+3200/69092	Loss: 139.005
+6400/69092	Loss: 138.687
+9600/69092	Loss: 136.539
+12800/69092	Loss: 140.354
+16000/69092	Loss: 138.659
+19200/69092	Loss: 136.413
+22400/69092	Loss: 136.883
+25600/69092	Loss: 136.617
+28800/69092	Loss: 134.222
+32000/69092	Loss: 138.373
+35200/69092	Loss: 135.156
+38400/69092	Loss: 139.113
+41600/69092	Loss: 136.176
+44800/69092	Loss: 137.891
+48000/69092	Loss: 138.615
+51200/69092	Loss: 138.471
+54400/69092	Loss: 138.331
+57600/69092	Loss: 139.576
+60800/69092	Loss: 137.767
+64000/69092	Loss: 139.469
+67200/69092	Loss: 136.544
+Training time 0:07:02.798628
+Epoch: 88 Average loss: 137.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 557)
+0/69092	Loss: 156.930
+3200/69092	Loss: 135.866
+6400/69092	Loss: 138.552
+9600/69092	Loss: 137.309
+12800/69092	Loss: 135.493
+16000/69092	Loss: 139.729
+19200/69092	Loss: 135.331
+22400/69092	Loss: 137.346
+25600/69092	Loss: 138.662
+28800/69092	Loss: 137.038
+32000/69092	Loss: 140.117
+35200/69092	Loss: 136.975
+38400/69092	Loss: 139.352
+41600/69092	Loss: 138.388
+44800/69092	Loss: 137.258
+48000/69092	Loss: 139.113
+51200/69092	Loss: 139.074
+54400/69092	Loss: 136.762
+57600/69092	Loss: 137.131
+60800/69092	Loss: 135.860
+64000/69092	Loss: 136.301
+67200/69092	Loss: 136.279
+Training time 0:07:04.790198
+Epoch: 89 Average loss: 137.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 558)
+0/69092	Loss: 138.511
+3200/69092	Loss: 136.210
+6400/69092	Loss: 135.587
+9600/69092	Loss: 138.228
+12800/69092	Loss: 137.891
+16000/69092	Loss: 138.360
+19200/69092	Loss: 138.384
+22400/69092	Loss: 135.816
+25600/69092	Loss: 137.243
+28800/69092	Loss: 140.028
+32000/69092	Loss: 137.089
+35200/69092	Loss: 139.611
+38400/69092	Loss: 137.061
+41600/69092	Loss: 138.263
+44800/69092	Loss: 139.515
+48000/69092	Loss: 138.667
+51200/69092	Loss: 140.072
+54400/69092	Loss: 135.583
+57600/69092	Loss: 138.043
+60800/69092	Loss: 136.352
+64000/69092	Loss: 138.327
+67200/69092	Loss: 135.535
+Training time 0:07:03.313215
+Epoch: 90 Average loss: 137.69
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 559)
+0/69092	Loss: 143.809
+3200/69092	Loss: 134.594
+6400/69092	Loss: 137.333
+9600/69092	Loss: 138.115
+12800/69092	Loss: 138.883
+16000/69092	Loss: 137.260
+19200/69092	Loss: 136.027
+22400/69092	Loss: 137.442
+25600/69092	Loss: 138.602
+28800/69092	Loss: 136.506
+32000/69092	Loss: 137.576
+35200/69092	Loss: 138.102
+38400/69092	Loss: 137.898
+41600/69092	Loss: 136.908
+44800/69092	Loss: 140.000
+48000/69092	Loss: 136.899
+51200/69092	Loss: 140.654
+54400/69092	Loss: 136.052
+57600/69092	Loss: 138.567
+60800/69092	Loss: 138.635
+64000/69092	Loss: 138.058
+67200/69092	Loss: 137.750
+Training time 0:07:03.856442
+Epoch: 91 Average loss: 137.73
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 560)
+0/69092	Loss: 135.565
+3200/69092	Loss: 138.729
+6400/69092	Loss: 139.497
+9600/69092	Loss: 137.149
+12800/69092	Loss: 137.232
+16000/69092	Loss: 135.914
+19200/69092	Loss: 137.866
+22400/69092	Loss: 136.592
+25600/69092	Loss: 138.468
+28800/69092	Loss: 138.532
+32000/69092	Loss: 135.842
+35200/69092	Loss: 135.261
+38400/69092	Loss: 136.950
+41600/69092	Loss: 139.182
+44800/69092	Loss: 136.167
+48000/69092	Loss: 139.098
+51200/69092	Loss: 138.782
+54400/69092	Loss: 137.054
+57600/69092	Loss: 137.813
+60800/69092	Loss: 136.379
+64000/69092	Loss: 135.963
+67200/69092	Loss: 138.597
+Training time 0:06:56.201143
+Epoch: 92 Average loss: 137.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 561)
+0/69092	Loss: 135.278
+3200/69092	Loss: 137.250
+6400/69092	Loss: 136.187
+9600/69092	Loss: 132.068
+12800/69092	Loss: 136.642
+16000/69092	Loss: 137.665
+19200/69092	Loss: 136.472
+22400/69092	Loss: 138.845
+25600/69092	Loss: 137.881
+28800/69092	Loss: 137.139
+32000/69092	Loss: 138.056
+35200/69092	Loss: 135.353
+38400/69092	Loss: 136.853
+41600/69092	Loss: 138.728
+44800/69092	Loss: 139.212
+48000/69092	Loss: 137.727
+51200/69092	Loss: 137.876
+54400/69092	Loss: 140.069
+57600/69092	Loss: 137.047
+60800/69092	Loss: 140.564
+64000/69092	Loss: 136.693
+67200/69092	Loss: 138.684
+Training time 0:07:02.806557
+Epoch: 93 Average loss: 137.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 562)
+0/69092	Loss: 132.208
+3200/69092	Loss: 136.266
+6400/69092	Loss: 135.165
+9600/69092	Loss: 140.734
+12800/69092	Loss: 136.540
+16000/69092	Loss: 137.836
+19200/69092	Loss: 140.870
+22400/69092	Loss: 138.118
+25600/69092	Loss: 137.122
+28800/69092	Loss: 137.464
+32000/69092	Loss: 134.333
+35200/69092	Loss: 137.472
+38400/69092	Loss: 136.207
+41600/69092	Loss: 135.616
+44800/69092	Loss: 137.309
+48000/69092	Loss: 138.895
+51200/69092	Loss: 138.484
+54400/69092	Loss: 136.076
+57600/69092	Loss: 140.025
+60800/69092	Loss: 135.623
+64000/69092	Loss: 137.328
+67200/69092	Loss: 139.125
+Training time 0:07:04.786560
+Epoch: 94 Average loss: 137.41
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 563)
+0/69092	Loss: 150.682
+3200/69092	Loss: 137.684
+6400/69092	Loss: 135.759
+9600/69092	Loss: 134.590
+12800/69092	Loss: 136.999
+16000/69092	Loss: 136.298
+19200/69092	Loss: 137.434
+22400/69092	Loss: 137.408
+25600/69092	Loss: 136.789
+28800/69092	Loss: 136.977
+32000/69092	Loss: 137.441
+35200/69092	Loss: 139.139
+38400/69092	Loss: 137.962
+41600/69092	Loss: 137.652
+44800/69092	Loss: 136.993
+48000/69092	Loss: 138.766
+51200/69092	Loss: 141.769
+54400/69092	Loss: 137.211
+57600/69092	Loss: 135.588
+60800/69092	Loss: 140.397
+64000/69092	Loss: 137.453
+67200/69092	Loss: 136.431
+Training time 0:07:05.200543
+Epoch: 95 Average loss: 137.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 564)
+0/69092	Loss: 135.517
+3200/69092	Loss: 136.046
+6400/69092	Loss: 137.769
+9600/69092	Loss: 136.884
+12800/69092	Loss: 138.431
+16000/69092	Loss: 138.801
+19200/69092	Loss: 135.763
+22400/69092	Loss: 137.235
+25600/69092	Loss: 135.689
+28800/69092	Loss: 138.487
+32000/69092	Loss: 138.191
+35200/69092	Loss: 137.319
+38400/69092	Loss: 138.876
+41600/69092	Loss: 138.423
+44800/69092	Loss: 136.980
+48000/69092	Loss: 135.971
+51200/69092	Loss: 138.629
+54400/69092	Loss: 137.472
+57600/69092	Loss: 135.998
+60800/69092	Loss: 136.609
+64000/69092	Loss: 138.640
+67200/69092	Loss: 138.710
+Training time 0:06:57.307091
+Epoch: 96 Average loss: 137.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 565)
+0/69092	Loss: 145.323
+3200/69092	Loss: 136.216
+6400/69092	Loss: 138.983
+9600/69092	Loss: 138.974
+12800/69092	Loss: 136.031
+16000/69092	Loss: 137.332
+19200/69092	Loss: 137.473
+22400/69092	Loss: 134.256
+25600/69092	Loss: 138.401
+28800/69092	Loss: 139.802
+32000/69092	Loss: 137.772
+35200/69092	Loss: 137.333
+38400/69092	Loss: 136.083
+41600/69092	Loss: 136.849
+44800/69092	Loss: 136.716
+48000/69092	Loss: 136.813
+51200/69092	Loss: 139.985
+54400/69092	Loss: 136.601
+57600/69092	Loss: 138.674
+60800/69092	Loss: 138.393
+64000/69092	Loss: 135.959
+67200/69092	Loss: 137.683
+Training time 0:06:57.217045
+Epoch: 97 Average loss: 137.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 566)
+0/69092	Loss: 121.019
+3200/69092	Loss: 137.140
+6400/69092	Loss: 137.980
+9600/69092	Loss: 135.733
+12800/69092	Loss: 137.737
+16000/69092	Loss: 137.739
+19200/69092	Loss: 139.915
+22400/69092	Loss: 138.259
+25600/69092	Loss: 137.409
+28800/69092	Loss: 136.399
+32000/69092	Loss: 139.573
+35200/69092	Loss: 136.591
+38400/69092	Loss: 138.457
+41600/69092	Loss: 137.257
+44800/69092	Loss: 139.082
+48000/69092	Loss: 138.394
+51200/69092	Loss: 136.753
+54400/69092	Loss: 136.515
+57600/69092	Loss: 139.582
+60800/69092	Loss: 138.280
+64000/69092	Loss: 136.440
+67200/69092	Loss: 136.432
+Training time 0:06:56.682158
+Epoch: 98 Average loss: 137.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 567)
+0/69092	Loss: 162.177
+3200/69092	Loss: 136.476
+6400/69092	Loss: 137.412
+9600/69092	Loss: 137.967
+12800/69092	Loss: 135.089
+16000/69092	Loss: 138.224
+19200/69092	Loss: 135.961
+22400/69092	Loss: 138.583
+25600/69092	Loss: 137.202
+28800/69092	Loss: 138.333
+32000/69092	Loss: 138.282
+35200/69092	Loss: 136.696
+38400/69092	Loss: 137.557
+41600/69092	Loss: 140.194
+44800/69092	Loss: 136.435
+48000/69092	Loss: 135.845
+51200/69092	Loss: 136.661
+54400/69092	Loss: 140.613
+57600/69092	Loss: 136.833
+60800/69092	Loss: 138.077
+64000/69092	Loss: 135.930
+67200/69092	Loss: 139.023
+Training time 0:07:01.005958
+Epoch: 99 Average loss: 137.53
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 568)
+0/69092	Loss: 152.814
+3200/69092	Loss: 135.508
+6400/69092	Loss: 136.148
+9600/69092	Loss: 137.351
+12800/69092	Loss: 138.427
+16000/69092	Loss: 137.623
+19200/69092	Loss: 135.437
+22400/69092	Loss: 137.985
+25600/69092	Loss: 137.637
+28800/69092	Loss: 137.108
+32000/69092	Loss: 139.696
+35200/69092	Loss: 140.132
+38400/69092	Loss: 136.973
+41600/69092	Loss: 139.388
+44800/69092	Loss: 139.250
+48000/69092	Loss: 139.945
+51200/69092	Loss: 138.455
+54400/69092	Loss: 136.112
+57600/69092	Loss: 136.089
+60800/69092	Loss: 137.288
+64000/69092	Loss: 137.065
+67200/69092	Loss: 135.359
+Training time 0:07:07.197932
+Epoch: 100 Average loss: 137.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 569)
+0/69092	Loss: 141.706
+3200/69092	Loss: 140.070
+6400/69092	Loss: 135.587
+9600/69092	Loss: 136.472
+12800/69092	Loss: 136.435
+16000/69092	Loss: 138.586
+19200/69092	Loss: 137.550
+22400/69092	Loss: 138.674
+25600/69092	Loss: 135.954
+28800/69092	Loss: 139.889
+32000/69092	Loss: 140.002
+35200/69092	Loss: 137.279
+38400/69092	Loss: 139.549
+41600/69092	Loss: 138.584
+44800/69092	Loss: 137.056
+48000/69092	Loss: 138.026
+51200/69092	Loss: 139.035
+54400/69092	Loss: 136.527
+57600/69092	Loss: 132.871
+60800/69092	Loss: 135.484
+64000/69092	Loss: 138.275
+67200/69092	Loss: 136.444
+Training time 0:07:03.974461
+Epoch: 101 Average loss: 137.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 570)
+0/69092	Loss: 136.064
+3200/69092	Loss: 139.152
+6400/69092	Loss: 134.847
+9600/69092	Loss: 138.018
+12800/69092	Loss: 136.954
+16000/69092	Loss: 136.100
+19200/69092	Loss: 136.513
+22400/69092	Loss: 138.138
+25600/69092	Loss: 137.796
+28800/69092	Loss: 137.556
+32000/69092	Loss: 139.746
+35200/69092	Loss: 138.035
+38400/69092	Loss: 138.688
+41600/69092	Loss: 135.731
+44800/69092	Loss: 138.542
+48000/69092	Loss: 137.158
+51200/69092	Loss: 136.604
+54400/69092	Loss: 138.319
+57600/69092	Loss: 136.721
+60800/69092	Loss: 137.902
+64000/69092	Loss: 136.349
+67200/69092	Loss: 136.986
+Training time 0:07:03.623227
+Epoch: 102 Average loss: 137.47
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 571)
+0/69092	Loss: 133.811
+3200/69092	Loss: 135.743
+6400/69092	Loss: 138.152
+9600/69092	Loss: 138.356
+12800/69092	Loss: 139.701
+16000/69092	Loss: 136.376
+19200/69092	Loss: 140.075
+22400/69092	Loss: 138.654
+25600/69092	Loss: 137.332
+28800/69092	Loss: 135.600
+32000/69092	Loss: 137.387
+35200/69092	Loss: 134.974
+38400/69092	Loss: 136.499
+41600/69092	Loss: 135.534
+44800/69092	Loss: 138.471
+48000/69092	Loss: 138.219
+51200/69092	Loss: 137.264
+54400/69092	Loss: 135.032
+57600/69092	Loss: 137.345
+60800/69092	Loss: 139.170
+64000/69092	Loss: 138.647
+67200/69092	Loss: 137.419
+Training time 0:07:06.695748
+Epoch: 103 Average loss: 137.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 572)
+0/69092	Loss: 134.644
+3200/69092	Loss: 139.694
+6400/69092	Loss: 137.753
+9600/69092	Loss: 138.768
+12800/69092	Loss: 139.049
+16000/69092	Loss: 137.833
+19200/69092	Loss: 139.649
+22400/69092	Loss: 135.966
+25600/69092	Loss: 140.097
+28800/69092	Loss: 136.961
+32000/69092	Loss: 138.124
+35200/69092	Loss: 136.622
+38400/69092	Loss: 137.996
+41600/69092	Loss: 139.213
+44800/69092	Loss: 135.309
+48000/69092	Loss: 138.735
+51200/69092	Loss: 134.773
+54400/69092	Loss: 135.717
+57600/69092	Loss: 137.293
+60800/69092	Loss: 136.343
+64000/69092	Loss: 137.692
+67200/69092	Loss: 135.065
+Training time 0:06:56.025388
+Epoch: 104 Average loss: 137.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 573)
+0/69092	Loss: 115.409
+3200/69092	Loss: 135.182
+6400/69092	Loss: 135.308
+9600/69092	Loss: 139.501
+12800/69092	Loss: 136.359
+16000/69092	Loss: 140.471
+19200/69092	Loss: 134.181
+22400/69092	Loss: 136.227
+25600/69092	Loss: 134.309
+28800/69092	Loss: 139.164
+32000/69092	Loss: 137.411
+35200/69092	Loss: 138.485
+38400/69092	Loss: 138.820
+41600/69092	Loss: 135.309
+44800/69092	Loss: 137.792
+48000/69092	Loss: 138.016
+51200/69092	Loss: 138.643
+54400/69092	Loss: 139.641
+57600/69092	Loss: 138.841
+60800/69092	Loss: 138.372
+64000/69092	Loss: 137.464
+67200/69092	Loss: 137.479
+Training time 0:06:57.566302
+Epoch: 105 Average loss: 137.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 574)
+0/69092	Loss: 133.853
+3200/69092	Loss: 139.869
+6400/69092	Loss: 140.069
+9600/69092	Loss: 138.346
+12800/69092	Loss: 136.207
+16000/69092	Loss: 135.186
+19200/69092	Loss: 137.963
+22400/69092	Loss: 137.347
+25600/69092	Loss: 138.038
+28800/69092	Loss: 136.558
+32000/69092	Loss: 138.078
+35200/69092	Loss: 140.048
+38400/69092	Loss: 137.205
+41600/69092	Loss: 140.222
+44800/69092	Loss: 138.219
+48000/69092	Loss: 135.378
+51200/69092	Loss: 137.162
+54400/69092	Loss: 138.933
+57600/69092	Loss: 136.469
+60800/69092	Loss: 136.783
+64000/69092	Loss: 137.024
+67200/69092	Loss: 136.859
+Training time 0:07:01.537553
+Epoch: 106 Average loss: 137.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 575)
+0/69092	Loss: 137.980
+3200/69092	Loss: 137.503
+6400/69092	Loss: 137.691
+9600/69092	Loss: 139.284
+12800/69092	Loss: 136.908
+16000/69092	Loss: 135.983
+19200/69092	Loss: 137.016
+22400/69092	Loss: 138.137
+25600/69092	Loss: 135.964
+28800/69092	Loss: 137.611
+32000/69092	Loss: 139.805
+35200/69092	Loss: 137.050
+38400/69092	Loss: 136.471
+41600/69092	Loss: 136.766
+44800/69092	Loss: 138.421
+48000/69092	Loss: 134.423
+51200/69092	Loss: 138.860
+54400/69092	Loss: 135.853
+57600/69092	Loss: 138.341
+60800/69092	Loss: 140.546
+64000/69092	Loss: 137.999
+67200/69092	Loss: 137.015
+Training time 0:07:07.926278
+Epoch: 107 Average loss: 137.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 576)
+0/69092	Loss: 145.514
+3200/69092	Loss: 139.730
+6400/69092	Loss: 137.256
+9600/69092	Loss: 136.303
+12800/69092	Loss: 135.934
+16000/69092	Loss: 138.360
+19200/69092	Loss: 135.878
+22400/69092	Loss: 137.107
+25600/69092	Loss: 135.649
+28800/69092	Loss: 135.059
+32000/69092	Loss: 137.441
+35200/69092	Loss: 138.506
+38400/69092	Loss: 137.365
+41600/69092	Loss: 137.307
+44800/69092	Loss: 137.455
+48000/69092	Loss: 137.289
+51200/69092	Loss: 138.579
+54400/69092	Loss: 137.191
+57600/69092	Loss: 137.107
+60800/69092	Loss: 137.320
+64000/69092	Loss: 138.310
+67200/69092	Loss: 137.822
+Training time 0:07:00.513488
+Epoch: 108 Average loss: 137.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 577)
+0/69092	Loss: 141.379
+3200/69092	Loss: 136.139
+6400/69092	Loss: 137.798
+9600/69092	Loss: 136.773
+12800/69092	Loss: 137.673
+16000/69092	Loss: 137.237
+19200/69092	Loss: 136.986
+22400/69092	Loss: 140.044
+25600/69092	Loss: 139.725
+28800/69092	Loss: 138.112
+32000/69092	Loss: 136.954
+35200/69092	Loss: 137.823
+38400/69092	Loss: 140.456
+41600/69092	Loss: 138.062
+44800/69092	Loss: 138.798
+48000/69092	Loss: 138.383
+51200/69092	Loss: 137.754
+54400/69092	Loss: 136.265
+57600/69092	Loss: 135.813
+60800/69092	Loss: 136.707
+64000/69092	Loss: 134.953
+67200/69092	Loss: 134.579
+Training time 0:07:04.655262
+Epoch: 109 Average loss: 137.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 578)
+0/69092	Loss: 128.293
+3200/69092	Loss: 139.264
+6400/69092	Loss: 136.299
+9600/69092	Loss: 134.699
+12800/69092	Loss: 136.443
+16000/69092	Loss: 138.902
+19200/69092	Loss: 140.745
+22400/69092	Loss: 137.677
+25600/69092	Loss: 137.892
+28800/69092	Loss: 139.421
+32000/69092	Loss: 138.713
+35200/69092	Loss: 137.537
+38400/69092	Loss: 137.053
+41600/69092	Loss: 136.891
+44800/69092	Loss: 135.418
+48000/69092	Loss: 134.783
+51200/69092	Loss: 135.678
+54400/69092	Loss: 137.667
+57600/69092	Loss: 141.672
+60800/69092	Loss: 135.528
+64000/69092	Loss: 138.388
+67200/69092	Loss: 138.926
+Training time 0:07:02.963028
+Epoch: 110 Average loss: 137.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 579)
+0/69092	Loss: 137.559
+3200/69092	Loss: 137.189
+6400/69092	Loss: 137.946
+9600/69092	Loss: 136.702
+12800/69092	Loss: 137.461
+16000/69092	Loss: 137.592
+19200/69092	Loss: 137.227
+22400/69092	Loss: 136.809
+25600/69092	Loss: 138.581
+28800/69092	Loss: 138.867
+32000/69092	Loss: 134.995
+35200/69092	Loss: 137.956
+38400/69092	Loss: 137.545
+41600/69092	Loss: 137.945
+44800/69092	Loss: 137.636
+48000/69092	Loss: 135.896
+51200/69092	Loss: 137.861
+54400/69092	Loss: 134.934
+57600/69092	Loss: 136.871
+60800/69092	Loss: 139.762
+64000/69092	Loss: 136.839
+67200/69092	Loss: 135.480
+Training time 0:07:00.626147
+Epoch: 111 Average loss: 137.32
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 580)
+0/69092	Loss: 125.567
+3200/69092	Loss: 136.137
+6400/69092	Loss: 140.266
+9600/69092	Loss: 134.805
+12800/69092	Loss: 139.812
+16000/69092	Loss: 137.764
+19200/69092	Loss: 138.253
+22400/69092	Loss: 137.063
+25600/69092	Loss: 138.517
+28800/69092	Loss: 139.471
+32000/69092	Loss: 138.131
+35200/69092	Loss: 138.934
+38400/69092	Loss: 136.895
+41600/69092	Loss: 134.084
+44800/69092	Loss: 138.866
+48000/69092	Loss: 137.948
+51200/69092	Loss: 135.488
+54400/69092	Loss: 135.933
+57600/69092	Loss: 139.743
+60800/69092	Loss: 137.825
+64000/69092	Loss: 135.608
+67200/69092	Loss: 136.306
+Training time 0:07:05.222537
+Epoch: 112 Average loss: 137.47
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 581)
+0/69092	Loss: 153.372
+3200/69092	Loss: 139.117
+6400/69092	Loss: 136.387
+9600/69092	Loss: 138.820
+12800/69092	Loss: 135.883
+16000/69092	Loss: 137.461
+19200/69092	Loss: 137.695
+22400/69092	Loss: 137.382
+25600/69092	Loss: 139.382
+28800/69092	Loss: 137.153
+32000/69092	Loss: 136.316
+35200/69092	Loss: 136.986
+38400/69092	Loss: 137.240
+41600/69092	Loss: 134.991
+44800/69092	Loss: 138.945
+48000/69092	Loss: 136.242
+51200/69092	Loss: 136.944
+54400/69092	Loss: 138.345
+57600/69092	Loss: 137.384
+60800/69092	Loss: 136.578
+64000/69092	Loss: 136.218
+67200/69092	Loss: 139.231
+Training time 0:06:59.854447
+Epoch: 113 Average loss: 137.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 582)
+0/69092	Loss: 137.648
+3200/69092	Loss: 135.653
+6400/69092	Loss: 138.243
+9600/69092	Loss: 138.529
+12800/69092	Loss: 138.670
+16000/69092	Loss: 138.867
+19200/69092	Loss: 136.936
+22400/69092	Loss: 137.245
+25600/69092	Loss: 138.667
+28800/69092	Loss: 137.264
+32000/69092	Loss: 137.707
+35200/69092	Loss: 136.237
+38400/69092	Loss: 137.295
+41600/69092	Loss: 138.263
+44800/69092	Loss: 139.045
+48000/69092	Loss: 137.120
+51200/69092	Loss: 136.695
+54400/69092	Loss: 137.372
+57600/69092	Loss: 139.529
+60800/69092	Loss: 135.912
+64000/69092	Loss: 137.278
+67200/69092	Loss: 134.754
+Training time 0:06:58.309749
+Epoch: 114 Average loss: 137.57
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 583)
+0/69092	Loss: 141.072
+3200/69092	Loss: 136.413
+6400/69092	Loss: 138.288
+9600/69092	Loss: 136.578
+12800/69092	Loss: 134.410
+16000/69092	Loss: 137.112
+19200/69092	Loss: 137.461
+22400/69092	Loss: 138.321
+25600/69092	Loss: 138.258
+28800/69092	Loss: 138.000
+32000/69092	Loss: 138.044
+35200/69092	Loss: 134.738
+38400/69092	Loss: 137.557
+41600/69092	Loss: 139.192
+44800/69092	Loss: 139.264
+48000/69092	Loss: 139.239
+51200/69092	Loss: 136.331
+54400/69092	Loss: 134.636
+57600/69092	Loss: 136.842
+60800/69092	Loss: 137.205
+64000/69092	Loss: 137.547
+67200/69092	Loss: 138.280
+Training time 0:07:05.548562
+Epoch: 115 Average loss: 137.38
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 584)
+0/69092	Loss: 145.842
+3200/69092	Loss: 137.567
+6400/69092	Loss: 139.632
+9600/69092	Loss: 137.947
+12800/69092	Loss: 138.653
+16000/69092	Loss: 139.267
+19200/69092	Loss: 138.876
+22400/69092	Loss: 136.472
+25600/69092	Loss: 137.098
+28800/69092	Loss: 135.679
+32000/69092	Loss: 138.471
+35200/69092	Loss: 138.247
+38400/69092	Loss: 136.541
+41600/69092	Loss: 136.532
+44800/69092	Loss: 139.236
+48000/69092	Loss: 135.849
+51200/69092	Loss: 137.262
+54400/69092	Loss: 137.455
+57600/69092	Loss: 136.735
+60800/69092	Loss: 137.607
+64000/69092	Loss: 136.417
+67200/69092	Loss: 136.690
+Training time 0:07:05.753116
+Epoch: 116 Average loss: 137.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 585)
+0/69092	Loss: 151.570
+3200/69092	Loss: 137.654
+6400/69092	Loss: 136.449
+9600/69092	Loss: 137.736
+12800/69092	Loss: 139.626
+16000/69092	Loss: 137.156
+19200/69092	Loss: 139.725
+22400/69092	Loss: 137.440
+25600/69092	Loss: 137.774
+28800/69092	Loss: 137.876
+32000/69092	Loss: 137.504
+35200/69092	Loss: 137.767
+38400/69092	Loss: 135.872
+41600/69092	Loss: 134.913
+44800/69092	Loss: 136.612
+48000/69092	Loss: 137.177
+51200/69092	Loss: 137.634
+54400/69092	Loss: 136.515
+57600/69092	Loss: 137.033
+60800/69092	Loss: 136.308
+64000/69092	Loss: 136.727
+67200/69092	Loss: 139.070
+Training time 0:06:58.613853
+Epoch: 117 Average loss: 137.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 586)
+0/69092	Loss: 134.090
+3200/69092	Loss: 138.902
+6400/69092	Loss: 135.224
+9600/69092	Loss: 136.159
+12800/69092	Loss: 138.267
+16000/69092	Loss: 139.944
+19200/69092	Loss: 137.635
+22400/69092	Loss: 137.235
+25600/69092	Loss: 137.497
+28800/69092	Loss: 137.428
+32000/69092	Loss: 138.361
+35200/69092	Loss: 138.210
+38400/69092	Loss: 137.193
+41600/69092	Loss: 136.893
+44800/69092	Loss: 138.661
+48000/69092	Loss: 138.786
+51200/69092	Loss: 138.698
+54400/69092	Loss: 134.855
+57600/69092	Loss: 136.249
+60800/69092	Loss: 137.639
+64000/69092	Loss: 136.871
+67200/69092	Loss: 135.350
+Training time 0:07:00.850074
+Epoch: 118 Average loss: 137.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 587)
+0/69092	Loss: 171.977
+3200/69092	Loss: 137.320
+6400/69092	Loss: 138.392
+9600/69092	Loss: 135.818
+12800/69092	Loss: 138.777
+16000/69092	Loss: 136.024
+19200/69092	Loss: 136.038
+22400/69092	Loss: 137.182
+25600/69092	Loss: 138.280
+28800/69092	Loss: 138.276
+32000/69092	Loss: 138.332
+35200/69092	Loss: 135.097
+38400/69092	Loss: 136.179
+41600/69092	Loss: 136.777
+44800/69092	Loss: 138.347
+48000/69092	Loss: 137.430
+51200/69092	Loss: 140.122
+54400/69092	Loss: 138.683
+57600/69092	Loss: 137.124
+60800/69092	Loss: 135.644
+64000/69092	Loss: 137.826
+67200/69092	Loss: 138.622
+Training time 0:07:02.131247
+Epoch: 119 Average loss: 137.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 588)
+0/69092	Loss: 152.717
+3200/69092	Loss: 138.368
+6400/69092	Loss: 137.535
+9600/69092	Loss: 136.370
+12800/69092	Loss: 136.407
+16000/69092	Loss: 136.792
+19200/69092	Loss: 135.130
+22400/69092	Loss: 138.735
+25600/69092	Loss: 138.883
+28800/69092	Loss: 138.623
+32000/69092	Loss: 135.149
+35200/69092	Loss: 135.089
+38400/69092	Loss: 139.177
+41600/69092	Loss: 136.699
+44800/69092	Loss: 140.049
+48000/69092	Loss: 136.316
+51200/69092	Loss: 137.850
+54400/69092	Loss: 140.049
+57600/69092	Loss: 136.871
+60800/69092	Loss: 139.197
+64000/69092	Loss: 136.568
+67200/69092	Loss: 135.397
+Training time 0:07:03.655075
+Epoch: 120 Average loss: 137.37
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 589)
+0/69092	Loss: 132.558
+3200/69092	Loss: 138.063
+6400/69092	Loss: 136.856
+9600/69092	Loss: 138.306
+12800/69092	Loss: 135.550
+16000/69092	Loss: 137.790
+19200/69092	Loss: 136.963
+22400/69092	Loss: 136.162
+25600/69092	Loss: 135.081
+28800/69092	Loss: 140.742
+32000/69092	Loss: 138.145
+35200/69092	Loss: 136.324
+38400/69092	Loss: 135.956
+41600/69092	Loss: 136.224
+44800/69092	Loss: 138.495
+48000/69092	Loss: 137.849
+51200/69092	Loss: 141.835
+54400/69092	Loss: 137.177
+57600/69092	Loss: 137.573
+60800/69092	Loss: 134.064
+64000/69092	Loss: 140.345
+67200/69092	Loss: 136.503
+Training time 0:07:05.257540
+Epoch: 121 Average loss: 137.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 590)
+0/69092	Loss: 131.473
+3200/69092	Loss: 137.991
+6400/69092	Loss: 139.076
+9600/69092	Loss: 136.478
+12800/69092	Loss: 139.331
+16000/69092	Loss: 137.023
+19200/69092	Loss: 136.818
+22400/69092	Loss: 136.867
+25600/69092	Loss: 137.229
+28800/69092	Loss: 139.767
+32000/69092	Loss: 137.876
+35200/69092	Loss: 136.088
+38400/69092	Loss: 137.033
+41600/69092	Loss: 135.018
+44800/69092	Loss: 136.151
+48000/69092	Loss: 138.040
+51200/69092	Loss: 137.032
+54400/69092	Loss: 141.154
+57600/69092	Loss: 139.473
+60800/69092	Loss: 136.121
+64000/69092	Loss: 136.973
+67200/69092	Loss: 137.503
+Training time 0:07:00.870921
+Epoch: 122 Average loss: 137.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 591)
+0/69092	Loss: 136.980
+3200/69092	Loss: 138.843
+6400/69092	Loss: 135.193
+9600/69092	Loss: 136.536
+12800/69092	Loss: 139.866
+16000/69092	Loss: 138.544
+19200/69092	Loss: 137.938
+22400/69092	Loss: 140.628
+25600/69092	Loss: 136.704
+28800/69092	Loss: 136.806
+32000/69092	Loss: 138.378
+35200/69092	Loss: 135.525
+38400/69092	Loss: 135.837
+41600/69092	Loss: 139.619
+44800/69092	Loss: 137.959
+48000/69092	Loss: 139.442
+51200/69092	Loss: 136.975
+54400/69092	Loss: 137.200
+57600/69092	Loss: 134.471
+60800/69092	Loss: 137.065
+64000/69092	Loss: 134.798
+67200/69092	Loss: 138.199
+Training time 0:07:04.265169
+Epoch: 123 Average loss: 137.41
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 592)
+0/69092	Loss: 128.618
+3200/69092	Loss: 136.665
+6400/69092	Loss: 135.923
+9600/69092	Loss: 136.460
+12800/69092	Loss: 140.450
+16000/69092	Loss: 138.304
+19200/69092	Loss: 138.977
+22400/69092	Loss: 137.426
+25600/69092	Loss: 136.303
+28800/69092	Loss: 137.072
+32000/69092	Loss: 135.327
+35200/69092	Loss: 136.751
+38400/69092	Loss: 137.739
+41600/69092	Loss: 136.240
+44800/69092	Loss: 140.395
+48000/69092	Loss: 137.255
+51200/69092	Loss: 135.790
+54400/69092	Loss: 136.268
+57600/69092	Loss: 137.469
+60800/69092	Loss: 137.416
+64000/69092	Loss: 136.999
+67200/69092	Loss: 138.404
+Training time 0:07:04.527241
+Epoch: 124 Average loss: 137.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 593)
+0/69092	Loss: 121.268
+3200/69092	Loss: 137.327
+6400/69092	Loss: 139.286
+9600/69092	Loss: 137.549
+12800/69092	Loss: 138.812
+16000/69092	Loss: 135.737
+19200/69092	Loss: 139.260
+22400/69092	Loss: 135.631
+25600/69092	Loss: 136.654
+28800/69092	Loss: 140.085
+32000/69092	Loss: 138.211
+35200/69092	Loss: 137.619
+38400/69092	Loss: 136.551
+41600/69092	Loss: 139.876
+44800/69092	Loss: 134.080
+48000/69092	Loss: 133.602
+51200/69092	Loss: 137.205
+54400/69092	Loss: 139.570
+57600/69092	Loss: 138.744
+60800/69092	Loss: 134.916
+64000/69092	Loss: 138.377
+67200/69092	Loss: 138.605
+Training time 0:07:04.142399
+Epoch: 125 Average loss: 137.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 594)
+0/69092	Loss: 145.567
+3200/69092	Loss: 138.042
+6400/69092	Loss: 137.125
+9600/69092	Loss: 135.972
+12800/69092	Loss: 138.211
+16000/69092	Loss: 138.090
+19200/69092	Loss: 135.951
+22400/69092	Loss: 136.387
+25600/69092	Loss: 137.857
+28800/69092	Loss: 138.654
+32000/69092	Loss: 136.491
+35200/69092	Loss: 137.247
+38400/69092	Loss: 136.684
+41600/69092	Loss: 135.701
+44800/69092	Loss: 136.341
+48000/69092	Loss: 136.988
+51200/69092	Loss: 137.523
+54400/69092	Loss: 138.421
+57600/69092	Loss: 140.860
+60800/69092	Loss: 137.850
+64000/69092	Loss: 138.025
+67200/69092	Loss: 140.309
+Training time 0:07:07.805571
+Epoch: 126 Average loss: 137.57
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 595)
+0/69092	Loss: 126.380
+3200/69092	Loss: 137.297
+6400/69092	Loss: 138.985
+9600/69092	Loss: 136.799
+12800/69092	Loss: 137.521
+16000/69092	Loss: 137.835
+19200/69092	Loss: 137.431
+22400/69092	Loss: 135.658
+25600/69092	Loss: 136.068
+28800/69092	Loss: 139.732
+32000/69092	Loss: 135.400
+35200/69092	Loss: 137.605
+38400/69092	Loss: 137.799
+41600/69092	Loss: 135.339
+44800/69092	Loss: 136.488
+48000/69092	Loss: 137.290
+51200/69092	Loss: 138.326
+54400/69092	Loss: 138.192
+57600/69092	Loss: 136.807
+60800/69092	Loss: 137.925
+64000/69092	Loss: 137.280
+67200/69092	Loss: 137.643
+Training time 0:06:58.995375
+Epoch: 127 Average loss: 137.30
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 596)
+0/69092	Loss: 146.283
+3200/69092	Loss: 137.003
+6400/69092	Loss: 137.233
+9600/69092	Loss: 135.068
+12800/69092	Loss: 137.095
+16000/69092	Loss: 137.024
+19200/69092	Loss: 138.154
+22400/69092	Loss: 138.143
+25600/69092	Loss: 138.279
+28800/69092	Loss: 136.625
+32000/69092	Loss: 140.093
+35200/69092	Loss: 139.978
+38400/69092	Loss: 138.527
+41600/69092	Loss: 134.858
+44800/69092	Loss: 137.498
+48000/69092	Loss: 137.356
+51200/69092	Loss: 137.248
+54400/69092	Loss: 138.795
+57600/69092	Loss: 138.945
+60800/69092	Loss: 135.404
+64000/69092	Loss: 136.427
+67200/69092	Loss: 138.250
+Training time 0:07:00.617462
+Epoch: 128 Average loss: 137.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 597)
+0/69092	Loss: 165.792
+3200/69092	Loss: 138.249
+6400/69092	Loss: 136.161
+9600/69092	Loss: 137.680
+12800/69092	Loss: 137.552
+16000/69092	Loss: 137.025
+19200/69092	Loss: 135.955
+22400/69092	Loss: 136.956
+25600/69092	Loss: 138.004
+28800/69092	Loss: 139.453
+32000/69092	Loss: 139.439
+35200/69092	Loss: 136.909
+38400/69092	Loss: 138.092
+41600/69092	Loss: 136.955
+44800/69092	Loss: 139.026
+48000/69092	Loss: 136.969
+51200/69092	Loss: 138.431
+54400/69092	Loss: 134.469
+57600/69092	Loss: 136.406
+60800/69092	Loss: 137.079
+64000/69092	Loss: 138.073
+67200/69092	Loss: 137.511
+Training time 0:07:06.008605
+Epoch: 129 Average loss: 137.47
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 598)
+0/69092	Loss: 127.436
+3200/69092	Loss: 138.087
+6400/69092	Loss: 137.705
+9600/69092	Loss: 137.799
+12800/69092	Loss: 138.107
+16000/69092	Loss: 136.736
+19200/69092	Loss: 137.785
+22400/69092	Loss: 137.919
+25600/69092	Loss: 136.862
+28800/69092	Loss: 138.022
+32000/69092	Loss: 137.765
+35200/69092	Loss: 137.000
+38400/69092	Loss: 138.694
+41600/69092	Loss: 136.685
+44800/69092	Loss: 137.894
+48000/69092	Loss: 137.223
+51200/69092	Loss: 136.671
+54400/69092	Loss: 137.181
+57600/69092	Loss: 137.252
+60800/69092	Loss: 135.507
+64000/69092	Loss: 136.341
+67200/69092	Loss: 136.376
+Training time 0:06:55.541309
+Epoch: 130 Average loss: 137.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 599)
+0/69092	Loss: 140.502
+3200/69092	Loss: 137.312
+6400/69092	Loss: 137.890
+9600/69092	Loss: 136.323
+12800/69092	Loss: 136.446
+16000/69092	Loss: 136.625
+19200/69092	Loss: 135.409
+22400/69092	Loss: 137.424
+25600/69092	Loss: 138.315
+28800/69092	Loss: 136.871
+32000/69092	Loss: 137.235
+35200/69092	Loss: 139.183
+38400/69092	Loss: 138.625
+41600/69092	Loss: 137.983
+44800/69092	Loss: 134.760
+48000/69092	Loss: 137.889
+51200/69092	Loss: 137.154
+54400/69092	Loss: 136.836
+57600/69092	Loss: 139.668
+60800/69092	Loss: 136.431
+64000/69092	Loss: 138.148
+67200/69092	Loss: 134.985
+Training time 0:07:00.033351
+Epoch: 131 Average loss: 137.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 600)
+0/69092	Loss: 130.557
+3200/69092	Loss: 137.531
+6400/69092	Loss: 136.070
+9600/69092	Loss: 137.658
+12800/69092	Loss: 139.371
+16000/69092	Loss: 139.742
+19200/69092	Loss: 137.672
+22400/69092	Loss: 136.000
+25600/69092	Loss: 138.360
+28800/69092	Loss: 137.908
+32000/69092	Loss: 135.132
+35200/69092	Loss: 137.786
+38400/69092	Loss: 138.021
+41600/69092	Loss: 137.134
+44800/69092	Loss: 137.553
+48000/69092	Loss: 136.758
+51200/69092	Loss: 135.758
+54400/69092	Loss: 136.682
+57600/69092	Loss: 138.759
+60800/69092	Loss: 135.576
+64000/69092	Loss: 137.567
+67200/69092	Loss: 138.935
+Training time 0:07:07.686889
+Epoch: 132 Average loss: 137.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 601)
+0/69092	Loss: 161.495
+3200/69092	Loss: 138.146
+6400/69092	Loss: 136.180
+9600/69092	Loss: 138.562
+12800/69092	Loss: 137.462
+16000/69092	Loss: 136.921
+19200/69092	Loss: 137.476
+22400/69092	Loss: 138.034
+25600/69092	Loss: 138.479
+28800/69092	Loss: 140.286
+32000/69092	Loss: 137.894
+35200/69092	Loss: 133.730
+38400/69092	Loss: 135.882
+41600/69092	Loss: 137.223
+44800/69092	Loss: 137.829
+48000/69092	Loss: 139.202
+51200/69092	Loss: 138.285
+54400/69092	Loss: 137.980
+57600/69092	Loss: 137.312
+60800/69092	Loss: 134.594
+64000/69092	Loss: 135.259
+67200/69092	Loss: 137.067
+Training time 0:07:08.731732
+Epoch: 133 Average loss: 137.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 602)
+0/69092	Loss: 140.403
+3200/69092	Loss: 140.625
+6400/69092	Loss: 136.302
+9600/69092	Loss: 139.991
+12800/69092	Loss: 139.647
+16000/69092	Loss: 137.683
+19200/69092	Loss: 136.367
+22400/69092	Loss: 137.371
+25600/69092	Loss: 136.536
+28800/69092	Loss: 137.439
+32000/69092	Loss: 137.125
+35200/69092	Loss: 138.322
+38400/69092	Loss: 137.686
+41600/69092	Loss: 135.970
+44800/69092	Loss: 137.461
+48000/69092	Loss: 136.866
+51200/69092	Loss: 136.339
+54400/69092	Loss: 137.988
+57600/69092	Loss: 135.839
+60800/69092	Loss: 135.823
+64000/69092	Loss: 135.519
+67200/69092	Loss: 136.271
+Training time 0:07:04.159290
+Epoch: 134 Average loss: 137.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 603)
+0/69092	Loss: 145.135
+3200/69092	Loss: 136.720
+6400/69092	Loss: 138.205
+9600/69092	Loss: 138.502
+12800/69092	Loss: 135.846
+16000/69092	Loss: 135.059
+19200/69092	Loss: 137.166
+22400/69092	Loss: 137.986
+25600/69092	Loss: 138.035
+28800/69092	Loss: 138.575
+32000/69092	Loss: 137.125
+35200/69092	Loss: 135.771
+38400/69092	Loss: 139.069
+41600/69092	Loss: 136.735
+44800/69092	Loss: 135.715
+48000/69092	Loss: 138.296
+51200/69092	Loss: 138.066
+54400/69092	Loss: 138.904
+57600/69092	Loss: 136.491
+60800/69092	Loss: 138.743
+64000/69092	Loss: 135.127
+67200/69092	Loss: 137.690
+Training time 0:07:07.700765
+Epoch: 135 Average loss: 137.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 604)
+0/69092	Loss: 128.222
+3200/69092	Loss: 137.991
+6400/69092	Loss: 137.308
+9600/69092	Loss: 137.646
+12800/69092	Loss: 136.099
+16000/69092	Loss: 139.563
+19200/69092	Loss: 138.335
+22400/69092	Loss: 137.080
+25600/69092	Loss: 138.145
+28800/69092	Loss: 136.891
+32000/69092	Loss: 139.252
+35200/69092	Loss: 138.111
+38400/69092	Loss: 137.264
+41600/69092	Loss: 136.906
+44800/69092	Loss: 137.366
+48000/69092	Loss: 134.073
+51200/69092	Loss: 139.609
+54400/69092	Loss: 136.701
+57600/69092	Loss: 135.146
+60800/69092	Loss: 138.184
+64000/69092	Loss: 137.863
+67200/69092	Loss: 138.237
+Training time 0:07:07.406879
+Epoch: 136 Average loss: 137.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 605)
+0/69092	Loss: 129.378
+3200/69092	Loss: 136.591
+6400/69092	Loss: 136.783
+9600/69092	Loss: 136.987
+12800/69092	Loss: 137.917
+16000/69092	Loss: 138.054
+19200/69092	Loss: 137.635
+22400/69092	Loss: 136.221
+25600/69092	Loss: 134.933
+28800/69092	Loss: 137.075
+32000/69092	Loss: 138.280
+35200/69092	Loss: 137.401
+38400/69092	Loss: 136.186
+41600/69092	Loss: 136.967
+44800/69092	Loss: 138.738
+48000/69092	Loss: 137.726
+51200/69092	Loss: 137.509
+54400/69092	Loss: 135.743
+57600/69092	Loss: 137.574
+60800/69092	Loss: 137.505
+64000/69092	Loss: 136.691
+67200/69092	Loss: 138.826
+Training time 0:07:08.155116
+Epoch: 137 Average loss: 137.28
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 606)
+0/69092	Loss: 137.293
+3200/69092	Loss: 138.179
+6400/69092	Loss: 137.646
+9600/69092	Loss: 137.499
+12800/69092	Loss: 135.902
+16000/69092	Loss: 140.409
+19200/69092	Loss: 138.592
+22400/69092	Loss: 135.634
+25600/69092	Loss: 136.679
+28800/69092	Loss: 135.871
+32000/69092	Loss: 136.854
+35200/69092	Loss: 138.191
+38400/69092	Loss: 136.087
+41600/69092	Loss: 137.149
+44800/69092	Loss: 139.762
+48000/69092	Loss: 137.455
+51200/69092	Loss: 138.770
+54400/69092	Loss: 135.510
+57600/69092	Loss: 135.024
+60800/69092	Loss: 136.312
+64000/69092	Loss: 141.086
+67200/69092	Loss: 137.296
+Training time 0:07:06.211211
+Epoch: 138 Average loss: 137.38
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 607)
+0/69092	Loss: 142.217
+3200/69092	Loss: 135.797
+6400/69092	Loss: 137.642
+9600/69092	Loss: 136.053
+12800/69092	Loss: 137.283
+16000/69092	Loss: 136.665
+19200/69092	Loss: 136.627
+22400/69092	Loss: 138.352
+25600/69092	Loss: 134.875
+28800/69092	Loss: 135.417
+32000/69092	Loss: 135.949
+35200/69092	Loss: 137.704
+38400/69092	Loss: 136.341
+41600/69092	Loss: 136.374
+44800/69092	Loss: 139.884
+48000/69092	Loss: 137.421
+51200/69092	Loss: 137.751
+54400/69092	Loss: 137.959
+57600/69092	Loss: 138.750
+60800/69092	Loss: 136.802
+64000/69092	Loss: 140.060
+67200/69092	Loss: 137.966
+Training time 0:07:00.433339
+Epoch: 139 Average loss: 137.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 608)
+0/69092	Loss: 139.555
+3200/69092	Loss: 137.725
+6400/69092	Loss: 137.070
+9600/69092	Loss: 134.132
+12800/69092	Loss: 135.371
+16000/69092	Loss: 135.437
+19200/69092	Loss: 138.262
+22400/69092	Loss: 137.049
+25600/69092	Loss: 138.480
+28800/69092	Loss: 137.473
+32000/69092	Loss: 135.880
+35200/69092	Loss: 138.249
+38400/69092	Loss: 137.511
+41600/69092	Loss: 140.401
+44800/69092	Loss: 138.418
+48000/69092	Loss: 136.271
+51200/69092	Loss: 139.437
+54400/69092	Loss: 137.623
+57600/69092	Loss: 136.764
+60800/69092	Loss: 138.058
+64000/69092	Loss: 136.513
+67200/69092	Loss: 137.886
+Training time 0:06:59.025088
+Epoch: 140 Average loss: 137.25
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 609)
+0/69092	Loss: 169.637
+3200/69092	Loss: 136.986
+6400/69092	Loss: 136.058
+9600/69092	Loss: 135.499
+12800/69092	Loss: 138.492
+16000/69092	Loss: 136.818
+19200/69092	Loss: 137.664
+22400/69092	Loss: 138.145
+25600/69092	Loss: 137.246
+28800/69092	Loss: 136.003
+32000/69092	Loss: 136.605
+35200/69092	Loss: 138.759
+38400/69092	Loss: 135.479
+41600/69092	Loss: 137.034
+44800/69092	Loss: 139.595
+48000/69092	Loss: 138.058
+51200/69092	Loss: 136.997
+54400/69092	Loss: 136.911
+57600/69092	Loss: 137.186
+60800/69092	Loss: 138.782
+64000/69092	Loss: 135.877
+67200/69092	Loss: 138.309
+Training time 0:06:53.234575
+Epoch: 141 Average loss: 137.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 610)
+0/69092	Loss: 156.874
+3200/69092	Loss: 137.948
+6400/69092	Loss: 136.438
+9600/69092	Loss: 137.237
+12800/69092	Loss: 136.485
+16000/69092	Loss: 136.389
+19200/69092	Loss: 138.609
+22400/69092	Loss: 137.892
+25600/69092	Loss: 136.503
+28800/69092	Loss: 137.340
+32000/69092	Loss: 135.164
+35200/69092	Loss: 138.208
+38400/69092	Loss: 139.728
+41600/69092	Loss: 134.913
+44800/69092	Loss: 139.733
+48000/69092	Loss: 137.594
+51200/69092	Loss: 138.941
+54400/69092	Loss: 138.687
+57600/69092	Loss: 138.452
+60800/69092	Loss: 136.019
+64000/69092	Loss: 137.999
+67200/69092	Loss: 134.458
+Training time 0:07:02.354517
+Epoch: 142 Average loss: 137.44
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 611)
+0/69092	Loss: 131.690
+3200/69092	Loss: 135.874
+6400/69092	Loss: 138.534
+9600/69092	Loss: 134.998
+12800/69092	Loss: 136.687
+16000/69092	Loss: 135.637
+19200/69092	Loss: 136.563
+22400/69092	Loss: 137.114
+25600/69092	Loss: 138.267
+28800/69092	Loss: 137.060
+32000/69092	Loss: 136.518
+35200/69092	Loss: 140.572
+38400/69092	Loss: 135.723
+41600/69092	Loss: 134.804
+44800/69092	Loss: 136.245
+48000/69092	Loss: 139.286
+51200/69092	Loss: 139.640
+54400/69092	Loss: 138.511
+57600/69092	Loss: 138.329
+60800/69092	Loss: 139.234
+64000/69092	Loss: 138.738
+67200/69092	Loss: 134.240
+Training time 0:06:52.148996
+Epoch: 143 Average loss: 137.23
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 612)
+0/69092	Loss: 127.645
+3200/69092	Loss: 139.078
+6400/69092	Loss: 136.389
+9600/69092	Loss: 135.393
+12800/69092	Loss: 138.444
+16000/69092	Loss: 136.113
+19200/69092	Loss: 137.037
+22400/69092	Loss: 137.330
+25600/69092	Loss: 138.036
+28800/69092	Loss: 136.683
+32000/69092	Loss: 138.907
+35200/69092	Loss: 138.892
+38400/69092	Loss: 137.374
+41600/69092	Loss: 135.701
+44800/69092	Loss: 136.058
+48000/69092	Loss: 139.039
+51200/69092	Loss: 139.282
+54400/69092	Loss: 136.387
+57600/69092	Loss: 134.074
+60800/69092	Loss: 136.237
+64000/69092	Loss: 137.707
+67200/69092	Loss: 139.025
+Training time 0:07:02.813147
+Epoch: 144 Average loss: 137.23
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 613)
+0/69092	Loss: 121.295
+3200/69092	Loss: 138.603
+6400/69092	Loss: 139.204
+9600/69092	Loss: 136.954
+12800/69092	Loss: 139.104
+16000/69092	Loss: 135.379
+19200/69092	Loss: 135.079
+22400/69092	Loss: 136.497
+25600/69092	Loss: 135.619
+28800/69092	Loss: 138.272
+32000/69092	Loss: 139.269
+35200/69092	Loss: 138.155
+38400/69092	Loss: 137.333
+41600/69092	Loss: 138.750
+44800/69092	Loss: 136.639
+48000/69092	Loss: 136.508
+51200/69092	Loss: 135.648
+54400/69092	Loss: 134.613
+57600/69092	Loss: 137.506
+60800/69092	Loss: 137.302
+64000/69092	Loss: 138.585
+67200/69092	Loss: 140.736
+Training time 0:07:04.504901
+Epoch: 145 Average loss: 137.42
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 614)
+0/69092	Loss: 122.992
+3200/69092	Loss: 133.984
+6400/69092	Loss: 137.165
+9600/69092	Loss: 136.063
+12800/69092	Loss: 136.980
+16000/69092	Loss: 137.486
+19200/69092	Loss: 139.524
+22400/69092	Loss: 137.150
+25600/69092	Loss: 136.811
+28800/69092	Loss: 139.236
+32000/69092	Loss: 135.751
+35200/69092	Loss: 137.183
+38400/69092	Loss: 137.081
+41600/69092	Loss: 137.353
+44800/69092	Loss: 138.075
+48000/69092	Loss: 140.188
+51200/69092	Loss: 136.717
+54400/69092	Loss: 138.877
+57600/69092	Loss: 137.460
+60800/69092	Loss: 134.799
+64000/69092	Loss: 139.702
+67200/69092	Loss: 137.790
+Training time 0:07:07.564262
+Epoch: 146 Average loss: 137.45
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 615)
+0/69092	Loss: 140.828
+3200/69092	Loss: 138.529
+6400/69092	Loss: 139.063
+9600/69092	Loss: 138.039
+12800/69092	Loss: 135.923
+16000/69092	Loss: 135.723
+19200/69092	Loss: 138.196
+22400/69092	Loss: 137.429
+25600/69092	Loss: 139.711
+28800/69092	Loss: 138.349
+32000/69092	Loss: 134.656
+35200/69092	Loss: 135.567
+38400/69092	Loss: 136.296
+41600/69092	Loss: 134.752
+44800/69092	Loss: 136.391
+48000/69092	Loss: 138.196
+51200/69092	Loss: 137.919
+54400/69092	Loss: 137.477
+57600/69092	Loss: 136.481
+60800/69092	Loss: 139.240
+64000/69092	Loss: 134.034
+67200/69092	Loss: 137.796
+Training time 0:06:57.179378
+Epoch: 147 Average loss: 137.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 616)
+0/69092	Loss: 156.629
+3200/69092	Loss: 138.219
+6400/69092	Loss: 137.189
+9600/69092	Loss: 137.069
+12800/69092	Loss: 137.917
+16000/69092	Loss: 138.196
+19200/69092	Loss: 136.550
+22400/69092	Loss: 136.585
+25600/69092	Loss: 136.999
+28800/69092	Loss: 136.835
+32000/69092	Loss: 134.869
+35200/69092	Loss: 139.333
+38400/69092	Loss: 138.491
+41600/69092	Loss: 136.317
+44800/69092	Loss: 136.428
+48000/69092	Loss: 138.260
+51200/69092	Loss: 137.966
+54400/69092	Loss: 137.451
+57600/69092	Loss: 136.661
+60800/69092	Loss: 137.898
+64000/69092	Loss: 137.740
+67200/69092	Loss: 137.406
+Training time 0:07:02.087132
+Epoch: 148 Average loss: 137.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 617)
+0/69092	Loss: 158.015
+3200/69092	Loss: 139.037
+6400/69092	Loss: 137.449
+9600/69092	Loss: 137.616
+12800/69092	Loss: 139.139
+16000/69092	Loss: 136.246
+19200/69092	Loss: 138.558
+22400/69092	Loss: 135.272
+25600/69092	Loss: 136.072
+28800/69092	Loss: 138.385
+32000/69092	Loss: 138.414
+35200/69092	Loss: 136.668
+38400/69092	Loss: 136.242
+41600/69092	Loss: 138.096
+44800/69092	Loss: 137.044
+48000/69092	Loss: 136.391
+51200/69092	Loss: 137.563
+54400/69092	Loss: 136.547
+57600/69092	Loss: 137.969
+60800/69092	Loss: 136.980
+64000/69092	Loss: 139.396
+67200/69092	Loss: 135.714
+Training time 0:07:02.628499
+Epoch: 149 Average loss: 137.41
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 618)
+0/69092	Loss: 142.375
+3200/69092	Loss: 135.429
+6400/69092	Loss: 136.802
+9600/69092	Loss: 137.530
+12800/69092	Loss: 134.706
+16000/69092	Loss: 138.461
+19200/69092	Loss: 136.250
+22400/69092	Loss: 141.704
+25600/69092	Loss: 141.572
+28800/69092	Loss: 137.391
+32000/69092	Loss: 137.267
+35200/69092	Loss: 138.921
+38400/69092	Loss: 136.591
+41600/69092	Loss: 137.713
+44800/69092	Loss: 139.190
+48000/69092	Loss: 136.354
+51200/69092	Loss: 136.949
+54400/69092	Loss: 135.410
+57600/69092	Loss: 136.229
+60800/69092	Loss: 139.495
+64000/69092	Loss: 137.145
+67200/69092	Loss: 137.040
+Training time 0:07:10.601837
+Epoch: 150 Average loss: 137.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 619)
+0/69092	Loss: 136.625
+3200/69092	Loss: 139.129
+6400/69092	Loss: 135.155
+9600/69092	Loss: 136.351
+12800/69092	Loss: 135.990
+16000/69092	Loss: 135.526
+19200/69092	Loss: 139.599
+22400/69092	Loss: 137.911
+25600/69092	Loss: 136.177
+28800/69092	Loss: 138.429
+32000/69092	Loss: 137.884
+35200/69092	Loss: 139.544
+38400/69092	Loss: 139.152
+41600/69092	Loss: 139.963
+44800/69092	Loss: 135.885
+48000/69092	Loss: 135.894
+51200/69092	Loss: 137.070
+54400/69092	Loss: 139.815
+57600/69092	Loss: 136.968
+60800/69092	Loss: 136.801
+64000/69092	Loss: 134.852
+67200/69092	Loss: 137.998
+Training time 0:07:08.969125
+Epoch: 151 Average loss: 137.38
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 620)
+0/69092	Loss: 129.457
+3200/69092	Loss: 137.548
+6400/69092	Loss: 134.707
+9600/69092	Loss: 137.487
+12800/69092	Loss: 137.299
+16000/69092	Loss: 138.196
+19200/69092	Loss: 138.457
+22400/69092	Loss: 135.305
+25600/69092	Loss: 139.240
+28800/69092	Loss: 140.284
+32000/69092	Loss: 136.700
+35200/69092	Loss: 137.166
+38400/69092	Loss: 138.589
+41600/69092	Loss: 138.048
+44800/69092	Loss: 139.237
+48000/69092	Loss: 136.850
+51200/69092	Loss: 138.358
+54400/69092	Loss: 135.795
+57600/69092	Loss: 135.547
+60800/69092	Loss: 137.474
+64000/69092	Loss: 137.601
+67200/69092	Loss: 135.390
+Training time 0:06:55.050465
+Epoch: 152 Average loss: 137.37
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 621)
+0/69092	Loss: 139.419
+3200/69092	Loss: 134.813
+6400/69092	Loss: 139.945
+9600/69092	Loss: 138.857
+12800/69092	Loss: 137.616
+16000/69092	Loss: 137.496
+19200/69092	Loss: 135.684
+22400/69092	Loss: 137.593
+25600/69092	Loss: 137.000
+28800/69092	Loss: 141.376
+32000/69092	Loss: 137.702
+35200/69092	Loss: 137.900
+38400/69092	Loss: 136.715
+41600/69092	Loss: 137.148
+44800/69092	Loss: 134.471
+48000/69092	Loss: 140.351
+51200/69092	Loss: 140.049
+54400/69092	Loss: 138.434
+57600/69092	Loss: 137.598
+60800/69092	Loss: 133.296
+64000/69092	Loss: 133.871
+67200/69092	Loss: 139.414
+Training time 0:07:05.576331
+Epoch: 153 Average loss: 137.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 622)
+0/69092	Loss: 121.743
+3200/69092	Loss: 136.824
+6400/69092	Loss: 135.275
+9600/69092	Loss: 135.910
+12800/69092	Loss: 138.611
+16000/69092	Loss: 137.371
+19200/69092	Loss: 135.332
+22400/69092	Loss: 139.136
+25600/69092	Loss: 135.997
+28800/69092	Loss: 136.486
+32000/69092	Loss: 136.750
+35200/69092	Loss: 134.836
+38400/69092	Loss: 138.617
+41600/69092	Loss: 139.054
+44800/69092	Loss: 136.880
+48000/69092	Loss: 137.928
+51200/69092	Loss: 137.988
+54400/69092	Loss: 137.811
+57600/69092	Loss: 139.803
+60800/69092	Loss: 136.498
+64000/69092	Loss: 135.327
+67200/69092	Loss: 139.255
+Training time 0:07:06.546023
+Epoch: 154 Average loss: 137.32
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 623)
+0/69092	Loss: 120.645
+3200/69092	Loss: 136.487
+6400/69092	Loss: 136.118
+9600/69092	Loss: 137.346
+12800/69092	Loss: 137.554
+16000/69092	Loss: 137.785
+19200/69092	Loss: 136.478
+22400/69092	Loss: 139.375
+25600/69092	Loss: 137.938
+28800/69092	Loss: 136.584
+32000/69092	Loss: 137.618
+35200/69092	Loss: 136.851
+38400/69092	Loss: 137.817
+41600/69092	Loss: 135.837
+44800/69092	Loss: 138.166
+48000/69092	Loss: 135.931
+51200/69092	Loss: 139.016
+54400/69092	Loss: 138.224
+57600/69092	Loss: 138.886
+60800/69092	Loss: 139.036
+64000/69092	Loss: 137.669
+67200/69092	Loss: 134.812
+Training time 0:07:02.154645
+Epoch: 155 Average loss: 137.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 624)
+0/69092	Loss: 124.046
+3200/69092	Loss: 136.456
+6400/69092	Loss: 139.995
+9600/69092	Loss: 140.252
+12800/69092	Loss: 138.071
+16000/69092	Loss: 135.230
+19200/69092	Loss: 137.541
+22400/69092	Loss: 137.609
+25600/69092	Loss: 137.746
+28800/69092	Loss: 133.935
+32000/69092	Loss: 136.519
+35200/69092	Loss: 137.143
+38400/69092	Loss: 136.310
+41600/69092	Loss: 139.143
+44800/69092	Loss: 137.373
+48000/69092	Loss: 137.086
+51200/69092	Loss: 135.817
+54400/69092	Loss: 134.919
+57600/69092	Loss: 136.346
+60800/69092	Loss: 138.308
+64000/69092	Loss: 136.880
+67200/69092	Loss: 136.680
+Training time 0:07:15.274479
+Epoch: 156 Average loss: 137.14
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 625)
+0/69092	Loss: 117.992
+3200/69092	Loss: 136.054
+6400/69092	Loss: 137.630
+9600/69092	Loss: 137.238
+12800/69092	Loss: 136.589
+16000/69092	Loss: 135.125
+19200/69092	Loss: 140.689
+22400/69092	Loss: 136.195
+25600/69092	Loss: 137.085
+28800/69092	Loss: 137.474
+32000/69092	Loss: 137.548
+35200/69092	Loss: 137.555
+38400/69092	Loss: 135.891
+41600/69092	Loss: 136.732
+44800/69092	Loss: 139.782
+48000/69092	Loss: 136.235
+51200/69092	Loss: 140.333
+54400/69092	Loss: 138.651
+57600/69092	Loss: 138.706
+60800/69092	Loss: 137.753
+64000/69092	Loss: 134.910
+67200/69092	Loss: 135.398
+Training time 0:07:11.144289
+Epoch: 157 Average loss: 137.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 626)
+0/69092	Loss: 133.730
+3200/69092	Loss: 137.699
+6400/69092	Loss: 137.510
+9600/69092	Loss: 137.051
+12800/69092	Loss: 138.015
+16000/69092	Loss: 137.267
+19200/69092	Loss: 138.071
+22400/69092	Loss: 136.123
+25600/69092	Loss: 136.885
+28800/69092	Loss: 136.107
+32000/69092	Loss: 136.444
+35200/69092	Loss: 138.473
+38400/69092	Loss: 138.295
+41600/69092	Loss: 137.404
+44800/69092	Loss: 135.692
+48000/69092	Loss: 137.100
+51200/69092	Loss: 135.978
+54400/69092	Loss: 137.572
+57600/69092	Loss: 140.156
+60800/69092	Loss: 137.552
+64000/69092	Loss: 136.765
+67200/69092	Loss: 138.244
+Training time 0:07:04.959482
+Epoch: 158 Average loss: 137.32
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 627)
+0/69092	Loss: 141.186
+3200/69092	Loss: 139.635
+6400/69092	Loss: 137.073
+9600/69092	Loss: 135.146
+12800/69092	Loss: 136.737
+16000/69092	Loss: 138.353
+19200/69092	Loss: 135.922
+22400/69092	Loss: 138.326
+25600/69092	Loss: 135.771
+28800/69092	Loss: 136.010
+32000/69092	Loss: 138.027
+35200/69092	Loss: 136.506
+38400/69092	Loss: 138.816
+41600/69092	Loss: 138.494
+44800/69092	Loss: 136.181
+48000/69092	Loss: 137.089
+51200/69092	Loss: 139.949
+54400/69092	Loss: 136.674
+57600/69092	Loss: 136.139
+60800/69092	Loss: 137.370
+64000/69092	Loss: 137.611
+67200/69092	Loss: 135.653
+Training time 0:06:59.543655
+Epoch: 159 Average loss: 137.22
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 628)
+0/69092	Loss: 135.930
+3200/69092	Loss: 135.911
+6400/69092	Loss: 139.102
+9600/69092	Loss: 138.464
+12800/69092	Loss: 136.776
+16000/69092	Loss: 135.898
+19200/69092	Loss: 137.792
+22400/69092	Loss: 137.491
+25600/69092	Loss: 137.447
+28800/69092	Loss: 135.576
+32000/69092	Loss: 139.326
+35200/69092	Loss: 137.588
+38400/69092	Loss: 139.188
+41600/69092	Loss: 136.802
+44800/69092	Loss: 136.496
+48000/69092	Loss: 138.510
+51200/69092	Loss: 135.761
+54400/69092	Loss: 135.612
+57600/69092	Loss: 136.575
+60800/69092	Loss: 137.163
+64000/69092	Loss: 139.689
+67200/69092	Loss: 139.965
+Training time 0:07:04.670691
+Epoch: 160 Average loss: 137.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 629)
+0/69092	Loss: 127.680
+3200/69092	Loss: 140.615
+6400/69092	Loss: 137.274
+9600/69092	Loss: 137.831
+12800/69092	Loss: 138.321
+16000/69092	Loss: 136.146
+19200/69092	Loss: 135.832
+22400/69092	Loss: 135.858
+25600/69092	Loss: 135.342
+28800/69092	Loss: 136.666
+32000/69092	Loss: 138.164
+35200/69092	Loss: 137.514
+38400/69092	Loss: 138.985
+41600/69092	Loss: 137.945
+44800/69092	Loss: 134.614
+48000/69092	Loss: 136.510
+51200/69092	Loss: 138.740
+54400/69092	Loss: 137.430
+57600/69092	Loss: 135.528
+60800/69092	Loss: 139.216
+64000/69092	Loss: 138.054
+67200/69092	Loss: 136.934
+Training time 0:07:04.696100
+Epoch: 161 Average loss: 137.28
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 630)
+0/69092	Loss: 128.855
+3200/69092	Loss: 137.804
+6400/69092	Loss: 136.401
+9600/69092	Loss: 138.942
+12800/69092	Loss: 137.867
+16000/69092	Loss: 137.871
+19200/69092	Loss: 138.055
+22400/69092	Loss: 138.680
+25600/69092	Loss: 138.562
+28800/69092	Loss: 135.947
+32000/69092	Loss: 137.661
+35200/69092	Loss: 134.759
+38400/69092	Loss: 138.724
+41600/69092	Loss: 137.489
+44800/69092	Loss: 136.678
+48000/69092	Loss: 136.760
+51200/69092	Loss: 134.139
+54400/69092	Loss: 138.430
+57600/69092	Loss: 136.863
+60800/69092	Loss: 137.694
+64000/69092	Loss: 136.665
+67200/69092	Loss: 140.952
+Training time 0:07:02.998019
+Epoch: 162 Average loss: 137.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 631)
+0/69092	Loss: 128.680
+3200/69092	Loss: 136.458
+6400/69092	Loss: 137.841
+9600/69092	Loss: 138.255
+12800/69092	Loss: 138.047
+16000/69092	Loss: 137.012
+19200/69092	Loss: 137.025
+22400/69092	Loss: 135.496
+25600/69092	Loss: 138.328
+28800/69092	Loss: 137.912
+32000/69092	Loss: 136.231
+35200/69092	Loss: 137.612
+38400/69092	Loss: 137.193
+41600/69092	Loss: 136.259
+44800/69092	Loss: 135.605
+48000/69092	Loss: 137.525
+51200/69092	Loss: 138.592
+54400/69092	Loss: 136.616
+57600/69092	Loss: 136.308
+60800/69092	Loss: 136.479
+64000/69092	Loss: 138.310
+67200/69092	Loss: 138.280
+Training time 0:07:05.804628
+Epoch: 163 Average loss: 137.22
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 632)
+0/69092	Loss: 129.115
+3200/69092	Loss: 136.749
+6400/69092	Loss: 137.629
+9600/69092	Loss: 136.888
+12800/69092	Loss: 138.472
+16000/69092	Loss: 138.795
+19200/69092	Loss: 138.384
+22400/69092	Loss: 137.504
+25600/69092	Loss: 136.772
+28800/69092	Loss: 139.005
+32000/69092	Loss: 137.004
+35200/69092	Loss: 137.964
+38400/69092	Loss: 136.984
+41600/69092	Loss: 136.172
+44800/69092	Loss: 135.261
+48000/69092	Loss: 138.485
+51200/69092	Loss: 133.876
+54400/69092	Loss: 140.018
+57600/69092	Loss: 136.785
+60800/69092	Loss: 136.879
+64000/69092	Loss: 137.706
+67200/69092	Loss: 137.032
+Training time 0:06:54.692784
+Epoch: 164 Average loss: 137.42
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 633)
+0/69092	Loss: 147.345
+3200/69092	Loss: 137.095
+6400/69092	Loss: 137.712
+9600/69092	Loss: 136.241
+12800/69092	Loss: 137.236
+16000/69092	Loss: 136.562
+19200/69092	Loss: 137.944
+22400/69092	Loss: 137.646
+25600/69092	Loss: 137.432
+28800/69092	Loss: 138.938
+32000/69092	Loss: 133.844
+35200/69092	Loss: 138.869
+38400/69092	Loss: 136.333
+41600/69092	Loss: 138.314
+44800/69092	Loss: 137.465
+48000/69092	Loss: 137.144
+51200/69092	Loss: 137.217
+54400/69092	Loss: 136.154
+57600/69092	Loss: 136.466
+60800/69092	Loss: 138.365
+64000/69092	Loss: 137.691
+67200/69092	Loss: 138.381
+Training time 0:06:57.115571
+Epoch: 165 Average loss: 137.45
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 634)
+0/69092	Loss: 145.605
+3200/69092	Loss: 140.393
+6400/69092	Loss: 134.598
+9600/69092	Loss: 138.350
+12800/69092	Loss: 135.411
+16000/69092	Loss: 139.057
+19200/69092	Loss: 137.853
+22400/69092	Loss: 136.918
+25600/69092	Loss: 138.213
+28800/69092	Loss: 136.805
+32000/69092	Loss: 137.913
+35200/69092	Loss: 137.967
+38400/69092	Loss: 135.102
+41600/69092	Loss: 140.336
+44800/69092	Loss: 138.614
+48000/69092	Loss: 137.457
+51200/69092	Loss: 135.858
+54400/69092	Loss: 135.490
+57600/69092	Loss: 136.074
+60800/69092	Loss: 138.006
+64000/69092	Loss: 137.950
+67200/69092	Loss: 136.088
+Training time 0:07:09.889647
+Epoch: 166 Average loss: 137.38
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 635)
+0/69092	Loss: 136.224
+3200/69092	Loss: 136.230
+6400/69092	Loss: 135.314
+9600/69092	Loss: 134.625
+12800/69092	Loss: 139.331
+16000/69092	Loss: 139.176
+19200/69092	Loss: 135.674
+22400/69092	Loss: 135.796
+25600/69092	Loss: 137.893
+28800/69092	Loss: 139.104
+32000/69092	Loss: 137.726
+35200/69092	Loss: 138.345
+38400/69092	Loss: 137.796
+41600/69092	Loss: 136.110
+44800/69092	Loss: 138.004
+48000/69092	Loss: 136.473
+51200/69092	Loss: 137.527
+54400/69092	Loss: 138.407
+57600/69092	Loss: 138.281
+60800/69092	Loss: 135.763
+64000/69092	Loss: 135.982
+67200/69092	Loss: 140.734
+Training time 0:07:02.986309
+Epoch: 167 Average loss: 137.41
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 636)
+0/69092	Loss: 125.382
+3200/69092	Loss: 141.314
+6400/69092	Loss: 136.799
+9600/69092	Loss: 137.675
+12800/69092	Loss: 136.521
+16000/69092	Loss: 137.020
+19200/69092	Loss: 138.286
+22400/69092	Loss: 136.919
+25600/69092	Loss: 137.289
+28800/69092	Loss: 133.581
+32000/69092	Loss: 135.955
+35200/69092	Loss: 136.563
+38400/69092	Loss: 137.093
+41600/69092	Loss: 138.113
+44800/69092	Loss: 137.992
+48000/69092	Loss: 139.808
+51200/69092	Loss: 138.051
+54400/69092	Loss: 136.606
+57600/69092	Loss: 137.671
+60800/69092	Loss: 137.234
+64000/69092	Loss: 138.672
+67200/69092	Loss: 135.372
+Training time 0:06:59.504046
+Epoch: 168 Average loss: 137.37
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 637)
+0/69092	Loss: 133.032
+3200/69092	Loss: 137.790
+6400/69092	Loss: 136.188
+9600/69092	Loss: 138.190
+12800/69092	Loss: 134.532
+16000/69092	Loss: 136.832
+19200/69092	Loss: 136.750
+22400/69092	Loss: 139.038
+25600/69092	Loss: 138.768
+28800/69092	Loss: 138.300
+32000/69092	Loss: 140.379
+35200/69092	Loss: 135.434
+38400/69092	Loss: 137.300
+41600/69092	Loss: 137.053
+44800/69092	Loss: 137.444
+48000/69092	Loss: 137.713
+51200/69092	Loss: 137.082
+54400/69092	Loss: 137.810
+57600/69092	Loss: 136.607
+60800/69092	Loss: 138.038
+64000/69092	Loss: 137.399
+67200/69092	Loss: 135.843
+Training time 0:07:01.328662
+Epoch: 169 Average loss: 137.44
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 638)
+0/69092	Loss: 141.717
+3200/69092	Loss: 137.220
+6400/69092	Loss: 137.196
+9600/69092	Loss: 135.865
+12800/69092	Loss: 138.326
+16000/69092	Loss: 134.038
+19200/69092	Loss: 136.452
+22400/69092	Loss: 138.033
+25600/69092	Loss: 135.072
+28800/69092	Loss: 136.660
+32000/69092	Loss: 137.697
+35200/69092	Loss: 137.152
+38400/69092	Loss: 138.974
+41600/69092	Loss: 137.060
+44800/69092	Loss: 138.959
+48000/69092	Loss: 137.970
+51200/69092	Loss: 136.799
+54400/69092	Loss: 138.721
+57600/69092	Loss: 139.594
+60800/69092	Loss: 137.153
+64000/69092	Loss: 138.230
+67200/69092	Loss: 135.638
+Training time 0:07:02.377090
+Epoch: 170 Average loss: 137.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 639)
+0/69092	Loss: 123.992
+3200/69092	Loss: 137.682
+6400/69092	Loss: 137.247
+9600/69092	Loss: 135.949
+12800/69092	Loss: 136.682
+16000/69092	Loss: 136.130
+19200/69092	Loss: 138.974
+22400/69092	Loss: 137.731
+25600/69092	Loss: 136.103
+28800/69092	Loss: 138.550
+32000/69092	Loss: 136.896
+35200/69092	Loss: 137.622
+38400/69092	Loss: 136.963
+41600/69092	Loss: 136.296
+44800/69092	Loss: 136.759
+48000/69092	Loss: 140.318
+51200/69092	Loss: 136.411
+54400/69092	Loss: 138.086
+57600/69092	Loss: 135.491
+60800/69092	Loss: 137.948
+64000/69092	Loss: 137.991
+67200/69092	Loss: 135.457
+Training time 0:07:01.536069
+Epoch: 171 Average loss: 137.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 640)
+0/69092	Loss: 136.708
+3200/69092	Loss: 137.422
+6400/69092	Loss: 134.495
+9600/69092	Loss: 135.260
+12800/69092	Loss: 136.142
+16000/69092	Loss: 137.661
+19200/69092	Loss: 135.320
+22400/69092	Loss: 137.400
+25600/69092	Loss: 138.398
+28800/69092	Loss: 138.920
+32000/69092	Loss: 137.235
+35200/69092	Loss: 138.165
+38400/69092	Loss: 134.705
+41600/69092	Loss: 139.482
+44800/69092	Loss: 137.887
+48000/69092	Loss: 137.788
+51200/69092	Loss: 139.340
+54400/69092	Loss: 138.944
+57600/69092	Loss: 138.420
+60800/69092	Loss: 136.808
+64000/69092	Loss: 139.406
+67200/69092	Loss: 137.098
+Training time 0:07:03.423821
+Epoch: 172 Average loss: 137.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 641)
+0/69092	Loss: 132.639
+3200/69092	Loss: 137.087
+6400/69092	Loss: 139.271
+9600/69092	Loss: 136.309
+12800/69092	Loss: 136.404
+16000/69092	Loss: 135.161
+19200/69092	Loss: 135.830
+22400/69092	Loss: 136.829
+25600/69092	Loss: 135.491
+28800/69092	Loss: 138.850
+32000/69092	Loss: 133.894
+35200/69092	Loss: 138.197
+38400/69092	Loss: 136.736
+41600/69092	Loss: 137.061
+44800/69092	Loss: 135.063
+48000/69092	Loss: 139.652
+51200/69092	Loss: 138.461
+54400/69092	Loss: 136.956
+57600/69092	Loss: 137.720
+60800/69092	Loss: 137.971
+64000/69092	Loss: 137.992
+67200/69092	Loss: 138.081
+Training time 0:07:06.304808
+Epoch: 173 Average loss: 137.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 642)
+0/69092	Loss: 148.388
+3200/69092	Loss: 135.785
+6400/69092	Loss: 137.679
+9600/69092	Loss: 137.744
+12800/69092	Loss: 138.848
+16000/69092	Loss: 137.159
+19200/69092	Loss: 138.104
+22400/69092	Loss: 137.650
+25600/69092	Loss: 135.661
+28800/69092	Loss: 137.016
+32000/69092	Loss: 137.279
+35200/69092	Loss: 137.231
+38400/69092	Loss: 139.299
+41600/69092	Loss: 137.836
+44800/69092	Loss: 137.040
+48000/69092	Loss: 137.062
+51200/69092	Loss: 137.580
+54400/69092	Loss: 135.841
+57600/69092	Loss: 139.646
+60800/69092	Loss: 136.046
+64000/69092	Loss: 135.742
+67200/69092	Loss: 137.801
+Training time 0:06:59.685285
+Epoch: 174 Average loss: 137.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 643)
+0/69092	Loss: 139.189
+3200/69092	Loss: 137.419
+6400/69092	Loss: 139.871
+9600/69092	Loss: 135.855
+12800/69092	Loss: 138.632
+16000/69092	Loss: 136.547
+19200/69092	Loss: 136.968
+22400/69092	Loss: 138.490
+25600/69092	Loss: 136.767
+28800/69092	Loss: 138.016
+32000/69092	Loss: 136.103
+35200/69092	Loss: 135.975
+38400/69092	Loss: 136.876
+41600/69092	Loss: 135.559
+44800/69092	Loss: 139.379
+48000/69092	Loss: 135.144
+51200/69092	Loss: 141.037
+54400/69092	Loss: 137.935
+57600/69092	Loss: 136.973
+60800/69092	Loss: 136.365
+64000/69092	Loss: 137.618
+67200/69092	Loss: 137.089
+Training time 0:06:59.145267
+Epoch: 175 Average loss: 137.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 644)
+0/69092	Loss: 134.153
+3200/69092	Loss: 136.646
+6400/69092	Loss: 135.994
+9600/69092	Loss: 137.880
+12800/69092	Loss: 136.118
+16000/69092	Loss: 136.165
+19200/69092	Loss: 135.870
+22400/69092	Loss: 136.137
+25600/69092	Loss: 138.196
+28800/69092	Loss: 139.644
+32000/69092	Loss: 136.251
+35200/69092	Loss: 135.749
+38400/69092	Loss: 138.907
+41600/69092	Loss: 138.745
+44800/69092	Loss: 138.036
+48000/69092	Loss: 134.538
+51200/69092	Loss: 135.657
+54400/69092	Loss: 139.340
+57600/69092	Loss: 138.619
+60800/69092	Loss: 137.635
+64000/69092	Loss: 138.167
+67200/69092	Loss: 137.430
+Training time 0:06:56.086483
+Epoch: 176 Average loss: 137.25
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 645)
+0/69092	Loss: 127.767
+3200/69092	Loss: 135.259
+6400/69092	Loss: 137.364
+9600/69092	Loss: 138.035
+12800/69092	Loss: 138.614
+16000/69092	Loss: 136.309
+19200/69092	Loss: 137.662
+22400/69092	Loss: 137.079
+25600/69092	Loss: 138.845
+28800/69092	Loss: 136.859
+32000/69092	Loss: 137.136
+35200/69092	Loss: 136.194
+38400/69092	Loss: 136.897
+41600/69092	Loss: 136.828
+44800/69092	Loss: 137.545
+48000/69092	Loss: 138.922
+51200/69092	Loss: 136.868
+54400/69092	Loss: 139.543
+57600/69092	Loss: 137.975
+60800/69092	Loss: 139.122
+64000/69092	Loss: 137.569
+67200/69092	Loss: 135.618
+Training time 0:07:04.567286
+Epoch: 177 Average loss: 137.41
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 646)
+0/69092	Loss: 139.475
+3200/69092	Loss: 135.280
+6400/69092	Loss: 135.869
+9600/69092	Loss: 135.646
+12800/69092	Loss: 139.043
+16000/69092	Loss: 137.428
+19200/69092	Loss: 136.605
+22400/69092	Loss: 137.416
+25600/69092	Loss: 137.479
+28800/69092	Loss: 135.880
+32000/69092	Loss: 135.239
+35200/69092	Loss: 137.418
+38400/69092	Loss: 136.794
+41600/69092	Loss: 138.655
+44800/69092	Loss: 137.671
+48000/69092	Loss: 138.197
+51200/69092	Loss: 135.071
+54400/69092	Loss: 137.690
+57600/69092	Loss: 140.763
+60800/69092	Loss: 138.863
+64000/69092	Loss: 136.654
+67200/69092	Loss: 138.094
+Training time 0:06:56.750453
+Epoch: 178 Average loss: 137.28
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 647)
+0/69092	Loss: 139.799
+3200/69092	Loss: 135.600
+6400/69092	Loss: 135.783
+9600/69092	Loss: 139.319
+12800/69092	Loss: 139.130
+16000/69092	Loss: 138.631
+19200/69092	Loss: 140.573
+22400/69092	Loss: 140.244
+25600/69092	Loss: 137.789
+28800/69092	Loss: 135.270
+32000/69092	Loss: 135.486
+35200/69092	Loss: 133.635
+38400/69092	Loss: 135.808
+41600/69092	Loss: 137.640
+44800/69092	Loss: 139.202
+48000/69092	Loss: 136.712
+51200/69092	Loss: 140.177
+54400/69092	Loss: 137.734
+57600/69092	Loss: 138.416
+60800/69092	Loss: 135.477
+64000/69092	Loss: 137.688
+67200/69092	Loss: 136.632
+Training time 0:07:04.804265
+Epoch: 179 Average loss: 137.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last' (iter 648)
+0/69092	Loss: 128.183
+3200/69092	Loss: 136.450
+6400/69092	Loss: 136.428
+9600/69092	Loss: 137.765
+12800/69092	Loss: 136.786
+16000/69092	Loss: 135.401
+19200/69092	Loss: 137.445
+22400/69092	Loss: 138.064
+25600/69092	Loss: 135.685
+28800/69092	Loss: 138.150
+32000/69092	Loss: 138.632
+35200/69092	Loss: 138.078
+38400/69092	Loss: 136.317
diff --git a/OAR.2073653.stderr b/OAR.2073653.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..53728a5c11f597b145dad300082ce7a98171a1c5
--- /dev/null
+++ b/OAR.2073653.stderr
@@ -0,0 +1,3 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+## OAR [2020-07-07 08:29:29] Job 2073653 KILLED ##
diff --git a/OAR.2073653.stdout b/OAR.2073653.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..e8dcd8bf1a151990f120b32b2da9dac7139df3cd
--- /dev/null
+++ b/OAR.2073653.stdout
@@ -0,0 +1,6439 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64_ls_15', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=15, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+GeForce RTX 2080 Ti
+GeForce RTX 2080 Ti
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=30, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=15, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 769185
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last (iter 473)'
+0/69092	Loss: 110.581
+3200/69092	Loss: 108.566
+6400/69092	Loss: 106.471
+9600/69092	Loss: 108.384
+12800/69092	Loss: 106.179
+16000/69092	Loss: 108.363
+19200/69092	Loss: 107.383
+22400/69092	Loss: 106.201
+25600/69092	Loss: 107.748
+28800/69092	Loss: 106.345
+32000/69092	Loss: 106.933
+35200/69092	Loss: 104.953
+38400/69092	Loss: 107.716
+41600/69092	Loss: 107.336
+44800/69092	Loss: 108.383
+48000/69092	Loss: 105.740
+51200/69092	Loss: 107.848
+54400/69092	Loss: 106.690
+57600/69092	Loss: 108.056
+60800/69092	Loss: 107.377
+64000/69092	Loss: 106.159
+67200/69092	Loss: 106.285
+Training time 0:11:27.149249
+Epoch: 1 Average loss: 107.14
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 474)
+0/69092	Loss: 99.702
+3200/69092	Loss: 107.183
+6400/69092	Loss: 105.993
+9600/69092	Loss: 108.311
+12800/69092	Loss: 106.867
+16000/69092	Loss: 107.440
+19200/69092	Loss: 107.263
+22400/69092	Loss: 107.394
+25600/69092	Loss: 107.183
+28800/69092	Loss: 107.871
+32000/69092	Loss: 107.158
+35200/69092	Loss: 106.926
+38400/69092	Loss: 107.633
+41600/69092	Loss: 107.240
+44800/69092	Loss: 106.964
+48000/69092	Loss: 107.199
+51200/69092	Loss: 107.033
+54400/69092	Loss: 108.140
+57600/69092	Loss: 108.732
+60800/69092	Loss: 107.360
+64000/69092	Loss: 106.795
+67200/69092	Loss: 105.665
+Training time 0:08:21.160838
+Epoch: 2 Average loss: 107.25
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 475)
+0/69092	Loss: 100.981
+3200/69092	Loss: 107.292
+6400/69092	Loss: 106.760
+9600/69092	Loss: 107.908
+12800/69092	Loss: 108.657
+16000/69092	Loss: 107.260
+19200/69092	Loss: 108.109
+22400/69092	Loss: 106.831
+25600/69092	Loss: 107.451
+28800/69092	Loss: 106.991
+32000/69092	Loss: 105.879
+35200/69092	Loss: 107.224
+38400/69092	Loss: 105.254
+41600/69092	Loss: 106.785
+44800/69092	Loss: 106.556
+48000/69092	Loss: 107.053
+51200/69092	Loss: 105.321
+54400/69092	Loss: 107.260
+57600/69092	Loss: 107.236
+60800/69092	Loss: 107.563
+64000/69092	Loss: 107.818
+67200/69092	Loss: 106.996
+Training time 0:08:24.511412
+Epoch: 3 Average loss: 107.09
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 476)
+0/69092	Loss: 101.654
+3200/69092	Loss: 107.112
+6400/69092	Loss: 107.697
+9600/69092	Loss: 108.108
+12800/69092	Loss: 107.534
+16000/69092	Loss: 107.792
+19200/69092	Loss: 107.133
+22400/69092	Loss: 106.991
+25600/69092	Loss: 106.777
+28800/69092	Loss: 107.075
+32000/69092	Loss: 106.054
+35200/69092	Loss: 106.968
+38400/69092	Loss: 106.188
+41600/69092	Loss: 107.597
+44800/69092	Loss: 107.695
+48000/69092	Loss: 106.289
+51200/69092	Loss: 108.033
+54400/69092	Loss: 105.069
+57600/69092	Loss: 106.915
+60800/69092	Loss: 106.857
+64000/69092	Loss: 106.869
+67200/69092	Loss: 106.638
+Training time 0:08:19.924611
+Epoch: 4 Average loss: 107.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 477)
+0/69092	Loss: 114.821
+3200/69092	Loss: 107.246
+6400/69092	Loss: 107.752
+9600/69092	Loss: 108.112
+12800/69092	Loss: 106.756
+16000/69092	Loss: 107.722
+19200/69092	Loss: 107.283
+22400/69092	Loss: 107.405
+25600/69092	Loss: 106.939
+28800/69092	Loss: 108.485
+32000/69092	Loss: 106.440
+35200/69092	Loss: 107.298
+38400/69092	Loss: 107.824
+41600/69092	Loss: 106.948
+44800/69092	Loss: 105.555
+48000/69092	Loss: 107.234
+51200/69092	Loss: 108.271
+54400/69092	Loss: 106.022
+57600/69092	Loss: 107.570
+60800/69092	Loss: 106.151
+64000/69092	Loss: 107.214
+67200/69092	Loss: 106.246
+Training time 0:08:23.167325
+Epoch: 5 Average loss: 107.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 478)
+0/69092	Loss: 103.693
+3200/69092	Loss: 106.994
+6400/69092	Loss: 105.527
+9600/69092	Loss: 106.331
+12800/69092	Loss: 108.530
+16000/69092	Loss: 107.233
+19200/69092	Loss: 107.429
+22400/69092	Loss: 107.106
+25600/69092	Loss: 105.530
+28800/69092	Loss: 108.257
+32000/69092	Loss: 107.044
+35200/69092	Loss: 108.063
+38400/69092	Loss: 104.476
+41600/69092	Loss: 107.319
+44800/69092	Loss: 107.246
+48000/69092	Loss: 107.314
+51200/69092	Loss: 108.196
+54400/69092	Loss: 106.151
+57600/69092	Loss: 107.594
+60800/69092	Loss: 107.574
+64000/69092	Loss: 107.560
+67200/69092	Loss: 107.120
+Training time 0:08:30.595398
+Epoch: 6 Average loss: 107.08
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 479)
+0/69092	Loss: 103.409
+3200/69092	Loss: 107.584
+6400/69092	Loss: 105.331
+9600/69092	Loss: 105.813
+12800/69092	Loss: 107.597
+16000/69092	Loss: 105.975
+19200/69092	Loss: 107.453
+22400/69092	Loss: 108.537
+25600/69092	Loss: 107.829
+28800/69092	Loss: 107.378
+32000/69092	Loss: 106.630
+35200/69092	Loss: 106.915
+38400/69092	Loss: 107.930
+41600/69092	Loss: 107.281
+44800/69092	Loss: 106.304
+48000/69092	Loss: 106.464
+51200/69092	Loss: 106.313
+54400/69092	Loss: 107.652
+57600/69092	Loss: 108.498
+60800/69092	Loss: 107.306
+64000/69092	Loss: 106.384
+67200/69092	Loss: 106.797
+Training time 0:08:27.744257
+Epoch: 7 Average loss: 107.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 480)
+0/69092	Loss: 108.074
+3200/69092	Loss: 106.775
+6400/69092	Loss: 106.262
+9600/69092	Loss: 106.973
+12800/69092	Loss: 108.121
+16000/69092	Loss: 107.404
+19200/69092	Loss: 107.896
+22400/69092	Loss: 106.314
+25600/69092	Loss: 107.000
+28800/69092	Loss: 105.784
+32000/69092	Loss: 107.484
+35200/69092	Loss: 107.277
+38400/69092	Loss: 108.077
+41600/69092	Loss: 107.103
+44800/69092	Loss: 108.139
+48000/69092	Loss: 106.600
+51200/69092	Loss: 106.753
+54400/69092	Loss: 107.793
+57600/69092	Loss: 107.806
+60800/69092	Loss: 106.514
+64000/69092	Loss: 106.559
+67200/69092	Loss: 105.460
+Training time 0:08:17.349364
+Epoch: 8 Average loss: 107.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 481)
+0/69092	Loss: 102.789
+3200/69092	Loss: 107.755
+6400/69092	Loss: 104.764
+9600/69092	Loss: 107.358
+12800/69092	Loss: 105.349
+16000/69092	Loss: 109.045
+19200/69092	Loss: 105.747
+22400/69092	Loss: 107.275
+25600/69092	Loss: 107.799
+28800/69092	Loss: 107.039
+32000/69092	Loss: 106.828
+35200/69092	Loss: 107.710
+38400/69092	Loss: 105.495
+41600/69092	Loss: 107.351
+44800/69092	Loss: 108.321
+48000/69092	Loss: 107.437
+51200/69092	Loss: 106.254
+54400/69092	Loss: 107.760
+57600/69092	Loss: 107.354
+60800/69092	Loss: 106.981
+64000/69092	Loss: 106.516
+67200/69092	Loss: 107.745
+Training time 0:08:30.688107
+Epoch: 9 Average loss: 107.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 482)
+0/69092	Loss: 105.944
+3200/69092	Loss: 105.756
+6400/69092	Loss: 106.049
+9600/69092	Loss: 108.480
+12800/69092	Loss: 107.277
+16000/69092	Loss: 106.685
+19200/69092	Loss: 106.659
+22400/69092	Loss: 108.246
+25600/69092	Loss: 107.582
+28800/69092	Loss: 106.032
+32000/69092	Loss: 107.498
+35200/69092	Loss: 107.376
+38400/69092	Loss: 106.715
+41600/69092	Loss: 106.488
+44800/69092	Loss: 107.986
+48000/69092	Loss: 106.161
+51200/69092	Loss: 106.795
+54400/69092	Loss: 107.495
+57600/69092	Loss: 106.581
+60800/69092	Loss: 106.513
+64000/69092	Loss: 107.938
+67200/69092	Loss: 106.343
+Training time 0:08:30.902520
+Epoch: 10 Average loss: 107.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 483)
+0/69092	Loss: 107.215
+3200/69092	Loss: 106.000
+6400/69092	Loss: 108.314
+9600/69092	Loss: 105.244
+12800/69092	Loss: 107.664
+16000/69092	Loss: 107.489
+19200/69092	Loss: 106.426
+22400/69092	Loss: 107.607
+25600/69092	Loss: 106.536
+28800/69092	Loss: 107.047
+32000/69092	Loss: 106.565
+35200/69092	Loss: 107.611
+38400/69092	Loss: 107.552
+41600/69092	Loss: 106.444
+44800/69092	Loss: 107.971
+48000/69092	Loss: 107.682
+51200/69092	Loss: 107.682
+54400/69092	Loss: 105.808
+57600/69092	Loss: 107.946
+60800/69092	Loss: 107.230
+64000/69092	Loss: 105.990
+67200/69092	Loss: 107.448
+Training time 0:08:17.127701
+Epoch: 11 Average loss: 107.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 484)
+0/69092	Loss: 108.883
+3200/69092	Loss: 105.996
+6400/69092	Loss: 107.297
+9600/69092	Loss: 106.803
+12800/69092	Loss: 105.791
+16000/69092	Loss: 106.937
+19200/69092	Loss: 106.463
+22400/69092	Loss: 107.672
+25600/69092	Loss: 106.902
+28800/69092	Loss: 107.051
+32000/69092	Loss: 106.500
+35200/69092	Loss: 106.837
+38400/69092	Loss: 107.289
+41600/69092	Loss: 106.878
+44800/69092	Loss: 107.706
+48000/69092	Loss: 107.641
+51200/69092	Loss: 108.040
+54400/69092	Loss: 107.375
+57600/69092	Loss: 108.067
+60800/69092	Loss: 106.578
+64000/69092	Loss: 107.220
+67200/69092	Loss: 106.131
+Training time 0:08:21.377214
+Epoch: 12 Average loss: 107.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 485)
+0/69092	Loss: 98.170
+3200/69092	Loss: 109.277
+6400/69092	Loss: 107.257
+9600/69092	Loss: 104.721
+12800/69092	Loss: 107.396
+16000/69092	Loss: 107.453
+19200/69092	Loss: 107.329
+22400/69092	Loss: 105.373
+25600/69092	Loss: 107.099
+28800/69092	Loss: 105.214
+32000/69092	Loss: 108.016
+35200/69092	Loss: 106.363
+38400/69092	Loss: 107.079
+41600/69092	Loss: 105.177
+44800/69092	Loss: 106.292
+48000/69092	Loss: 108.207
+51200/69092	Loss: 107.205
+54400/69092	Loss: 107.133
+57600/69092	Loss: 106.349
+60800/69092	Loss: 106.411
+64000/69092	Loss: 108.426
+67200/69092	Loss: 108.723
+Training time 0:08:40.537179
+Epoch: 13 Average loss: 106.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 486)
+0/69092	Loss: 131.432
+3200/69092	Loss: 105.775
+6400/69092	Loss: 107.623
+9600/69092	Loss: 106.193
+12800/69092	Loss: 107.760
+16000/69092	Loss: 106.770
+19200/69092	Loss: 106.897
+22400/69092	Loss: 106.845
+25600/69092	Loss: 107.052
+28800/69092	Loss: 106.259
+32000/69092	Loss: 106.689
+35200/69092	Loss: 106.810
+38400/69092	Loss: 106.179
+41600/69092	Loss: 107.628
+44800/69092	Loss: 106.408
+48000/69092	Loss: 108.090
+51200/69092	Loss: 106.630
+54400/69092	Loss: 106.855
+57600/69092	Loss: 107.487
+60800/69092	Loss: 107.528
+64000/69092	Loss: 106.653
+67200/69092	Loss: 107.294
+Training time 0:08:34.089958
+Epoch: 14 Average loss: 106.99
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 487)
+0/69092	Loss: 112.647
+3200/69092	Loss: 105.902
+6400/69092	Loss: 106.145
+9600/69092	Loss: 106.712
+12800/69092	Loss: 106.521
+16000/69092	Loss: 106.187
+19200/69092	Loss: 108.799
+22400/69092	Loss: 107.252
+25600/69092	Loss: 107.509
+28800/69092	Loss: 107.038
+32000/69092	Loss: 104.798
+35200/69092	Loss: 107.998
+38400/69092	Loss: 107.046
+41600/69092	Loss: 107.723
+44800/69092	Loss: 107.305
+48000/69092	Loss: 106.835
+51200/69092	Loss: 107.211
+54400/69092	Loss: 106.013
+57600/69092	Loss: 106.989
+60800/69092	Loss: 106.761
+64000/69092	Loss: 107.381
+67200/69092	Loss: 105.521
+Training time 0:08:18.814183
+Epoch: 15 Average loss: 106.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 488)
+0/69092	Loss: 105.213
+3200/69092	Loss: 106.556
+6400/69092	Loss: 106.534
+9600/69092	Loss: 106.534
+12800/69092	Loss: 107.659
+16000/69092	Loss: 106.278
+19200/69092	Loss: 107.353
+22400/69092	Loss: 106.516
+25600/69092	Loss: 106.815
+28800/69092	Loss: 106.272
+32000/69092	Loss: 106.202
+35200/69092	Loss: 107.211
+38400/69092	Loss: 108.800
+41600/69092	Loss: 107.586
+44800/69092	Loss: 107.131
+48000/69092	Loss: 106.819
+51200/69092	Loss: 106.776
+54400/69092	Loss: 107.619
+57600/69092	Loss: 107.367
+60800/69092	Loss: 107.814
+64000/69092	Loss: 107.028
+67200/69092	Loss: 105.636
+Training time 0:08:30.234504
+Epoch: 16 Average loss: 107.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 489)
+0/69092	Loss: 109.155
+3200/69092	Loss: 106.319
+6400/69092	Loss: 106.810
+9600/69092	Loss: 107.343
+12800/69092	Loss: 107.245
+16000/69092	Loss: 107.087
+19200/69092	Loss: 104.626
+22400/69092	Loss: 108.206
+25600/69092	Loss: 106.612
+28800/69092	Loss: 106.779
+32000/69092	Loss: 107.265
+35200/69092	Loss: 108.162
+38400/69092	Loss: 108.400
+41600/69092	Loss: 106.947
+44800/69092	Loss: 106.623
+48000/69092	Loss: 107.640
+51200/69092	Loss: 107.158
+54400/69092	Loss: 106.243
+57600/69092	Loss: 107.981
+60800/69092	Loss: 107.052
+64000/69092	Loss: 106.735
+67200/69092	Loss: 106.029
+Training time 0:08:36.323006
+Epoch: 17 Average loss: 106.99
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 490)
+0/69092	Loss: 108.026
+3200/69092	Loss: 107.877
+6400/69092	Loss: 107.309
+9600/69092	Loss: 107.339
+12800/69092	Loss: 107.716
+16000/69092	Loss: 107.257
+19200/69092	Loss: 109.342
+22400/69092	Loss: 108.281
+25600/69092	Loss: 106.066
+28800/69092	Loss: 106.281
+32000/69092	Loss: 106.672
+35200/69092	Loss: 107.658
+38400/69092	Loss: 106.854
+41600/69092	Loss: 106.254
+44800/69092	Loss: 107.185
+48000/69092	Loss: 107.933
+51200/69092	Loss: 105.698
+54400/69092	Loss: 106.216
+57600/69092	Loss: 106.335
+60800/69092	Loss: 108.794
+64000/69092	Loss: 106.184
+67200/69092	Loss: 105.062
+Training time 0:08:06.879925
+Epoch: 18 Average loss: 107.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 491)
+0/69092	Loss: 103.597
+3200/69092	Loss: 106.341
+6400/69092	Loss: 108.225
+9600/69092	Loss: 107.684
+12800/69092	Loss: 106.259
+16000/69092	Loss: 106.648
+19200/69092	Loss: 106.431
+22400/69092	Loss: 105.961
+25600/69092	Loss: 106.845
+28800/69092	Loss: 107.147
+32000/69092	Loss: 108.493
+35200/69092	Loss: 106.672
+38400/69092	Loss: 107.321
+41600/69092	Loss: 105.631
+44800/69092	Loss: 106.323
+48000/69092	Loss: 107.250
+51200/69092	Loss: 106.301
+54400/69092	Loss: 107.021
+57600/69092	Loss: 107.016
+60800/69092	Loss: 107.770
+64000/69092	Loss: 106.568
+67200/69092	Loss: 105.828
+Training time 0:08:23.348185
+Epoch: 19 Average loss: 106.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 492)
+0/69092	Loss: 108.248
+3200/69092	Loss: 107.122
+6400/69092	Loss: 108.162
+9600/69092	Loss: 107.138
+12800/69092	Loss: 106.262
+16000/69092	Loss: 106.244
+19200/69092	Loss: 105.231
+22400/69092	Loss: 107.058
+25600/69092	Loss: 106.647
+28800/69092	Loss: 107.388
+32000/69092	Loss: 108.098
+35200/69092	Loss: 106.578
+38400/69092	Loss: 107.507
+41600/69092	Loss: 106.009
+44800/69092	Loss: 105.557
+48000/69092	Loss: 106.489
+51200/69092	Loss: 107.989
+54400/69092	Loss: 107.395
+57600/69092	Loss: 107.140
+60800/69092	Loss: 107.572
+64000/69092	Loss: 105.796
+67200/69092	Loss: 109.904
+Training time 0:08:24.788049
+Epoch: 20 Average loss: 107.09
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 493)
+0/69092	Loss: 100.870
+3200/69092	Loss: 107.126
+6400/69092	Loss: 106.857
+9600/69092	Loss: 108.536
+12800/69092	Loss: 106.562
+16000/69092	Loss: 107.101
+19200/69092	Loss: 106.720
+22400/69092	Loss: 105.400
+25600/69092	Loss: 104.825
+28800/69092	Loss: 105.123
+32000/69092	Loss: 108.347
+35200/69092	Loss: 107.264
+38400/69092	Loss: 108.469
+41600/69092	Loss: 106.208
+44800/69092	Loss: 107.207
+48000/69092	Loss: 106.957
+51200/69092	Loss: 107.260
+54400/69092	Loss: 106.784
+57600/69092	Loss: 106.922
+60800/69092	Loss: 105.668
+64000/69092	Loss: 107.480
+67200/69092	Loss: 107.907
+Training time 0:08:07.942677
+Epoch: 21 Average loss: 106.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 494)
+0/69092	Loss: 108.267
+3200/69092	Loss: 106.839
+6400/69092	Loss: 106.348
+9600/69092	Loss: 107.386
+12800/69092	Loss: 107.184
+16000/69092	Loss: 107.226
+19200/69092	Loss: 105.995
+22400/69092	Loss: 107.061
+25600/69092	Loss: 106.122
+28800/69092	Loss: 107.395
+32000/69092	Loss: 107.483
+35200/69092	Loss: 105.361
+38400/69092	Loss: 107.751
+41600/69092	Loss: 108.151
+44800/69092	Loss: 107.938
+48000/69092	Loss: 107.507
+51200/69092	Loss: 109.059
+54400/69092	Loss: 106.667
+57600/69092	Loss: 105.810
+60800/69092	Loss: 106.929
+64000/69092	Loss: 105.931
+67200/69092	Loss: 106.566
+Training time 0:08:18.878440
+Epoch: 22 Average loss: 106.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 495)
+0/69092	Loss: 105.672
+3200/69092	Loss: 108.753
+6400/69092	Loss: 105.781
+9600/69092	Loss: 106.675
+12800/69092	Loss: 106.896
+16000/69092	Loss: 108.113
+19200/69092	Loss: 105.695
+22400/69092	Loss: 107.899
+25600/69092	Loss: 107.738
+28800/69092	Loss: 106.382
+32000/69092	Loss: 105.981
+35200/69092	Loss: 105.818
+38400/69092	Loss: 107.833
+41600/69092	Loss: 107.663
+44800/69092	Loss: 105.357
+48000/69092	Loss: 107.884
+51200/69092	Loss: 107.039
+54400/69092	Loss: 106.675
+57600/69092	Loss: 105.224
+60800/69092	Loss: 108.835
+64000/69092	Loss: 106.660
+67200/69092	Loss: 108.126
+Training time 0:08:36.022962
+Epoch: 23 Average loss: 107.01
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 496)
+0/69092	Loss: 107.576
+3200/69092	Loss: 106.632
+6400/69092	Loss: 106.224
+9600/69092	Loss: 106.893
+12800/69092	Loss: 105.810
+16000/69092	Loss: 106.152
+19200/69092	Loss: 106.513
+22400/69092	Loss: 108.053
+25600/69092	Loss: 106.056
+28800/69092	Loss: 107.938
+32000/69092	Loss: 106.839
+35200/69092	Loss: 108.765
+38400/69092	Loss: 106.971
+41600/69092	Loss: 108.739
+44800/69092	Loss: 106.710
+48000/69092	Loss: 107.535
+51200/69092	Loss: 107.811
+54400/69092	Loss: 106.460
+57600/69092	Loss: 107.138
+60800/69092	Loss: 108.401
+64000/69092	Loss: 106.212
+67200/69092	Loss: 106.666
+Training time 0:08:17.218747
+Epoch: 24 Average loss: 107.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 497)
+0/69092	Loss: 102.996
+3200/69092	Loss: 106.118
+6400/69092	Loss: 106.992
+9600/69092	Loss: 105.989
+12800/69092	Loss: 105.910
+16000/69092	Loss: 106.373
+19200/69092	Loss: 106.200
+22400/69092	Loss: 107.477
+25600/69092	Loss: 107.872
+28800/69092	Loss: 107.502
+32000/69092	Loss: 107.335
+35200/69092	Loss: 106.230
+38400/69092	Loss: 106.722
+41600/69092	Loss: 105.630
+44800/69092	Loss: 107.345
+48000/69092	Loss: 106.915
+51200/69092	Loss: 106.840
+54400/69092	Loss: 106.987
+57600/69092	Loss: 106.607
+60800/69092	Loss: 106.304
+64000/69092	Loss: 108.054
+67200/69092	Loss: 108.310
+Training time 0:08:24.180124
+Epoch: 25 Average loss: 106.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 498)
+0/69092	Loss: 105.010
+3200/69092	Loss: 108.896
+6400/69092	Loss: 106.295
+9600/69092	Loss: 106.410
+12800/69092	Loss: 107.433
+16000/69092	Loss: 105.642
+19200/69092	Loss: 108.190
+22400/69092	Loss: 107.077
+25600/69092	Loss: 107.923
+28800/69092	Loss: 107.344
+32000/69092	Loss: 106.113
+35200/69092	Loss: 106.689
+38400/69092	Loss: 107.690
+41600/69092	Loss: 108.282
+44800/69092	Loss: 107.482
+48000/69092	Loss: 106.993
+51200/69092	Loss: 106.132
+54400/69092	Loss: 105.725
+57600/69092	Loss: 106.606
+60800/69092	Loss: 106.179
+64000/69092	Loss: 108.073
+67200/69092	Loss: 107.625
+Training time 0:08:43.351278
+Epoch: 26 Average loss: 107.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 499)
+0/69092	Loss: 106.543
+3200/69092	Loss: 107.193
+6400/69092	Loss: 106.418
+9600/69092	Loss: 107.404
+12800/69092	Loss: 107.335
+16000/69092	Loss: 106.308
+19200/69092	Loss: 106.810
+22400/69092	Loss: 104.263
+25600/69092	Loss: 107.484
+28800/69092	Loss: 107.588
+32000/69092	Loss: 108.462
+35200/69092	Loss: 107.494
+38400/69092	Loss: 106.157
+41600/69092	Loss: 106.973
+44800/69092	Loss: 105.203
+48000/69092	Loss: 105.543
+51200/69092	Loss: 106.507
+54400/69092	Loss: 107.511
+57600/69092	Loss: 106.889
+60800/69092	Loss: 108.089
+64000/69092	Loss: 106.536
+67200/69092	Loss: 106.497
+Training time 0:08:22.273776
+Epoch: 27 Average loss: 106.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 500)
+0/69092	Loss: 97.420
+3200/69092	Loss: 107.024
+6400/69092	Loss: 106.458
+9600/69092	Loss: 107.287
+12800/69092	Loss: 106.788
+16000/69092	Loss: 107.978
+19200/69092	Loss: 107.754
+22400/69092	Loss: 107.332
+25600/69092	Loss: 106.206
+28800/69092	Loss: 105.199
+32000/69092	Loss: 106.908
+35200/69092	Loss: 106.104
+38400/69092	Loss: 106.949
+41600/69092	Loss: 106.501
+44800/69092	Loss: 105.393
+48000/69092	Loss: 108.152
+51200/69092	Loss: 106.595
+54400/69092	Loss: 107.061
+57600/69092	Loss: 108.498
+60800/69092	Loss: 106.840
+64000/69092	Loss: 106.131
+67200/69092	Loss: 106.161
+Training time 0:08:14.546658
+Epoch: 28 Average loss: 106.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 501)
+0/69092	Loss: 108.669
+3200/69092	Loss: 106.569
+6400/69092	Loss: 106.626
+9600/69092	Loss: 107.054
+12800/69092	Loss: 107.283
+16000/69092	Loss: 107.007
+19200/69092	Loss: 106.005
+22400/69092	Loss: 107.045
+25600/69092	Loss: 107.353
+28800/69092	Loss: 106.559
+32000/69092	Loss: 105.510
+35200/69092	Loss: 108.191
+38400/69092	Loss: 106.361
+41600/69092	Loss: 106.957
+44800/69092	Loss: 106.322
+48000/69092	Loss: 107.274
+51200/69092	Loss: 107.770
+54400/69092	Loss: 105.803
+57600/69092	Loss: 106.405
+60800/69092	Loss: 105.515
+64000/69092	Loss: 108.015
+67200/69092	Loss: 108.649
+Training time 0:08:27.655091
+Epoch: 29 Average loss: 106.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 502)
+0/69092	Loss: 106.857
+3200/69092	Loss: 106.873
+6400/69092	Loss: 106.267
+9600/69092	Loss: 105.969
+12800/69092	Loss: 107.742
+16000/69092	Loss: 106.952
+19200/69092	Loss: 106.847
+22400/69092	Loss: 107.004
+25600/69092	Loss: 107.268
+28800/69092	Loss: 106.542
+32000/69092	Loss: 106.626
+35200/69092	Loss: 107.428
+38400/69092	Loss: 106.724
+41600/69092	Loss: 104.702
+44800/69092	Loss: 106.833
+48000/69092	Loss: 107.734
+51200/69092	Loss: 106.590
+54400/69092	Loss: 106.606
+57600/69092	Loss: 107.504
+60800/69092	Loss: 107.595
+64000/69092	Loss: 108.234
+67200/69092	Loss: 106.115
+Training time 0:08:29.535035
+Epoch: 30 Average loss: 106.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 503)
+0/69092	Loss: 107.827
+3200/69092	Loss: 106.073
+6400/69092	Loss: 106.897
+9600/69092	Loss: 106.870
+12800/69092	Loss: 106.946
+16000/69092	Loss: 106.631
+19200/69092	Loss: 107.671
+22400/69092	Loss: 107.664
+25600/69092	Loss: 105.752
+28800/69092	Loss: 105.688
+32000/69092	Loss: 107.678
+35200/69092	Loss: 106.947
+38400/69092	Loss: 105.980
+41600/69092	Loss: 107.643
+44800/69092	Loss: 106.687
+48000/69092	Loss: 107.158
+51200/69092	Loss: 107.248
+54400/69092	Loss: 106.510
+57600/69092	Loss: 105.684
+60800/69092	Loss: 106.212
+64000/69092	Loss: 106.979
+67200/69092	Loss: 107.192
+Training time 0:08:05.845919
+Epoch: 31 Average loss: 106.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 504)
+0/69092	Loss: 108.461
+3200/69092	Loss: 108.145
+6400/69092	Loss: 106.632
+9600/69092	Loss: 105.608
+12800/69092	Loss: 107.973
+16000/69092	Loss: 107.031
+19200/69092	Loss: 108.228
+22400/69092	Loss: 106.640
+25600/69092	Loss: 105.945
+28800/69092	Loss: 105.854
+32000/69092	Loss: 107.204
+35200/69092	Loss: 106.140
+38400/69092	Loss: 104.946
+41600/69092	Loss: 107.611
+44800/69092	Loss: 107.065
+48000/69092	Loss: 106.297
+51200/69092	Loss: 105.887
+54400/69092	Loss: 105.536
+57600/69092	Loss: 106.101
+60800/69092	Loss: 107.308
+64000/69092	Loss: 108.106
+67200/69092	Loss: 107.629
+Training time 0:08:23.864787
+Epoch: 32 Average loss: 106.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 505)
+0/69092	Loss: 101.212
+3200/69092	Loss: 107.772
+6400/69092	Loss: 105.749
+9600/69092	Loss: 106.881
+12800/69092	Loss: 108.960
+16000/69092	Loss: 106.376
+19200/69092	Loss: 107.399
+22400/69092	Loss: 106.471
+25600/69092	Loss: 105.895
+28800/69092	Loss: 107.655
+32000/69092	Loss: 106.518
+35200/69092	Loss: 106.101
+38400/69092	Loss: 107.582
+41600/69092	Loss: 107.576
+44800/69092	Loss: 105.842
+48000/69092	Loss: 106.587
+51200/69092	Loss: 106.687
+54400/69092	Loss: 108.002
+57600/69092	Loss: 106.438
+60800/69092	Loss: 107.092
+64000/69092	Loss: 107.006
+67200/69092	Loss: 106.410
+Training time 0:08:33.277565
+Epoch: 33 Average loss: 106.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 506)
+0/69092	Loss: 109.246
+3200/69092	Loss: 106.619
+6400/69092	Loss: 106.207
+9600/69092	Loss: 107.888
+12800/69092	Loss: 107.262
+16000/69092	Loss: 106.334
+19200/69092	Loss: 107.032
+22400/69092	Loss: 107.633
+25600/69092	Loss: 109.776
+28800/69092	Loss: 106.656
+32000/69092	Loss: 106.536
+35200/69092	Loss: 108.375
+38400/69092	Loss: 105.658
+41600/69092	Loss: 107.611
+44800/69092	Loss: 104.977
+48000/69092	Loss: 106.749
+51200/69092	Loss: 108.565
+54400/69092	Loss: 107.083
+57600/69092	Loss: 105.167
+60800/69092	Loss: 107.340
+64000/69092	Loss: 105.946
+67200/69092	Loss: 107.182
+Training time 0:08:21.139834
+Epoch: 34 Average loss: 106.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 507)
+0/69092	Loss: 110.170
+3200/69092	Loss: 108.322
+6400/69092	Loss: 106.893
+9600/69092	Loss: 106.532
+12800/69092	Loss: 107.037
+16000/69092	Loss: 106.681
+19200/69092	Loss: 106.283
+22400/69092	Loss: 105.767
+25600/69092	Loss: 106.004
+28800/69092	Loss: 107.043
+32000/69092	Loss: 107.321
+35200/69092	Loss: 105.726
+38400/69092	Loss: 104.772
+41600/69092	Loss: 105.755
+44800/69092	Loss: 106.256
+48000/69092	Loss: 108.280
+51200/69092	Loss: 107.653
+54400/69092	Loss: 107.005
+57600/69092	Loss: 106.009
+60800/69092	Loss: 106.482
+64000/69092	Loss: 107.809
+67200/69092	Loss: 105.659
+Training time 0:08:17.733348
+Epoch: 35 Average loss: 106.72
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 508)
+0/69092	Loss: 110.557
+3200/69092	Loss: 106.410
+6400/69092	Loss: 106.518
+9600/69092	Loss: 107.600
+12800/69092	Loss: 109.078
+16000/69092	Loss: 106.978
+19200/69092	Loss: 105.890
+22400/69092	Loss: 107.280
+25600/69092	Loss: 106.900
+28800/69092	Loss: 106.252
+32000/69092	Loss: 105.889
+35200/69092	Loss: 106.463
+38400/69092	Loss: 106.380
+41600/69092	Loss: 106.067
+44800/69092	Loss: 107.137
+48000/69092	Loss: 106.704
+51200/69092	Loss: 107.798
+54400/69092	Loss: 107.473
+57600/69092	Loss: 108.272
+60800/69092	Loss: 106.100
+64000/69092	Loss: 106.764
+67200/69092	Loss: 107.516
+Training time 0:08:37.361854
+Epoch: 36 Average loss: 106.88
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 509)
+0/69092	Loss: 107.444
+3200/69092	Loss: 106.662
+6400/69092	Loss: 107.098
+9600/69092	Loss: 107.999
+12800/69092	Loss: 107.046
+16000/69092	Loss: 108.800
+19200/69092	Loss: 105.016
+22400/69092	Loss: 107.985
+25600/69092	Loss: 105.942
+28800/69092	Loss: 105.818
+32000/69092	Loss: 107.889
+35200/69092	Loss: 106.710
+38400/69092	Loss: 107.147
+41600/69092	Loss: 106.291
+44800/69092	Loss: 106.536
+48000/69092	Loss: 106.982
+51200/69092	Loss: 106.912
+54400/69092	Loss: 107.344
+57600/69092	Loss: 105.220
+60800/69092	Loss: 106.958
+64000/69092	Loss: 106.911
+67200/69092	Loss: 106.952
+Training time 0:08:23.202986
+Epoch: 37 Average loss: 106.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 510)
+0/69092	Loss: 100.629
+3200/69092	Loss: 107.848
+6400/69092	Loss: 108.056
+9600/69092	Loss: 106.803
+12800/69092	Loss: 106.100
+16000/69092	Loss: 105.998
+19200/69092	Loss: 106.265
+22400/69092	Loss: 107.394
+25600/69092	Loss: 106.804
+28800/69092	Loss: 108.393
+32000/69092	Loss: 107.156
+35200/69092	Loss: 106.850
+38400/69092	Loss: 106.741
+41600/69092	Loss: 104.793
+44800/69092	Loss: 107.003
+48000/69092	Loss: 108.023
+51200/69092	Loss: 106.073
+54400/69092	Loss: 104.939
+57600/69092	Loss: 107.922
+60800/69092	Loss: 106.742
+64000/69092	Loss: 106.262
+67200/69092	Loss: 106.401
+Training time 0:08:06.821813
+Epoch: 38 Average loss: 106.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 511)
+0/69092	Loss: 109.724
+3200/69092	Loss: 106.508
+6400/69092	Loss: 107.910
+9600/69092	Loss: 106.535
+12800/69092	Loss: 107.349
+16000/69092	Loss: 106.108
+19200/69092	Loss: 106.120
+22400/69092	Loss: 106.935
+25600/69092	Loss: 105.665
+28800/69092	Loss: 108.991
+32000/69092	Loss: 106.678
+35200/69092	Loss: 105.922
+38400/69092	Loss: 104.620
+41600/69092	Loss: 106.537
+44800/69092	Loss: 106.395
+48000/69092	Loss: 106.549
+51200/69092	Loss: 106.264
+54400/69092	Loss: 106.134
+57600/69092	Loss: 108.281
+60800/69092	Loss: 107.664
+64000/69092	Loss: 107.395
+67200/69092	Loss: 107.978
+Training time 0:08:30.801808
+Epoch: 39 Average loss: 106.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 512)
+0/69092	Loss: 109.247
+3200/69092	Loss: 108.578
+6400/69092	Loss: 106.147
+9600/69092	Loss: 108.482
+12800/69092	Loss: 106.185
+16000/69092	Loss: 105.012
+19200/69092	Loss: 106.996
+22400/69092	Loss: 105.604
+25600/69092	Loss: 105.303
+28800/69092	Loss: 106.530
+32000/69092	Loss: 108.041
+35200/69092	Loss: 106.429
+38400/69092	Loss: 105.155
+41600/69092	Loss: 107.396
+44800/69092	Loss: 107.649
+48000/69092	Loss: 106.824
+51200/69092	Loss: 106.821
+54400/69092	Loss: 106.505
+57600/69092	Loss: 106.454
+60800/69092	Loss: 105.907
+64000/69092	Loss: 107.592
+67200/69092	Loss: 107.295
+Training time 0:08:35.982697
+Epoch: 40 Average loss: 106.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 513)
+0/69092	Loss: 114.350
+3200/69092	Loss: 106.682
+6400/69092	Loss: 106.009
+9600/69092	Loss: 106.302
+12800/69092	Loss: 108.305
+16000/69092	Loss: 105.490
+19200/69092	Loss: 105.432
+22400/69092	Loss: 106.721
+25600/69092	Loss: 106.706
+28800/69092	Loss: 107.209
+32000/69092	Loss: 109.893
+35200/69092	Loss: 109.479
+38400/69092	Loss: 106.742
+41600/69092	Loss: 107.065
+44800/69092	Loss: 108.064
+48000/69092	Loss: 105.576
+51200/69092	Loss: 105.902
+54400/69092	Loss: 107.118
+57600/69092	Loss: 106.050
+60800/69092	Loss: 106.753
+64000/69092	Loss: 106.105
+67200/69092	Loss: 105.076
+Training time 0:08:07.857647
+Epoch: 41 Average loss: 106.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 514)
+0/69092	Loss: 102.038
+3200/69092	Loss: 109.922
+6400/69092	Loss: 105.815
+9600/69092	Loss: 106.493
+12800/69092	Loss: 107.484
+16000/69092	Loss: 106.596
+19200/69092	Loss: 106.378
+22400/69092	Loss: 107.316
+25600/69092	Loss: 107.115
+28800/69092	Loss: 106.703
+32000/69092	Loss: 106.695
+35200/69092	Loss: 107.728
+38400/69092	Loss: 107.789
+41600/69092	Loss: 106.428
+44800/69092	Loss: 105.520
+48000/69092	Loss: 107.843
+51200/69092	Loss: 107.281
+54400/69092	Loss: 106.313
+57600/69092	Loss: 105.557
+60800/69092	Loss: 105.716
+64000/69092	Loss: 106.714
+67200/69092	Loss: 107.592
+Training time 0:08:25.967587
+Epoch: 42 Average loss: 106.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 515)
+0/69092	Loss: 101.390
+3200/69092	Loss: 107.405
+6400/69092	Loss: 107.609
+9600/69092	Loss: 107.797
+12800/69092	Loss: 106.650
+16000/69092	Loss: 105.702
+19200/69092	Loss: 105.273
+22400/69092	Loss: 105.955
+25600/69092	Loss: 106.845
+28800/69092	Loss: 105.636
+32000/69092	Loss: 105.610
+35200/69092	Loss: 108.198
+38400/69092	Loss: 105.806
+41600/69092	Loss: 105.594
+44800/69092	Loss: 106.841
+48000/69092	Loss: 106.960
+51200/69092	Loss: 108.810
+54400/69092	Loss: 106.051
+57600/69092	Loss: 107.328
+60800/69092	Loss: 106.294
+64000/69092	Loss: 107.300
+67200/69092	Loss: 106.395
+Training time 0:08:31.408546
+Epoch: 43 Average loss: 106.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 516)
+0/69092	Loss: 102.848
+3200/69092	Loss: 106.033
+6400/69092	Loss: 106.320
+9600/69092	Loss: 106.961
+12800/69092	Loss: 106.706
+16000/69092	Loss: 105.678
+19200/69092	Loss: 106.095
+22400/69092	Loss: 107.887
+25600/69092	Loss: 107.070
+28800/69092	Loss: 107.213
+32000/69092	Loss: 108.178
+35200/69092	Loss: 107.664
+38400/69092	Loss: 107.535
+41600/69092	Loss: 106.038
+44800/69092	Loss: 108.408
+48000/69092	Loss: 104.797
+51200/69092	Loss: 108.708
+54400/69092	Loss: 106.583
+57600/69092	Loss: 107.269
+60800/69092	Loss: 106.591
+64000/69092	Loss: 105.971
+67200/69092	Loss: 105.606
+Training time 0:08:13.582210
+Epoch: 44 Average loss: 106.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 517)
+0/69092	Loss: 105.827
+3200/69092	Loss: 106.205
+6400/69092	Loss: 107.455
+9600/69092	Loss: 107.544
+12800/69092	Loss: 108.701
+16000/69092	Loss: 107.936
+19200/69092	Loss: 107.604
+22400/69092	Loss: 107.274
+25600/69092	Loss: 105.197
+28800/69092	Loss: 106.126
+32000/69092	Loss: 107.541
+35200/69092	Loss: 105.957
+38400/69092	Loss: 108.218
+41600/69092	Loss: 106.857
+44800/69092	Loss: 107.006
+48000/69092	Loss: 107.561
+51200/69092	Loss: 105.684
+54400/69092	Loss: 107.322
+57600/69092	Loss: 107.773
+60800/69092	Loss: 105.880
+64000/69092	Loss: 106.092
+67200/69092	Loss: 105.626
+Training time 0:08:18.106203
+Epoch: 45 Average loss: 106.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 518)
+0/69092	Loss: 109.860
+3200/69092	Loss: 105.764
+6400/69092	Loss: 105.985
+9600/69092	Loss: 106.342
+12800/69092	Loss: 107.274
+16000/69092	Loss: 105.462
+19200/69092	Loss: 106.628
+22400/69092	Loss: 105.899
+25600/69092	Loss: 107.117
+28800/69092	Loss: 106.538
+32000/69092	Loss: 107.762
+35200/69092	Loss: 107.619
+38400/69092	Loss: 107.434
+41600/69092	Loss: 104.578
+44800/69092	Loss: 109.876
+48000/69092	Loss: 108.222
+51200/69092	Loss: 106.361
+54400/69092	Loss: 106.332
+57600/69092	Loss: 106.598
+60800/69092	Loss: 106.290
+64000/69092	Loss: 107.496
+67200/69092	Loss: 107.478
+Training time 0:08:39.952923
+Epoch: 46 Average loss: 106.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 519)
+0/69092	Loss: 105.803
+3200/69092	Loss: 105.469
+6400/69092	Loss: 105.932
+9600/69092	Loss: 105.877
+12800/69092	Loss: 107.837
+16000/69092	Loss: 107.789
+19200/69092	Loss: 106.782
+22400/69092	Loss: 106.652
+25600/69092	Loss: 106.474
+28800/69092	Loss: 105.564
+32000/69092	Loss: 106.586
+35200/69092	Loss: 108.011
+38400/69092	Loss: 107.188
+41600/69092	Loss: 107.798
+44800/69092	Loss: 108.757
+48000/69092	Loss: 104.974
+51200/69092	Loss: 106.995
+54400/69092	Loss: 108.837
+57600/69092	Loss: 107.007
+60800/69092	Loss: 106.155
+64000/69092	Loss: 105.993
+67200/69092	Loss: 107.549
+Training time 0:08:21.676459
+Epoch: 47 Average loss: 106.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 520)
+0/69092	Loss: 108.203
+3200/69092	Loss: 106.524
+6400/69092	Loss: 105.515
+9600/69092	Loss: 106.197
+12800/69092	Loss: 107.347
+16000/69092	Loss: 106.653
+19200/69092	Loss: 106.651
+22400/69092	Loss: 107.174
+25600/69092	Loss: 106.456
+28800/69092	Loss: 107.546
+32000/69092	Loss: 107.244
+35200/69092	Loss: 106.776
+38400/69092	Loss: 107.812
+41600/69092	Loss: 106.700
+44800/69092	Loss: 107.211
+48000/69092	Loss: 108.394
+51200/69092	Loss: 106.195
+54400/69092	Loss: 105.493
+57600/69092	Loss: 107.863
+60800/69092	Loss: 107.016
+64000/69092	Loss: 106.536
+67200/69092	Loss: 106.268
+Training time 0:08:17.604271
+Epoch: 48 Average loss: 106.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 521)
+0/69092	Loss: 102.978
+3200/69092	Loss: 106.468
+6400/69092	Loss: 103.890
+9600/69092	Loss: 107.473
+12800/69092	Loss: 106.071
+16000/69092	Loss: 106.918
+19200/69092	Loss: 105.772
+22400/69092	Loss: 106.806
+25600/69092	Loss: 105.864
+28800/69092	Loss: 107.401
+32000/69092	Loss: 106.899
+35200/69092	Loss: 107.052
+38400/69092	Loss: 107.087
+41600/69092	Loss: 107.963
+44800/69092	Loss: 106.511
+48000/69092	Loss: 106.965
+51200/69092	Loss: 107.969
+54400/69092	Loss: 106.642
+57600/69092	Loss: 107.029
+60800/69092	Loss: 106.361
+64000/69092	Loss: 106.886
+67200/69092	Loss: 108.013
+Training time 0:08:30.393458
+Epoch: 49 Average loss: 106.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 522)
+0/69092	Loss: 95.741
+3200/69092	Loss: 106.334
+6400/69092	Loss: 108.141
+9600/69092	Loss: 106.306
+12800/69092	Loss: 108.745
+16000/69092	Loss: 108.070
+19200/69092	Loss: 107.803
+22400/69092	Loss: 105.934
+25600/69092	Loss: 107.191
+28800/69092	Loss: 105.372
+32000/69092	Loss: 107.674
+35200/69092	Loss: 107.673
+38400/69092	Loss: 105.772
+41600/69092	Loss: 106.580
+44800/69092	Loss: 105.924
+48000/69092	Loss: 106.089
+51200/69092	Loss: 107.257
+54400/69092	Loss: 106.356
+57600/69092	Loss: 106.322
+60800/69092	Loss: 106.747
+64000/69092	Loss: 106.514
+67200/69092	Loss: 104.662
+Training time 0:08:29.382164
+Epoch: 50 Average loss: 106.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 523)
+0/69092	Loss: 101.972
+3200/69092	Loss: 106.313
+6400/69092	Loss: 106.647
+9600/69092	Loss: 106.959
+12800/69092	Loss: 106.342
+16000/69092	Loss: 107.635
+19200/69092	Loss: 106.454
+22400/69092	Loss: 107.158
+25600/69092	Loss: 107.453
+28800/69092	Loss: 107.335
+32000/69092	Loss: 107.739
+35200/69092	Loss: 107.990
+38400/69092	Loss: 106.934
+41600/69092	Loss: 105.147
+44800/69092	Loss: 107.051
+48000/69092	Loss: 104.712
+51200/69092	Loss: 107.068
+54400/69092	Loss: 105.616
+57600/69092	Loss: 108.176
+60800/69092	Loss: 107.511
+64000/69092	Loss: 107.636
+67200/69092	Loss: 104.888
+Training time 0:08:20.121373
+Epoch: 51 Average loss: 106.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 524)
+0/69092	Loss: 93.587
+3200/69092	Loss: 107.374
+6400/69092	Loss: 106.663
+9600/69092	Loss: 106.714
+12800/69092	Loss: 107.444
+16000/69092	Loss: 105.215
+19200/69092	Loss: 107.283
+22400/69092	Loss: 107.709
+25600/69092	Loss: 106.121
+28800/69092	Loss: 105.951
+32000/69092	Loss: 109.354
+35200/69092	Loss: 107.679
+38400/69092	Loss: 105.551
+41600/69092	Loss: 107.467
+44800/69092	Loss: 107.667
+48000/69092	Loss: 105.611
+51200/69092	Loss: 106.438
+54400/69092	Loss: 105.717
+57600/69092	Loss: 106.327
+60800/69092	Loss: 105.746
+64000/69092	Loss: 107.642
+67200/69092	Loss: 105.958
+Training time 0:08:30.745085
+Epoch: 52 Average loss: 106.71
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 525)
+0/69092	Loss: 112.160
+3200/69092	Loss: 106.440
+6400/69092	Loss: 107.581
+9600/69092	Loss: 105.631
+12800/69092	Loss: 106.926
+16000/69092	Loss: 106.457
+19200/69092	Loss: 106.489
+22400/69092	Loss: 105.510
+25600/69092	Loss: 108.836
+28800/69092	Loss: 107.760
+32000/69092	Loss: 105.559
+35200/69092	Loss: 105.682
+38400/69092	Loss: 107.110
+41600/69092	Loss: 106.419
+44800/69092	Loss: 105.980
+48000/69092	Loss: 106.853
+51200/69092	Loss: 106.923
+54400/69092	Loss: 107.570
+57600/69092	Loss: 105.892
+60800/69092	Loss: 105.469
+64000/69092	Loss: 105.728
+67200/69092	Loss: 106.600
+Training time 0:08:45.418786
+Epoch: 53 Average loss: 106.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 526)
+0/69092	Loss: 102.195
+3200/69092	Loss: 107.118
+6400/69092	Loss: 106.974
+9600/69092	Loss: 105.472
+12800/69092	Loss: 106.946
+16000/69092	Loss: 107.167
+19200/69092	Loss: 105.577
+22400/69092	Loss: 107.048
+25600/69092	Loss: 107.961
+28800/69092	Loss: 107.448
+32000/69092	Loss: 106.838
+35200/69092	Loss: 106.739
+38400/69092	Loss: 107.685
+41600/69092	Loss: 106.328
+44800/69092	Loss: 105.111
+48000/69092	Loss: 105.203
+51200/69092	Loss: 106.698
+54400/69092	Loss: 107.482
+57600/69092	Loss: 106.516
+60800/69092	Loss: 106.298
+64000/69092	Loss: 106.267
+67200/69092	Loss: 109.480
+Training time 0:08:22.556495
+Epoch: 54 Average loss: 106.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 527)
+0/69092	Loss: 108.209
+3200/69092	Loss: 107.823
+6400/69092	Loss: 106.985
+9600/69092	Loss: 107.505
+12800/69092	Loss: 107.094
+16000/69092	Loss: 106.705
+19200/69092	Loss: 106.293
+22400/69092	Loss: 107.451
+25600/69092	Loss: 106.788
+28800/69092	Loss: 105.683
+32000/69092	Loss: 107.584
+35200/69092	Loss: 106.157
+38400/69092	Loss: 106.938
+41600/69092	Loss: 106.661
+44800/69092	Loss: 107.833
+48000/69092	Loss: 105.252
+51200/69092	Loss: 106.931
+54400/69092	Loss: 106.828
+57600/69092	Loss: 106.179
+60800/69092	Loss: 106.439
+64000/69092	Loss: 106.747
+67200/69092	Loss: 106.926
+Training time 0:08:10.221260
+Epoch: 55 Average loss: 106.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 528)
+0/69092	Loss: 109.420
+3200/69092	Loss: 108.991
+6400/69092	Loss: 107.875
+9600/69092	Loss: 107.293
+12800/69092	Loss: 107.075
+16000/69092	Loss: 106.492
+19200/69092	Loss: 106.480
+22400/69092	Loss: 106.645
+25600/69092	Loss: 107.123
+28800/69092	Loss: 106.739
+32000/69092	Loss: 105.794
+35200/69092	Loss: 107.405
+38400/69092	Loss: 105.508
+41600/69092	Loss: 107.081
+44800/69092	Loss: 106.113
+48000/69092	Loss: 107.965
+51200/69092	Loss: 105.703
+54400/69092	Loss: 106.718
+57600/69092	Loss: 106.942
+60800/69092	Loss: 107.319
+64000/69092	Loss: 108.163
+67200/69092	Loss: 105.169
+Training time 0:08:36.355698
+Epoch: 56 Average loss: 106.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 529)
+0/69092	Loss: 100.465
+3200/69092	Loss: 107.272
+6400/69092	Loss: 108.924
+9600/69092	Loss: 107.829
+12800/69092	Loss: 106.168
+16000/69092	Loss: 106.408
+19200/69092	Loss: 108.190
+22400/69092	Loss: 107.250
+25600/69092	Loss: 107.463
+28800/69092	Loss: 107.658
+32000/69092	Loss: 104.361
+35200/69092	Loss: 106.182
+38400/69092	Loss: 104.780
+41600/69092	Loss: 107.314
+44800/69092	Loss: 107.224
+48000/69092	Loss: 105.673
+51200/69092	Loss: 106.430
+54400/69092	Loss: 106.830
+57600/69092	Loss: 106.561
+60800/69092	Loss: 106.044
+64000/69092	Loss: 106.222
+67200/69092	Loss: 105.596
+Training time 0:08:21.643994
+Epoch: 57 Average loss: 106.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 530)
+0/69092	Loss: 98.758
+3200/69092	Loss: 106.472
+6400/69092	Loss: 107.820
+9600/69092	Loss: 107.238
+12800/69092	Loss: 106.649
+16000/69092	Loss: 106.293
+19200/69092	Loss: 107.955
+22400/69092	Loss: 107.307
+25600/69092	Loss: 105.488
+28800/69092	Loss: 107.026
+32000/69092	Loss: 106.625
+35200/69092	Loss: 109.939
+38400/69092	Loss: 106.629
+41600/69092	Loss: 105.961
+44800/69092	Loss: 105.147
+48000/69092	Loss: 106.347
+51200/69092	Loss: 106.109
+54400/69092	Loss: 106.690
+57600/69092	Loss: 106.794
+60800/69092	Loss: 105.890
+64000/69092	Loss: 106.664
+67200/69092	Loss: 107.543
+Training time 0:08:09.871251
+Epoch: 58 Average loss: 106.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 531)
+0/69092	Loss: 108.428
+3200/69092	Loss: 105.886
+6400/69092	Loss: 106.944
+9600/69092	Loss: 106.287
+12800/69092	Loss: 106.540
+16000/69092	Loss: 105.932
+19200/69092	Loss: 105.131
+22400/69092	Loss: 107.265
+25600/69092	Loss: 106.732
+28800/69092	Loss: 106.844
+32000/69092	Loss: 107.476
+35200/69092	Loss: 106.372
+38400/69092	Loss: 107.511
+41600/69092	Loss: 105.322
+44800/69092	Loss: 107.139
+48000/69092	Loss: 105.875
+51200/69092	Loss: 108.235
+54400/69092	Loss: 107.404
+57600/69092	Loss: 106.026
+60800/69092	Loss: 108.478
+64000/69092	Loss: 108.211
+67200/69092	Loss: 106.507
+Training time 0:08:31.787390
+Epoch: 59 Average loss: 106.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 532)
+0/69092	Loss: 108.698
+3200/69092	Loss: 107.275
+6400/69092	Loss: 107.531
+9600/69092	Loss: 106.384
+12800/69092	Loss: 107.447
+16000/69092	Loss: 106.106
+19200/69092	Loss: 106.766
+22400/69092	Loss: 107.103
+25600/69092	Loss: 107.157
+28800/69092	Loss: 106.150
+32000/69092	Loss: 106.438
+35200/69092	Loss: 106.090
+38400/69092	Loss: 107.609
+41600/69092	Loss: 107.172
+44800/69092	Loss: 107.083
+48000/69092	Loss: 106.671
+51200/69092	Loss: 106.723
+54400/69092	Loss: 106.216
+57600/69092	Loss: 105.887
+60800/69092	Loss: 106.272
+64000/69092	Loss: 107.759
+67200/69092	Loss: 107.448
+Training time 0:08:37.463056
+Epoch: 60 Average loss: 106.83
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 533)
+0/69092	Loss: 104.250
+3200/69092	Loss: 105.862
+6400/69092	Loss: 105.964
+9600/69092	Loss: 106.609
+12800/69092	Loss: 106.665
+16000/69092	Loss: 106.525
+19200/69092	Loss: 107.308
+22400/69092	Loss: 105.962
+25600/69092	Loss: 105.774
+28800/69092	Loss: 105.981
+32000/69092	Loss: 108.180
+35200/69092	Loss: 107.349
+38400/69092	Loss: 104.827
+41600/69092	Loss: 106.227
+44800/69092	Loss: 109.025
+48000/69092	Loss: 106.376
+51200/69092	Loss: 107.433
+54400/69092	Loss: 108.442
+57600/69092	Loss: 104.143
+60800/69092	Loss: 106.602
+64000/69092	Loss: 107.485
+67200/69092	Loss: 105.913
+Training time 0:08:27.137078
+Epoch: 61 Average loss: 106.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 534)
+0/69092	Loss: 119.722
+3200/69092	Loss: 107.069
+6400/69092	Loss: 106.705
+9600/69092	Loss: 105.566
+12800/69092	Loss: 105.498
+16000/69092	Loss: 106.748
+19200/69092	Loss: 106.485
+22400/69092	Loss: 107.436
+25600/69092	Loss: 107.625
+28800/69092	Loss: 107.373
+32000/69092	Loss: 107.248
+35200/69092	Loss: 106.855
+38400/69092	Loss: 106.684
+41600/69092	Loss: 105.001
+44800/69092	Loss: 107.639
+48000/69092	Loss: 107.366
+51200/69092	Loss: 106.844
+54400/69092	Loss: 106.253
+57600/69092	Loss: 107.009
+60800/69092	Loss: 106.688
+64000/69092	Loss: 107.537
+67200/69092	Loss: 107.166
+Training time 0:08:22.210383
+Epoch: 62 Average loss: 106.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 535)
+0/69092	Loss: 107.845
+3200/69092	Loss: 106.216
+6400/69092	Loss: 106.168
+9600/69092	Loss: 107.975
+12800/69092	Loss: 107.211
+16000/69092	Loss: 105.226
+19200/69092	Loss: 105.755
+22400/69092	Loss: 107.111
+25600/69092	Loss: 106.224
+28800/69092	Loss: 107.624
+32000/69092	Loss: 106.296
+35200/69092	Loss: 106.039
+38400/69092	Loss: 106.196
+41600/69092	Loss: 106.224
+44800/69092	Loss: 106.773
+48000/69092	Loss: 107.783
+51200/69092	Loss: 106.054
+54400/69092	Loss: 107.029
+57600/69092	Loss: 108.663
+60800/69092	Loss: 105.947
+64000/69092	Loss: 106.820
+67200/69092	Loss: 107.061
+Training time 0:08:37.904903
+Epoch: 63 Average loss: 106.70
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 536)
+0/69092	Loss: 111.054
+3200/69092	Loss: 106.672
+6400/69092	Loss: 106.212
+9600/69092	Loss: 108.126
+12800/69092	Loss: 107.029
+16000/69092	Loss: 107.758
+19200/69092	Loss: 106.359
+22400/69092	Loss: 106.246
+25600/69092	Loss: 106.931
+28800/69092	Loss: 106.470
+32000/69092	Loss: 107.582
+35200/69092	Loss: 109.367
+38400/69092	Loss: 105.843
+41600/69092	Loss: 106.772
+44800/69092	Loss: 105.913
+48000/69092	Loss: 107.322
+51200/69092	Loss: 106.561
+54400/69092	Loss: 106.277
+57600/69092	Loss: 106.100
+60800/69092	Loss: 105.362
+64000/69092	Loss: 105.952
+67200/69092	Loss: 107.689
+Training time 0:08:24.476130
+Epoch: 64 Average loss: 106.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 537)
+0/69092	Loss: 111.773
+3200/69092	Loss: 104.871
+6400/69092	Loss: 108.071
+9600/69092	Loss: 107.920
+12800/69092	Loss: 107.922
+16000/69092	Loss: 106.287
+19200/69092	Loss: 106.118
+22400/69092	Loss: 107.349
+25600/69092	Loss: 107.380
+28800/69092	Loss: 106.257
+32000/69092	Loss: 105.502
+35200/69092	Loss: 106.947
+38400/69092	Loss: 106.041
+41600/69092	Loss: 106.067
+44800/69092	Loss: 105.584
+48000/69092	Loss: 106.243
+51200/69092	Loss: 107.221
+54400/69092	Loss: 107.389
+57600/69092	Loss: 107.492
+60800/69092	Loss: 108.348
+64000/69092	Loss: 105.872
+67200/69092	Loss: 106.413
+Training time 0:08:18.334459
+Epoch: 65 Average loss: 106.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 538)
+0/69092	Loss: 112.067
+3200/69092	Loss: 107.682
+6400/69092	Loss: 105.987
+9600/69092	Loss: 105.848
+12800/69092	Loss: 106.582
+16000/69092	Loss: 106.802
+19200/69092	Loss: 105.275
+22400/69092	Loss: 105.901
+25600/69092	Loss: 106.418
+28800/69092	Loss: 107.751
+32000/69092	Loss: 106.626
+35200/69092	Loss: 106.677
+38400/69092	Loss: 108.056
+41600/69092	Loss: 107.051
+44800/69092	Loss: 106.778
+48000/69092	Loss: 105.643
+51200/69092	Loss: 106.562
+54400/69092	Loss: 107.139
+57600/69092	Loss: 104.818
+60800/69092	Loss: 107.066
+64000/69092	Loss: 107.190
+67200/69092	Loss: 105.588
+Training time 0:08:34.224917
+Epoch: 66 Average loss: 106.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 539)
+0/69092	Loss: 96.431
+3200/69092	Loss: 105.703
+6400/69092	Loss: 106.395
+9600/69092	Loss: 105.818
+12800/69092	Loss: 106.416
+16000/69092	Loss: 107.512
+19200/69092	Loss: 107.952
+22400/69092	Loss: 107.421
+25600/69092	Loss: 107.462
+28800/69092	Loss: 106.543
+32000/69092	Loss: 107.037
+35200/69092	Loss: 108.065
+38400/69092	Loss: 107.340
+41600/69092	Loss: 105.795
+44800/69092	Loss: 106.505
+48000/69092	Loss: 107.215
+51200/69092	Loss: 106.552
+54400/69092	Loss: 104.983
+57600/69092	Loss: 105.564
+60800/69092	Loss: 106.356
+64000/69092	Loss: 107.983
+67200/69092	Loss: 105.731
+Training time 0:08:30.439337
+Epoch: 67 Average loss: 106.70
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 540)
+0/69092	Loss: 114.976
+3200/69092	Loss: 107.309
+6400/69092	Loss: 107.935
+9600/69092	Loss: 106.125
+12800/69092	Loss: 107.908
+16000/69092	Loss: 107.148
+19200/69092	Loss: 104.218
+22400/69092	Loss: 106.371
+25600/69092	Loss: 106.396
+28800/69092	Loss: 106.559
+32000/69092	Loss: 106.036
+35200/69092	Loss: 106.566
+38400/69092	Loss: 107.157
+41600/69092	Loss: 108.126
+44800/69092	Loss: 106.319
+48000/69092	Loss: 106.069
+51200/69092	Loss: 106.067
+54400/69092	Loss: 107.370
+57600/69092	Loss: 105.881
+60800/69092	Loss: 105.403
+64000/69092	Loss: 107.310
+67200/69092	Loss: 107.275
+Training time 0:08:13.252026
+Epoch: 68 Average loss: 106.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 541)
+0/69092	Loss: 99.917
+3200/69092	Loss: 106.224
+6400/69092	Loss: 105.666
+9600/69092	Loss: 107.847
+12800/69092	Loss: 106.500
+16000/69092	Loss: 106.338
+19200/69092	Loss: 107.664
+22400/69092	Loss: 105.729
+25600/69092	Loss: 106.861
+28800/69092	Loss: 105.373
+32000/69092	Loss: 105.832
+35200/69092	Loss: 106.081
+38400/69092	Loss: 107.193
+41600/69092	Loss: 105.715
+44800/69092	Loss: 107.808
+48000/69092	Loss: 106.107
+51200/69092	Loss: 106.647
+54400/69092	Loss: 106.196
+57600/69092	Loss: 107.286
+60800/69092	Loss: 107.081
+64000/69092	Loss: 107.824
+67200/69092	Loss: 106.659
+Training time 0:08:26.220815
+Epoch: 69 Average loss: 106.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 542)
+0/69092	Loss: 96.187
+3200/69092	Loss: 106.788
+6400/69092	Loss: 108.266
+9600/69092	Loss: 107.103
+12800/69092	Loss: 105.631
+16000/69092	Loss: 105.931
+19200/69092	Loss: 107.223
+22400/69092	Loss: 105.194
+25600/69092	Loss: 106.766
+28800/69092	Loss: 106.415
+32000/69092	Loss: 107.222
+35200/69092	Loss: 108.016
+38400/69092	Loss: 103.679
+41600/69092	Loss: 107.784
+44800/69092	Loss: 106.803
+48000/69092	Loss: 107.110
+51200/69092	Loss: 106.737
+54400/69092	Loss: 106.157
+57600/69092	Loss: 106.908
+60800/69092	Loss: 106.449
+64000/69092	Loss: 106.568
+67200/69092	Loss: 106.570
+Training time 0:08:35.328716
+Epoch: 70 Average loss: 106.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 543)
+0/69092	Loss: 96.465
+3200/69092	Loss: 106.525
+6400/69092	Loss: 106.143
+9600/69092	Loss: 108.722
+12800/69092	Loss: 108.110
+16000/69092	Loss: 104.806
+19200/69092	Loss: 106.896
+22400/69092	Loss: 107.663
+25600/69092	Loss: 106.672
+28800/69092	Loss: 106.500
+32000/69092	Loss: 106.319
+35200/69092	Loss: 105.591
+38400/69092	Loss: 106.479
+41600/69092	Loss: 106.430
+44800/69092	Loss: 106.870
+48000/69092	Loss: 105.698
+51200/69092	Loss: 108.331
+54400/69092	Loss: 106.279
+57600/69092	Loss: 106.722
+60800/69092	Loss: 106.074
+64000/69092	Loss: 105.704
+67200/69092	Loss: 108.033
+Training time 0:08:26.880116
+Epoch: 71 Average loss: 106.76
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 544)
+0/69092	Loss: 101.296
+3200/69092	Loss: 106.033
+6400/69092	Loss: 107.260
+9600/69092	Loss: 106.719
+12800/69092	Loss: 106.981
+16000/69092	Loss: 105.958
+19200/69092	Loss: 107.825
+22400/69092	Loss: 105.346
+25600/69092	Loss: 106.700
+28800/69092	Loss: 105.283
+32000/69092	Loss: 103.792
+35200/69092	Loss: 108.263
+38400/69092	Loss: 106.326
+41600/69092	Loss: 108.210
+44800/69092	Loss: 107.555
+48000/69092	Loss: 107.407
+51200/69092	Loss: 107.132
+54400/69092	Loss: 106.339
+57600/69092	Loss: 107.422
+60800/69092	Loss: 105.770
+64000/69092	Loss: 107.280
+67200/69092	Loss: 105.756
+Training time 0:08:21.596944
+Epoch: 72 Average loss: 106.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 545)
+0/69092	Loss: 116.358
+3200/69092	Loss: 103.536
+6400/69092	Loss: 106.004
+9600/69092	Loss: 103.473
+12800/69092	Loss: 107.769
+16000/69092	Loss: 107.683
+19200/69092	Loss: 107.130
+22400/69092	Loss: 105.699
+25600/69092	Loss: 105.810
+28800/69092	Loss: 107.358
+32000/69092	Loss: 107.047
+35200/69092	Loss: 106.652
+38400/69092	Loss: 105.134
+41600/69092	Loss: 107.443
+44800/69092	Loss: 107.734
+48000/69092	Loss: 106.109
+51200/69092	Loss: 106.634
+54400/69092	Loss: 107.113
+57600/69092	Loss: 107.120
+60800/69092	Loss: 107.067
+64000/69092	Loss: 106.259
+67200/69092	Loss: 108.002
+Training time 0:08:30.729269
+Epoch: 73 Average loss: 106.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 546)
+0/69092	Loss: 106.279
+3200/69092	Loss: 106.892
+6400/69092	Loss: 106.179
+9600/69092	Loss: 106.715
+12800/69092	Loss: 104.768
+16000/69092	Loss: 107.740
+19200/69092	Loss: 105.980
+22400/69092	Loss: 105.612
+25600/69092	Loss: 106.042
+28800/69092	Loss: 105.079
+32000/69092	Loss: 106.306
+35200/69092	Loss: 108.450
+38400/69092	Loss: 107.619
+41600/69092	Loss: 106.596
+44800/69092	Loss: 107.582
+48000/69092	Loss: 106.963
+51200/69092	Loss: 105.493
+54400/69092	Loss: 107.232
+57600/69092	Loss: 105.938
+60800/69092	Loss: 106.657
+64000/69092	Loss: 106.846
+67200/69092	Loss: 106.780
+Training time 0:08:40.156697
+Epoch: 74 Average loss: 106.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 547)
+0/69092	Loss: 93.932
+3200/69092	Loss: 107.153
+6400/69092	Loss: 106.022
+9600/69092	Loss: 108.522
+12800/69092	Loss: 106.109
+16000/69092	Loss: 107.748
+19200/69092	Loss: 106.444
+22400/69092	Loss: 106.379
+25600/69092	Loss: 107.872
+28800/69092	Loss: 107.523
+32000/69092	Loss: 107.394
+35200/69092	Loss: 105.740
+38400/69092	Loss: 104.618
+41600/69092	Loss: 108.158
+44800/69092	Loss: 105.419
+48000/69092	Loss: 106.338
+51200/69092	Loss: 106.559
+54400/69092	Loss: 105.933
+57600/69092	Loss: 107.268
+60800/69092	Loss: 108.054
+64000/69092	Loss: 105.295
+67200/69092	Loss: 107.670
+Training time 0:08:22.713389
+Epoch: 75 Average loss: 106.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 548)
+0/69092	Loss: 112.471
+3200/69092	Loss: 105.479
+6400/69092	Loss: 105.327
+9600/69092	Loss: 106.741
+12800/69092	Loss: 107.022
+16000/69092	Loss: 108.649
+19200/69092	Loss: 106.341
+22400/69092	Loss: 108.150
+25600/69092	Loss: 105.045
+28800/69092	Loss: 105.651
+32000/69092	Loss: 106.048
+35200/69092	Loss: 107.443
+38400/69092	Loss: 107.691
+41600/69092	Loss: 107.966
+44800/69092	Loss: 107.182
+48000/69092	Loss: 105.511
+51200/69092	Loss: 108.080
+54400/69092	Loss: 106.122
+57600/69092	Loss: 107.991
+60800/69092	Loss: 106.702
+64000/69092	Loss: 106.680
+67200/69092	Loss: 106.126
+Training time 0:08:25.586818
+Epoch: 76 Average loss: 106.71
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 549)
+0/69092	Loss: 125.446
+3200/69092	Loss: 108.327
+6400/69092	Loss: 105.549
+9600/69092	Loss: 106.768
+12800/69092	Loss: 105.472
+16000/69092	Loss: 107.463
+19200/69092	Loss: 106.317
+22400/69092	Loss: 106.274
+25600/69092	Loss: 107.934
+28800/69092	Loss: 106.100
+32000/69092	Loss: 106.401
+35200/69092	Loss: 106.016
+38400/69092	Loss: 106.066
+41600/69092	Loss: 106.097
+44800/69092	Loss: 107.460
+48000/69092	Loss: 106.000
+51200/69092	Loss: 106.356
+54400/69092	Loss: 106.783
+57600/69092	Loss: 105.841
+60800/69092	Loss: 105.273
+64000/69092	Loss: 106.082
+67200/69092	Loss: 107.837
+Training time 0:08:36.774481
+Epoch: 77 Average loss: 106.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 550)
+0/69092	Loss: 106.139
+3200/69092	Loss: 107.667
+6400/69092	Loss: 107.984
+9600/69092	Loss: 107.187
+12800/69092	Loss: 106.824
+16000/69092	Loss: 105.626
+19200/69092	Loss: 105.925
+22400/69092	Loss: 105.984
+25600/69092	Loss: 104.631
+28800/69092	Loss: 105.691
+32000/69092	Loss: 106.019
+35200/69092	Loss: 109.997
+38400/69092	Loss: 106.446
+41600/69092	Loss: 107.079
+44800/69092	Loss: 107.219
+48000/69092	Loss: 106.572
+51200/69092	Loss: 105.760
+54400/69092	Loss: 107.277
+57600/69092	Loss: 106.704
+60800/69092	Loss: 106.896
+64000/69092	Loss: 106.848
+67200/69092	Loss: 108.343
+Training time 0:08:29.199597
+Epoch: 78 Average loss: 106.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 551)
+0/69092	Loss: 105.906
+3200/69092	Loss: 105.913
+6400/69092	Loss: 107.170
+9600/69092	Loss: 108.895
+12800/69092	Loss: 107.597
+16000/69092	Loss: 106.216
+19200/69092	Loss: 107.371
+22400/69092	Loss: 104.867
+25600/69092	Loss: 106.390
+28800/69092	Loss: 107.227
+32000/69092	Loss: 107.842
+35200/69092	Loss: 107.306
+38400/69092	Loss: 106.476
+41600/69092	Loss: 106.402
+44800/69092	Loss: 105.766
+48000/69092	Loss: 106.704
+51200/69092	Loss: 107.318
+54400/69092	Loss: 106.777
+57600/69092	Loss: 106.117
+60800/69092	Loss: 107.979
+64000/69092	Loss: 106.311
+67200/69092	Loss: 105.790
+Training time 0:08:11.219389
+Epoch: 79 Average loss: 106.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 552)
+0/69092	Loss: 110.955
+3200/69092	Loss: 105.677
+6400/69092	Loss: 105.314
+9600/69092	Loss: 106.001
+12800/69092	Loss: 105.724
+16000/69092	Loss: 104.606
+19200/69092	Loss: 107.861
+22400/69092	Loss: 106.510
+25600/69092	Loss: 106.375
+28800/69092	Loss: 107.115
+32000/69092	Loss: 106.786
+35200/69092	Loss: 106.548
+38400/69092	Loss: 106.094
+41600/69092	Loss: 107.739
+44800/69092	Loss: 107.100
+48000/69092	Loss: 106.136
+51200/69092	Loss: 105.870
+54400/69092	Loss: 106.975
+57600/69092	Loss: 107.084
+60800/69092	Loss: 106.723
+64000/69092	Loss: 107.267
+67200/69092	Loss: 107.024
+Training time 0:08:25.854508
+Epoch: 80 Average loss: 106.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 553)
+0/69092	Loss: 106.960
+3200/69092	Loss: 108.173
+6400/69092	Loss: 105.275
+9600/69092	Loss: 106.056
+12800/69092	Loss: 107.179
+16000/69092	Loss: 106.083
+19200/69092	Loss: 107.189
+22400/69092	Loss: 106.707
+25600/69092	Loss: 105.663
+28800/69092	Loss: 105.250
+32000/69092	Loss: 107.233
+35200/69092	Loss: 104.668
+38400/69092	Loss: 106.654
+41600/69092	Loss: 107.300
+44800/69092	Loss: 107.596
+48000/69092	Loss: 105.159
+51200/69092	Loss: 108.112
+54400/69092	Loss: 107.545
+57600/69092	Loss: 108.110
+60800/69092	Loss: 106.197
+64000/69092	Loss: 106.268
+67200/69092	Loss: 106.146
+Training time 0:08:32.617019
+Epoch: 81 Average loss: 106.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 554)
+0/69092	Loss: 107.212
+3200/69092	Loss: 106.938
+6400/69092	Loss: 107.014
+9600/69092	Loss: 105.588
+12800/69092	Loss: 106.036
+16000/69092	Loss: 106.525
+19200/69092	Loss: 106.197
+22400/69092	Loss: 106.753
+25600/69092	Loss: 107.698
+28800/69092	Loss: 107.652
+32000/69092	Loss: 106.486
+35200/69092	Loss: 106.304
+38400/69092	Loss: 107.150
+41600/69092	Loss: 105.466
+44800/69092	Loss: 105.933
+48000/69092	Loss: 107.223
+51200/69092	Loss: 108.269
+54400/69092	Loss: 106.749
+57600/69092	Loss: 106.128
+60800/69092	Loss: 106.430
+64000/69092	Loss: 106.371
+67200/69092	Loss: 105.995
+Training time 0:08:26.599709
+Epoch: 82 Average loss: 106.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 555)
+0/69092	Loss: 115.997
+3200/69092	Loss: 107.198
+6400/69092	Loss: 104.869
+9600/69092	Loss: 104.136
+12800/69092	Loss: 106.274
+16000/69092	Loss: 106.781
+19200/69092	Loss: 107.005
+22400/69092	Loss: 106.329
+25600/69092	Loss: 106.498
+28800/69092	Loss: 108.122
+32000/69092	Loss: 107.925
+35200/69092	Loss: 105.565
+38400/69092	Loss: 106.657
+41600/69092	Loss: 107.688
+44800/69092	Loss: 106.680
+48000/69092	Loss: 106.717
+51200/69092	Loss: 107.740
+54400/69092	Loss: 108.111
+57600/69092	Loss: 107.357
+60800/69092	Loss: 105.864
+64000/69092	Loss: 107.012
+67200/69092	Loss: 107.682
+Training time 0:08:24.579715
+Epoch: 83 Average loss: 106.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 556)
+0/69092	Loss: 100.154
+3200/69092	Loss: 106.847
+6400/69092	Loss: 105.558
+9600/69092	Loss: 105.568
+12800/69092	Loss: 107.240
+16000/69092	Loss: 107.364
+19200/69092	Loss: 107.726
+22400/69092	Loss: 106.409
+25600/69092	Loss: 105.221
+28800/69092	Loss: 106.967
+32000/69092	Loss: 107.232
+35200/69092	Loss: 107.840
+38400/69092	Loss: 104.893
+41600/69092	Loss: 107.144
+44800/69092	Loss: 107.629
+48000/69092	Loss: 109.101
+51200/69092	Loss: 107.478
+54400/69092	Loss: 106.878
+57600/69092	Loss: 104.645
+60800/69092	Loss: 105.861
+64000/69092	Loss: 105.539
+67200/69092	Loss: 107.056
+Training time 0:08:33.416262
+Epoch: 84 Average loss: 106.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 557)
+0/69092	Loss: 105.662
+3200/69092	Loss: 105.575
+6400/69092	Loss: 107.484
+9600/69092	Loss: 106.945
+12800/69092	Loss: 106.892
+16000/69092	Loss: 107.622
+19200/69092	Loss: 106.659
+22400/69092	Loss: 106.549
+25600/69092	Loss: 107.377
+28800/69092	Loss: 106.225
+32000/69092	Loss: 105.550
+35200/69092	Loss: 107.221
+38400/69092	Loss: 106.690
+41600/69092	Loss: 106.347
+44800/69092	Loss: 105.450
+48000/69092	Loss: 107.171
+51200/69092	Loss: 106.586
+54400/69092	Loss: 108.083
+57600/69092	Loss: 107.785
+60800/69092	Loss: 105.308
+64000/69092	Loss: 106.415
+67200/69092	Loss: 105.815
+Training time 0:08:27.993073
+Epoch: 85 Average loss: 106.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 558)
+0/69092	Loss: 105.058
+3200/69092	Loss: 105.433
+6400/69092	Loss: 105.411
+9600/69092	Loss: 107.266
+12800/69092	Loss: 106.522
+16000/69092	Loss: 105.677
+19200/69092	Loss: 106.750
+22400/69092	Loss: 106.820
+25600/69092	Loss: 106.956
+28800/69092	Loss: 106.802
+32000/69092	Loss: 108.028
+35200/69092	Loss: 106.721
+38400/69092	Loss: 106.031
+41600/69092	Loss: 105.631
+44800/69092	Loss: 106.996
+48000/69092	Loss: 107.511
+51200/69092	Loss: 107.214
+54400/69092	Loss: 106.492
+57600/69092	Loss: 106.354
+60800/69092	Loss: 105.675
+64000/69092	Loss: 107.078
+67200/69092	Loss: 106.644
+Training time 0:08:21.113474
+Epoch: 86 Average loss: 106.59
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 559)
+0/69092	Loss: 87.738
+3200/69092	Loss: 108.162
+6400/69092	Loss: 105.874
+9600/69092	Loss: 105.788
+12800/69092	Loss: 106.591
+16000/69092	Loss: 106.330
+19200/69092	Loss: 105.440
+22400/69092	Loss: 105.758
+25600/69092	Loss: 105.230
+28800/69092	Loss: 106.226
+32000/69092	Loss: 108.200
+35200/69092	Loss: 106.278
+38400/69092	Loss: 107.685
+41600/69092	Loss: 106.803
+44800/69092	Loss: 107.027
+48000/69092	Loss: 107.643
+51200/69092	Loss: 107.109
+54400/69092	Loss: 106.528
+57600/69092	Loss: 107.204
+60800/69092	Loss: 106.700
+64000/69092	Loss: 107.322
+67200/69092	Loss: 105.244
+Training time 0:08:34.354287
+Epoch: 87 Average loss: 106.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 560)
+0/69092	Loss: 104.140
+3200/69092	Loss: 106.488
+6400/69092	Loss: 108.441
+9600/69092	Loss: 105.809
+12800/69092	Loss: 107.063
+16000/69092	Loss: 105.639
+19200/69092	Loss: 105.780
+22400/69092	Loss: 105.358
+25600/69092	Loss: 106.857
+28800/69092	Loss: 105.501
+32000/69092	Loss: 106.418
+35200/69092	Loss: 106.043
+38400/69092	Loss: 107.935
+41600/69092	Loss: 106.012
+44800/69092	Loss: 107.955
+48000/69092	Loss: 106.256
+51200/69092	Loss: 105.531
+54400/69092	Loss: 106.118
+57600/69092	Loss: 108.879
+60800/69092	Loss: 107.136
+64000/69092	Loss: 105.615
+67200/69092	Loss: 106.285
+Training time 0:08:37.034070
+Epoch: 88 Average loss: 106.53
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 561)
+0/69092	Loss: 105.211
+3200/69092	Loss: 106.010
+6400/69092	Loss: 104.993
+9600/69092	Loss: 105.633
+12800/69092	Loss: 106.076
+16000/69092	Loss: 105.572
+19200/69092	Loss: 106.904
+22400/69092	Loss: 106.634
+25600/69092	Loss: 106.452
+28800/69092	Loss: 105.901
+32000/69092	Loss: 108.212
+35200/69092	Loss: 105.657
+38400/69092	Loss: 106.694
+41600/69092	Loss: 107.034
+44800/69092	Loss: 106.607
+48000/69092	Loss: 106.575
+51200/69092	Loss: 106.384
+54400/69092	Loss: 108.745
+57600/69092	Loss: 106.425
+60800/69092	Loss: 106.217
+64000/69092	Loss: 106.343
+67200/69092	Loss: 107.606
+Training time 0:08:19.491601
+Epoch: 89 Average loss: 106.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 562)
+0/69092	Loss: 101.996
+3200/69092	Loss: 105.231
+6400/69092	Loss: 106.409
+9600/69092	Loss: 107.256
+12800/69092	Loss: 107.033
+16000/69092	Loss: 107.012
+19200/69092	Loss: 107.187
+22400/69092	Loss: 107.347
+25600/69092	Loss: 105.871
+28800/69092	Loss: 106.757
+32000/69092	Loss: 106.765
+35200/69092	Loss: 106.306
+38400/69092	Loss: 106.443
+41600/69092	Loss: 105.710
+44800/69092	Loss: 107.804
+48000/69092	Loss: 108.114
+51200/69092	Loss: 106.316
+54400/69092	Loss: 107.193
+57600/69092	Loss: 105.402
+60800/69092	Loss: 104.739
+64000/69092	Loss: 105.906
+67200/69092	Loss: 106.012
+Training time 0:08:17.810853
+Epoch: 90 Average loss: 106.54
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 563)
+0/69092	Loss: 101.866
+3200/69092	Loss: 107.387
+6400/69092	Loss: 106.410
+9600/69092	Loss: 106.109
+12800/69092	Loss: 105.469
+16000/69092	Loss: 105.496
+19200/69092	Loss: 108.623
+22400/69092	Loss: 107.144
+25600/69092	Loss: 106.123
+28800/69092	Loss: 107.911
+32000/69092	Loss: 107.436
+35200/69092	Loss: 106.696
+38400/69092	Loss: 104.772
+41600/69092	Loss: 105.925
+44800/69092	Loss: 105.818
+48000/69092	Loss: 106.528
+51200/69092	Loss: 107.295
+54400/69092	Loss: 106.600
+57600/69092	Loss: 103.775
+60800/69092	Loss: 105.873
+64000/69092	Loss: 106.677
+67200/69092	Loss: 106.123
+Training time 0:08:46.247104
+Epoch: 91 Average loss: 106.42
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 564)
+0/69092	Loss: 104.837
+3200/69092	Loss: 106.875
+6400/69092	Loss: 106.457
+9600/69092	Loss: 105.655
+12800/69092	Loss: 105.351
+16000/69092	Loss: 106.428
+19200/69092	Loss: 105.372
+22400/69092	Loss: 108.413
+25600/69092	Loss: 108.880
+28800/69092	Loss: 107.827
+32000/69092	Loss: 105.930
+35200/69092	Loss: 105.307
+38400/69092	Loss: 107.566
+41600/69092	Loss: 106.520
+44800/69092	Loss: 106.724
+48000/69092	Loss: 106.119
+51200/69092	Loss: 106.419
+54400/69092	Loss: 105.963
+57600/69092	Loss: 107.450
+60800/69092	Loss: 108.206
+64000/69092	Loss: 106.904
+67200/69092	Loss: 106.441
+Training time 0:08:32.769669
+Epoch: 92 Average loss: 106.69
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 565)
+0/69092	Loss: 97.841
+3200/69092	Loss: 104.655
+6400/69092	Loss: 107.035
+9600/69092	Loss: 107.489
+12800/69092	Loss: 105.805
+16000/69092	Loss: 106.489
+19200/69092	Loss: 105.825
+22400/69092	Loss: 106.233
+25600/69092	Loss: 106.867
+28800/69092	Loss: 106.509
+32000/69092	Loss: 108.193
+35200/69092	Loss: 105.844
+38400/69092	Loss: 107.280
+41600/69092	Loss: 106.671
+44800/69092	Loss: 106.287
+48000/69092	Loss: 105.643
+51200/69092	Loss: 107.181
+54400/69092	Loss: 106.311
+57600/69092	Loss: 106.823
+60800/69092	Loss: 107.617
+64000/69092	Loss: 106.174
+67200/69092	Loss: 107.108
+Training time 0:08:20.870279
+Epoch: 93 Average loss: 106.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 566)
+0/69092	Loss: 97.813
+3200/69092	Loss: 107.677
+6400/69092	Loss: 106.696
+9600/69092	Loss: 105.603
+12800/69092	Loss: 107.431
+16000/69092	Loss: 108.037
+19200/69092	Loss: 106.538
+22400/69092	Loss: 107.028
+25600/69092	Loss: 105.010
+28800/69092	Loss: 106.051
+32000/69092	Loss: 105.185
+35200/69092	Loss: 105.695
+38400/69092	Loss: 107.749
+41600/69092	Loss: 107.442
+44800/69092	Loss: 105.340
+48000/69092	Loss: 106.588
+51200/69092	Loss: 106.778
+54400/69092	Loss: 106.053
+57600/69092	Loss: 106.711
+60800/69092	Loss: 105.811
+64000/69092	Loss: 107.183
+67200/69092	Loss: 106.535
+Training time 0:08:18.803144
+Epoch: 94 Average loss: 106.53
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 567)
+0/69092	Loss: 108.440
+3200/69092	Loss: 105.307
+6400/69092	Loss: 106.170
+9600/69092	Loss: 104.826
+12800/69092	Loss: 106.699
+16000/69092	Loss: 107.565
+19200/69092	Loss: 105.973
+22400/69092	Loss: 106.493
+25600/69092	Loss: 106.743
+28800/69092	Loss: 105.288
+32000/69092	Loss: 105.875
+35200/69092	Loss: 108.064
+38400/69092	Loss: 107.672
+41600/69092	Loss: 107.145
+44800/69092	Loss: 108.879
+48000/69092	Loss: 107.308
+51200/69092	Loss: 105.958
+54400/69092	Loss: 106.727
+57600/69092	Loss: 106.470
+60800/69092	Loss: 106.323
+64000/69092	Loss: 106.873
+67200/69092	Loss: 105.398
+Training time 0:08:36.684925
+Epoch: 95 Average loss: 106.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 568)
+0/69092	Loss: 112.306
+3200/69092	Loss: 107.046
+6400/69092	Loss: 108.012
+9600/69092	Loss: 108.744
+12800/69092	Loss: 105.387
+16000/69092	Loss: 106.749
+19200/69092	Loss: 106.476
+22400/69092	Loss: 106.902
+25600/69092	Loss: 107.680
+28800/69092	Loss: 105.778
+32000/69092	Loss: 106.024
+35200/69092	Loss: 106.227
+38400/69092	Loss: 107.963
+41600/69092	Loss: 106.264
+44800/69092	Loss: 105.777
+48000/69092	Loss: 106.060
+51200/69092	Loss: 105.065
+54400/69092	Loss: 107.312
+57600/69092	Loss: 107.417
+60800/69092	Loss: 105.747
+64000/69092	Loss: 106.944
+67200/69092	Loss: 105.562
+Training time 0:08:22.477667
+Epoch: 96 Average loss: 106.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 569)
+0/69092	Loss: 103.174
+3200/69092	Loss: 108.266
+6400/69092	Loss: 106.937
+9600/69092	Loss: 106.551
+12800/69092	Loss: 107.026
+16000/69092	Loss: 106.835
+19200/69092	Loss: 105.323
+22400/69092	Loss: 106.354
+25600/69092	Loss: 107.187
+28800/69092	Loss: 104.643
+32000/69092	Loss: 104.611
+35200/69092	Loss: 105.228
+38400/69092	Loss: 106.619
+41600/69092	Loss: 105.949
+44800/69092	Loss: 105.117
+48000/69092	Loss: 107.675
+51200/69092	Loss: 107.087
+54400/69092	Loss: 106.688
+57600/69092	Loss: 108.028
+60800/69092	Loss: 107.003
+64000/69092	Loss: 107.631
+67200/69092	Loss: 107.081
+Training time 0:08:12.499307
+Epoch: 97 Average loss: 106.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 570)
+0/69092	Loss: 96.257
+3200/69092	Loss: 105.628
+6400/69092	Loss: 107.010
+9600/69092	Loss: 104.935
+12800/69092	Loss: 106.254
+16000/69092	Loss: 106.339
+19200/69092	Loss: 106.130
+22400/69092	Loss: 106.609
+25600/69092	Loss: 107.554
+28800/69092	Loss: 107.556
+32000/69092	Loss: 106.997
+35200/69092	Loss: 107.574
+38400/69092	Loss: 106.652
+41600/69092	Loss: 106.061
+44800/69092	Loss: 107.786
+48000/69092	Loss: 105.993
+51200/69092	Loss: 106.971
+54400/69092	Loss: 107.254
+57600/69092	Loss: 107.461
+60800/69092	Loss: 105.741
+64000/69092	Loss: 106.470
+67200/69092	Loss: 105.178
+Training time 0:08:36.302635
+Epoch: 98 Average loss: 106.59
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 571)
+0/69092	Loss: 108.847
+3200/69092	Loss: 105.326
+6400/69092	Loss: 107.382
+9600/69092	Loss: 105.930
+12800/69092	Loss: 105.297
+16000/69092	Loss: 106.556
+19200/69092	Loss: 105.766
+22400/69092	Loss: 106.902
+25600/69092	Loss: 107.530
+28800/69092	Loss: 108.505
+32000/69092	Loss: 105.405
+35200/69092	Loss: 106.487
+38400/69092	Loss: 106.815
+41600/69092	Loss: 107.256
+44800/69092	Loss: 106.005
+48000/69092	Loss: 106.362
+51200/69092	Loss: 104.808
+54400/69092	Loss: 105.526
+57600/69092	Loss: 107.615
+60800/69092	Loss: 108.101
+64000/69092	Loss: 107.221
+67200/69092	Loss: 106.666
+Training time 0:08:32.220972
+Epoch: 99 Average loss: 106.53
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 572)
+0/69092	Loss: 110.655
+3200/69092	Loss: 104.544
+6400/69092	Loss: 105.357
+9600/69092	Loss: 106.638
+12800/69092	Loss: 107.022
+16000/69092	Loss: 105.573
+19200/69092	Loss: 107.178
+22400/69092	Loss: 104.602
+25600/69092	Loss: 107.409
+28800/69092	Loss: 104.997
+32000/69092	Loss: 105.977
+35200/69092	Loss: 106.093
+38400/69092	Loss: 107.718
+41600/69092	Loss: 106.939
+44800/69092	Loss: 106.759
+48000/69092	Loss: 105.517
+51200/69092	Loss: 106.247
+54400/69092	Loss: 107.240
+57600/69092	Loss: 107.913
+60800/69092	Loss: 107.271
+64000/69092	Loss: 106.277
+67200/69092	Loss: 106.964
+Training time 0:08:15.646117
+Epoch: 100 Average loss: 106.42
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 573)
+0/69092	Loss: 104.857
+3200/69092	Loss: 106.219
+6400/69092	Loss: 107.007
+9600/69092	Loss: 106.799
+12800/69092	Loss: 108.105
+16000/69092	Loss: 107.167
+19200/69092	Loss: 105.635
+22400/69092	Loss: 106.038
+25600/69092	Loss: 106.076
+28800/69092	Loss: 106.105
+32000/69092	Loss: 108.328
+35200/69092	Loss: 106.938
+38400/69092	Loss: 107.063
+41600/69092	Loss: 106.562
+44800/69092	Loss: 104.637
+48000/69092	Loss: 105.994
+51200/69092	Loss: 106.819
+54400/69092	Loss: 107.028
+57600/69092	Loss: 106.172
+60800/69092	Loss: 106.296
+64000/69092	Loss: 106.977
+67200/69092	Loss: 106.896
+Training time 0:08:22.812712
+Epoch: 101 Average loss: 106.59
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 574)
+0/69092	Loss: 108.823
+3200/69092	Loss: 106.071
+6400/69092	Loss: 106.411
+9600/69092	Loss: 104.916
+12800/69092	Loss: 105.965
+16000/69092	Loss: 106.965
+19200/69092	Loss: 106.267
+22400/69092	Loss: 105.886
+25600/69092	Loss: 107.156
+28800/69092	Loss: 107.479
+32000/69092	Loss: 106.866
+35200/69092	Loss: 106.268
+38400/69092	Loss: 105.987
+41600/69092	Loss: 107.420
+44800/69092	Loss: 105.909
+48000/69092	Loss: 106.953
+51200/69092	Loss: 106.461
+54400/69092	Loss: 104.351
+57600/69092	Loss: 105.880
+60800/69092	Loss: 106.526
+64000/69092	Loss: 107.518
+67200/69092	Loss: 108.069
+Training time 0:08:28.246423
+Epoch: 102 Average loss: 106.44
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 575)
+0/69092	Loss: 90.145
+3200/69092	Loss: 106.912
+6400/69092	Loss: 106.513
+9600/69092	Loss: 106.783
+12800/69092	Loss: 106.567
+16000/69092	Loss: 108.657
+19200/69092	Loss: 104.472
+22400/69092	Loss: 104.730
+25600/69092	Loss: 106.228
+28800/69092	Loss: 106.621
+32000/69092	Loss: 105.932
+35200/69092	Loss: 106.758
+38400/69092	Loss: 106.631
+41600/69092	Loss: 106.657
+44800/69092	Loss: 106.986
+48000/69092	Loss: 105.172
+51200/69092	Loss: 107.157
+54400/69092	Loss: 105.394
+57600/69092	Loss: 107.325
+60800/69092	Loss: 107.413
+64000/69092	Loss: 106.906
+67200/69092	Loss: 106.041
+Training time 0:08:21.547282
+Epoch: 103 Average loss: 106.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 576)
+0/69092	Loss: 101.803
+3200/69092	Loss: 105.891
+6400/69092	Loss: 107.034
+9600/69092	Loss: 104.733
+12800/69092	Loss: 109.100
+16000/69092	Loss: 106.509
+19200/69092	Loss: 107.214
+22400/69092	Loss: 106.740
+25600/69092	Loss: 106.181
+28800/69092	Loss: 106.539
+32000/69092	Loss: 106.197
+35200/69092	Loss: 106.938
+38400/69092	Loss: 105.540
+41600/69092	Loss: 106.054
+44800/69092	Loss: 104.853
+48000/69092	Loss: 106.676
+51200/69092	Loss: 106.511
+54400/69092	Loss: 107.937
+57600/69092	Loss: 107.244
+60800/69092	Loss: 105.338
+64000/69092	Loss: 105.975
+67200/69092	Loss: 106.113
+Training time 0:08:12.558727
+Epoch: 104 Average loss: 106.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 577)
+0/69092	Loss: 109.674
+3200/69092	Loss: 108.123
+6400/69092	Loss: 105.217
+9600/69092	Loss: 107.941
+12800/69092	Loss: 106.427
+16000/69092	Loss: 107.033
+19200/69092	Loss: 105.876
+22400/69092	Loss: 105.880
+25600/69092	Loss: 106.558
+28800/69092	Loss: 105.464
+32000/69092	Loss: 106.877
+35200/69092	Loss: 104.750
+38400/69092	Loss: 106.217
+41600/69092	Loss: 107.001
+44800/69092	Loss: 106.580
+48000/69092	Loss: 107.178
+51200/69092	Loss: 106.426
+54400/69092	Loss: 108.541
+57600/69092	Loss: 106.001
+60800/69092	Loss: 106.436
+64000/69092	Loss: 107.500
+67200/69092	Loss: 107.767
+Training time 0:08:34.456709
+Epoch: 105 Average loss: 106.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 578)
+0/69092	Loss: 101.095
+3200/69092	Loss: 106.131
+6400/69092	Loss: 106.041
+9600/69092	Loss: 106.539
+12800/69092	Loss: 105.599
+16000/69092	Loss: 106.751
+19200/69092	Loss: 106.833
+22400/69092	Loss: 107.411
+25600/69092	Loss: 106.772
+28800/69092	Loss: 104.804
+32000/69092	Loss: 106.089
+35200/69092	Loss: 106.887
+38400/69092	Loss: 106.886
+41600/69092	Loss: 106.114
+44800/69092	Loss: 106.894
+48000/69092	Loss: 106.840
+51200/69092	Loss: 105.489
+54400/69092	Loss: 106.712
+57600/69092	Loss: 106.660
+60800/69092	Loss: 106.437
+64000/69092	Loss: 106.806
+67200/69092	Loss: 107.489
+Training time 0:08:28.235144
+Epoch: 106 Average loss: 106.50
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 579)
+0/69092	Loss: 97.506
+3200/69092	Loss: 106.761
+6400/69092	Loss: 107.421
+9600/69092	Loss: 107.569
+12800/69092	Loss: 105.493
+16000/69092	Loss: 106.673
+19200/69092	Loss: 107.873
+22400/69092	Loss: 108.085
+25600/69092	Loss: 105.795
+28800/69092	Loss: 107.487
+32000/69092	Loss: 105.760
+35200/69092	Loss: 105.321
+38400/69092	Loss: 106.811
+41600/69092	Loss: 105.967
+44800/69092	Loss: 105.562
+48000/69092	Loss: 106.116
+51200/69092	Loss: 106.836
+54400/69092	Loss: 107.578
+57600/69092	Loss: 106.066
+60800/69092	Loss: 105.927
+64000/69092	Loss: 107.201
+67200/69092	Loss: 106.226
+Training time 0:08:12.790983
+Epoch: 107 Average loss: 106.59
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 580)
+0/69092	Loss: 104.775
+3200/69092	Loss: 107.174
+6400/69092	Loss: 106.880
+9600/69092	Loss: 107.510
+12800/69092	Loss: 108.077
+16000/69092	Loss: 106.683
+19200/69092	Loss: 105.363
+22400/69092	Loss: 108.048
+25600/69092	Loss: 106.564
+28800/69092	Loss: 106.165
+32000/69092	Loss: 107.178
+35200/69092	Loss: 105.587
+38400/69092	Loss: 106.691
+41600/69092	Loss: 105.587
+44800/69092	Loss: 107.081
+48000/69092	Loss: 105.576
+51200/69092	Loss: 106.919
+54400/69092	Loss: 105.137
+57600/69092	Loss: 105.929
+60800/69092	Loss: 105.176
+64000/69092	Loss: 105.134
+67200/69092	Loss: 105.331
+Training time 0:08:34.503189
+Epoch: 108 Average loss: 106.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 581)
+0/69092	Loss: 114.262
+3200/69092	Loss: 104.593
+6400/69092	Loss: 106.806
+9600/69092	Loss: 107.125
+12800/69092	Loss: 105.918
+16000/69092	Loss: 106.070
+19200/69092	Loss: 105.864
+22400/69092	Loss: 106.633
+25600/69092	Loss: 107.604
+28800/69092	Loss: 106.119
+32000/69092	Loss: 106.117
+35200/69092	Loss: 106.122
+38400/69092	Loss: 108.070
+41600/69092	Loss: 106.325
+44800/69092	Loss: 106.823
+48000/69092	Loss: 106.984
+51200/69092	Loss: 106.556
+54400/69092	Loss: 106.284
+57600/69092	Loss: 106.956
+60800/69092	Loss: 106.351
+64000/69092	Loss: 104.856
+67200/69092	Loss: 106.425
+Training time 0:08:28.963040
+Epoch: 109 Average loss: 106.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 582)
+0/69092	Loss: 103.309
+3200/69092	Loss: 106.830
+6400/69092	Loss: 106.490
+9600/69092	Loss: 107.545
+12800/69092	Loss: 106.740
+16000/69092	Loss: 107.174
+19200/69092	Loss: 106.037
+22400/69092	Loss: 105.181
+25600/69092	Loss: 107.872
+28800/69092	Loss: 106.313
+32000/69092	Loss: 106.348
+35200/69092	Loss: 106.432
+38400/69092	Loss: 106.739
+41600/69092	Loss: 106.703
+44800/69092	Loss: 106.294
+48000/69092	Loss: 106.885
+51200/69092	Loss: 105.335
+54400/69092	Loss: 105.724
+57600/69092	Loss: 105.690
+60800/69092	Loss: 107.216
+64000/69092	Loss: 106.446
+67200/69092	Loss: 106.363
+Training time 0:08:08.024328
+Epoch: 110 Average loss: 106.52
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 583)
+0/69092	Loss: 107.794
+3200/69092	Loss: 107.753
+6400/69092	Loss: 105.483
+9600/69092	Loss: 106.462
+12800/69092	Loss: 104.751
+16000/69092	Loss: 107.653
+19200/69092	Loss: 106.754
+22400/69092	Loss: 105.699
+25600/69092	Loss: 108.046
+28800/69092	Loss: 105.099
+32000/69092	Loss: 107.641
+35200/69092	Loss: 106.035
+38400/69092	Loss: 107.441
+41600/69092	Loss: 105.351
+44800/69092	Loss: 106.360
+48000/69092	Loss: 105.913
+51200/69092	Loss: 107.599
+54400/69092	Loss: 106.876
+57600/69092	Loss: 105.477
+60800/69092	Loss: 105.446
+64000/69092	Loss: 106.565
+67200/69092	Loss: 105.272
+Training time 0:08:26.274149
+Epoch: 111 Average loss: 106.44
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 584)
+0/69092	Loss: 97.800
+3200/69092	Loss: 104.214
+6400/69092	Loss: 105.424
+9600/69092	Loss: 106.198
+12800/69092	Loss: 107.105
+16000/69092	Loss: 107.020
+19200/69092	Loss: 104.743
+22400/69092	Loss: 105.924
+25600/69092	Loss: 106.824
+28800/69092	Loss: 105.913
+32000/69092	Loss: 106.818
+35200/69092	Loss: 105.020
+38400/69092	Loss: 106.240
+41600/69092	Loss: 107.335
+44800/69092	Loss: 107.042
+48000/69092	Loss: 106.666
+51200/69092	Loss: 107.157
+54400/69092	Loss: 106.591
+57600/69092	Loss: 105.460
+60800/69092	Loss: 107.370
+64000/69092	Loss: 106.605
+67200/69092	Loss: 108.525
+Training time 0:08:28.023627
+Epoch: 112 Average loss: 106.39
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 585)
+0/69092	Loss: 97.752
+3200/69092	Loss: 107.426
+6400/69092	Loss: 106.317
+9600/69092	Loss: 106.898
+12800/69092	Loss: 107.114
+16000/69092	Loss: 106.105
+19200/69092	Loss: 107.259
+22400/69092	Loss: 107.036
+25600/69092	Loss: 105.074
+28800/69092	Loss: 105.453
+32000/69092	Loss: 105.192
+35200/69092	Loss: 106.822
+38400/69092	Loss: 104.521
+41600/69092	Loss: 104.586
+44800/69092	Loss: 107.501
+48000/69092	Loss: 106.268
+51200/69092	Loss: 108.413
+54400/69092	Loss: 105.898
+57600/69092	Loss: 107.150
+60800/69092	Loss: 106.675
+64000/69092	Loss: 105.366
+67200/69092	Loss: 106.280
+Training time 0:08:28.891248
+Epoch: 113 Average loss: 106.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 586)
+0/69092	Loss: 105.591
+3200/69092	Loss: 106.394
+6400/69092	Loss: 107.415
+9600/69092	Loss: 108.271
+12800/69092	Loss: 108.131
+16000/69092	Loss: 106.722
+19200/69092	Loss: 106.922
+22400/69092	Loss: 106.939
+25600/69092	Loss: 105.477
+28800/69092	Loss: 106.114
+32000/69092	Loss: 106.219
+35200/69092	Loss: 105.660
+38400/69092	Loss: 106.372
+41600/69092	Loss: 107.382
+44800/69092	Loss: 106.470
+48000/69092	Loss: 106.321
+51200/69092	Loss: 106.890
+54400/69092	Loss: 107.213
+57600/69092	Loss: 105.992
+60800/69092	Loss: 107.278
+64000/69092	Loss: 105.836
+67200/69092	Loss: 105.479
+Training time 0:08:11.030553
+Epoch: 114 Average loss: 106.59
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 587)
+0/69092	Loss: 97.103
+3200/69092	Loss: 106.608
+6400/69092	Loss: 106.589
+9600/69092	Loss: 105.374
+12800/69092	Loss: 107.543
+16000/69092	Loss: 106.442
+19200/69092	Loss: 106.628
+22400/69092	Loss: 106.406
+25600/69092	Loss: 106.435
+28800/69092	Loss: 104.022
+32000/69092	Loss: 106.017
+35200/69092	Loss: 105.766
+38400/69092	Loss: 105.761
+41600/69092	Loss: 105.409
+44800/69092	Loss: 107.452
+48000/69092	Loss: 106.582
+51200/69092	Loss: 105.450
+54400/69092	Loss: 106.892
+57600/69092	Loss: 105.557
+60800/69092	Loss: 108.768
+64000/69092	Loss: 106.782
+67200/69092	Loss: 106.896
+Training time 0:08:29.245296
+Epoch: 115 Average loss: 106.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 588)
+0/69092	Loss: 105.229
+3200/69092	Loss: 105.985
+6400/69092	Loss: 106.827
+9600/69092	Loss: 106.551
+12800/69092	Loss: 104.720
+16000/69092	Loss: 106.133
+19200/69092	Loss: 106.348
+22400/69092	Loss: 107.927
+25600/69092	Loss: 107.240
+28800/69092	Loss: 106.887
+32000/69092	Loss: 105.037
+35200/69092	Loss: 106.658
+38400/69092	Loss: 106.463
+41600/69092	Loss: 106.902
+44800/69092	Loss: 106.547
+48000/69092	Loss: 107.392
+51200/69092	Loss: 107.407
+54400/69092	Loss: 106.834
+57600/69092	Loss: 105.283
+60800/69092	Loss: 106.722
+64000/69092	Loss: 107.001
+67200/69092	Loss: 105.936
+Training time 0:08:48.953124
+Epoch: 116 Average loss: 106.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 589)
+0/69092	Loss: 103.118
+3200/69092	Loss: 106.755
+6400/69092	Loss: 106.061
+9600/69092	Loss: 105.774
+12800/69092	Loss: 106.025
+16000/69092	Loss: 105.834
+19200/69092	Loss: 106.687
+22400/69092	Loss: 107.147
+25600/69092	Loss: 106.915
+28800/69092	Loss: 106.410
+32000/69092	Loss: 108.176
+35200/69092	Loss: 104.790
+38400/69092	Loss: 107.187
+41600/69092	Loss: 106.425
+44800/69092	Loss: 105.947
+48000/69092	Loss: 106.277
+51200/69092	Loss: 106.188
+54400/69092	Loss: 105.367
+57600/69092	Loss: 104.945
+60800/69092	Loss: 108.165
+64000/69092	Loss: 105.182
+67200/69092	Loss: 105.689
+Training time 0:08:16.602949
+Epoch: 117 Average loss: 106.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 590)
+0/69092	Loss: 119.743
+3200/69092	Loss: 105.768
+6400/69092	Loss: 106.127
+9600/69092	Loss: 106.418
+12800/69092	Loss: 105.977
+16000/69092	Loss: 104.420
+19200/69092	Loss: 107.169
+22400/69092	Loss: 105.479
+25600/69092	Loss: 104.814
+28800/69092	Loss: 108.067
+32000/69092	Loss: 106.086
+35200/69092	Loss: 108.541
+38400/69092	Loss: 107.326
+41600/69092	Loss: 106.012
+44800/69092	Loss: 106.440
+48000/69092	Loss: 107.001
+51200/69092	Loss: 106.054
+54400/69092	Loss: 106.745
+57600/69092	Loss: 106.697
+60800/69092	Loss: 107.612
+64000/69092	Loss: 106.268
+67200/69092	Loss: 107.344
+Training time 0:08:27.542186
+Epoch: 118 Average loss: 106.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 591)
+0/69092	Loss: 96.661
+3200/69092	Loss: 106.137
+6400/69092	Loss: 105.095
+9600/69092	Loss: 106.112
+12800/69092	Loss: 105.124
+16000/69092	Loss: 107.041
+19200/69092	Loss: 107.167
+22400/69092	Loss: 106.055
+25600/69092	Loss: 106.759
+28800/69092	Loss: 106.469
+32000/69092	Loss: 106.223
+35200/69092	Loss: 107.669
+38400/69092	Loss: 105.719
+41600/69092	Loss: 106.517
+44800/69092	Loss: 105.777
+48000/69092	Loss: 107.730
+51200/69092	Loss: 106.931
+54400/69092	Loss: 106.590
+57600/69092	Loss: 106.871
+60800/69092	Loss: 106.979
+64000/69092	Loss: 106.402
+67200/69092	Loss: 105.103
+Training time 0:08:28.363494
+Epoch: 119 Average loss: 106.44
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 592)
+0/69092	Loss: 113.644
+3200/69092	Loss: 106.551
+6400/69092	Loss: 104.861
+9600/69092	Loss: 106.265
+12800/69092	Loss: 105.388
+16000/69092	Loss: 106.465
+19200/69092	Loss: 105.612
+22400/69092	Loss: 109.600
+25600/69092	Loss: 107.627
+28800/69092	Loss: 105.646
+32000/69092	Loss: 105.520
+35200/69092	Loss: 104.602
+38400/69092	Loss: 105.231
+41600/69092	Loss: 106.590
+44800/69092	Loss: 105.713
+48000/69092	Loss: 106.131
+51200/69092	Loss: 107.068
+54400/69092	Loss: 105.567
+57600/69092	Loss: 106.380
+60800/69092	Loss: 106.401
+64000/69092	Loss: 107.425
+67200/69092	Loss: 107.170
+Training time 0:08:34.803348
+Epoch: 120 Average loss: 106.28
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 593)
+0/69092	Loss: 104.630
+3200/69092	Loss: 104.440
+6400/69092	Loss: 105.104
+9600/69092	Loss: 105.837
+12800/69092	Loss: 105.936
+16000/69092	Loss: 105.117
+19200/69092	Loss: 106.623
+22400/69092	Loss: 105.770
+25600/69092	Loss: 107.649
+28800/69092	Loss: 106.685
+32000/69092	Loss: 106.831
+35200/69092	Loss: 106.589
+38400/69092	Loss: 107.943
+41600/69092	Loss: 107.373
+44800/69092	Loss: 106.926
+48000/69092	Loss: 105.803
+51200/69092	Loss: 106.560
+54400/69092	Loss: 107.363
+57600/69092	Loss: 106.822
+60800/69092	Loss: 108.878
+64000/69092	Loss: 106.219
+67200/69092	Loss: 106.611
+Training time 0:08:14.919534
+Epoch: 121 Average loss: 106.55
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 594)
+0/69092	Loss: 101.315
+3200/69092	Loss: 105.890
+6400/69092	Loss: 105.370
+9600/69092	Loss: 107.407
+12800/69092	Loss: 105.891
+16000/69092	Loss: 104.991
+19200/69092	Loss: 106.024
+22400/69092	Loss: 107.245
+25600/69092	Loss: 106.381
+28800/69092	Loss: 106.326
+32000/69092	Loss: 105.435
+35200/69092	Loss: 107.826
+38400/69092	Loss: 106.359
+41600/69092	Loss: 106.437
+44800/69092	Loss: 106.346
+48000/69092	Loss: 106.349
+51200/69092	Loss: 106.990
+54400/69092	Loss: 106.704
+57600/69092	Loss: 107.567
+60800/69092	Loss: 107.675
+64000/69092	Loss: 106.474
+67200/69092	Loss: 105.417
+Training time 0:08:18.623811
+Epoch: 122 Average loss: 106.44
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 595)
+0/69092	Loss: 102.429
+3200/69092	Loss: 106.037
+6400/69092	Loss: 106.831
+9600/69092	Loss: 106.770
+12800/69092	Loss: 106.117
+16000/69092	Loss: 105.508
+19200/69092	Loss: 105.744
+22400/69092	Loss: 106.718
+25600/69092	Loss: 105.912
+28800/69092	Loss: 108.314
+32000/69092	Loss: 106.325
+35200/69092	Loss: 107.150
+38400/69092	Loss: 106.054
+41600/69092	Loss: 106.640
+44800/69092	Loss: 108.025
+48000/69092	Loss: 105.248
+51200/69092	Loss: 105.531
+54400/69092	Loss: 107.128
+57600/69092	Loss: 106.754
+60800/69092	Loss: 106.831
+64000/69092	Loss: 107.007
+67200/69092	Loss: 106.866
+Training time 0:08:30.658669
+Epoch: 123 Average loss: 106.54
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 596)
+0/69092	Loss: 107.835
+3200/69092	Loss: 106.623
+6400/69092	Loss: 106.246
+9600/69092	Loss: 107.522
+12800/69092	Loss: 106.709
+16000/69092	Loss: 107.464
+19200/69092	Loss: 105.407
+22400/69092	Loss: 105.617
+25600/69092	Loss: 106.054
+28800/69092	Loss: 106.538
+32000/69092	Loss: 106.082
+35200/69092	Loss: 106.230
+38400/69092	Loss: 106.589
+41600/69092	Loss: 106.343
+44800/69092	Loss: 105.836
+48000/69092	Loss: 106.071
+51200/69092	Loss: 105.857
+54400/69092	Loss: 104.746
+57600/69092	Loss: 107.207
+60800/69092	Loss: 105.396
+64000/69092	Loss: 107.155
+67200/69092	Loss: 107.643
+Training time 0:08:20.486913
+Epoch: 124 Average loss: 106.37
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 597)
+0/69092	Loss: 103.166
+3200/69092	Loss: 106.715
+6400/69092	Loss: 105.546
+9600/69092	Loss: 105.337
+12800/69092	Loss: 106.911
+16000/69092	Loss: 105.444
+19200/69092	Loss: 106.380
+22400/69092	Loss: 106.603
+25600/69092	Loss: 105.923
+28800/69092	Loss: 108.098
+32000/69092	Loss: 107.570
+35200/69092	Loss: 106.293
+38400/69092	Loss: 107.966
+41600/69092	Loss: 106.807
+44800/69092	Loss: 106.515
+48000/69092	Loss: 107.138
+51200/69092	Loss: 107.418
+54400/69092	Loss: 106.295
+57600/69092	Loss: 105.855
+60800/69092	Loss: 106.414
+64000/69092	Loss: 105.596
+67200/69092	Loss: 106.692
+Training time 0:08:17.332521
+Epoch: 125 Average loss: 106.53
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 598)
+0/69092	Loss: 105.111
+3200/69092	Loss: 104.476
+6400/69092	Loss: 106.249
+9600/69092	Loss: 105.327
+12800/69092	Loss: 106.027
+16000/69092	Loss: 105.614
+19200/69092	Loss: 107.485
+22400/69092	Loss: 105.200
+25600/69092	Loss: 107.388
+28800/69092	Loss: 106.803
+32000/69092	Loss: 104.665
+35200/69092	Loss: 105.369
+38400/69092	Loss: 106.338
+41600/69092	Loss: 107.317
+44800/69092	Loss: 105.720
+48000/69092	Loss: 105.836
+51200/69092	Loss: 107.443
+54400/69092	Loss: 106.583
+57600/69092	Loss: 106.481
+60800/69092	Loss: 107.986
+64000/69092	Loss: 106.785
+67200/69092	Loss: 109.144
+Training time 0:08:33.796142
+Epoch: 126 Average loss: 106.37
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 599)
+0/69092	Loss: 105.267
+3200/69092	Loss: 105.740
+6400/69092	Loss: 105.368
+9600/69092	Loss: 106.310
+12800/69092	Loss: 108.301
+16000/69092	Loss: 106.223
+19200/69092	Loss: 106.160
+22400/69092	Loss: 106.523
+25600/69092	Loss: 105.164
+28800/69092	Loss: 106.265
+32000/69092	Loss: 107.491
+35200/69092	Loss: 106.396
+38400/69092	Loss: 106.430
+41600/69092	Loss: 105.629
+44800/69092	Loss: 106.231
+48000/69092	Loss: 106.040
+51200/69092	Loss: 105.864
+54400/69092	Loss: 106.237
+57600/69092	Loss: 105.828
+60800/69092	Loss: 107.219
+64000/69092	Loss: 106.337
+67200/69092	Loss: 106.374
+Training time 0:08:25.077128
+Epoch: 127 Average loss: 106.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 600)
+0/69092	Loss: 109.431
+3200/69092	Loss: 105.668
+6400/69092	Loss: 107.004
+9600/69092	Loss: 108.074
+12800/69092	Loss: 107.686
+16000/69092	Loss: 106.271
+19200/69092	Loss: 105.931
+22400/69092	Loss: 106.594
+25600/69092	Loss: 107.101
+28800/69092	Loss: 106.281
+32000/69092	Loss: 105.554
+35200/69092	Loss: 105.083
+38400/69092	Loss: 106.437
+41600/69092	Loss: 105.270
+44800/69092	Loss: 106.243
+48000/69092	Loss: 106.977
+51200/69092	Loss: 105.794
+54400/69092	Loss: 106.586
+57600/69092	Loss: 106.681
+60800/69092	Loss: 105.542
+64000/69092	Loss: 108.228
+67200/69092	Loss: 105.383
+Training time 0:08:11.675960
+Epoch: 128 Average loss: 106.44
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 601)
+0/69092	Loss: 95.905
+3200/69092	Loss: 106.125
+6400/69092	Loss: 106.219
+9600/69092	Loss: 105.957
+12800/69092	Loss: 105.352
+16000/69092	Loss: 106.789
+19200/69092	Loss: 105.449
+22400/69092	Loss: 105.926
+25600/69092	Loss: 106.291
+28800/69092	Loss: 107.513
+32000/69092	Loss: 107.065
+35200/69092	Loss: 108.309
+38400/69092	Loss: 105.017
+41600/69092	Loss: 106.239
+44800/69092	Loss: 106.296
+48000/69092	Loss: 106.892
+51200/69092	Loss: 106.450
+54400/69092	Loss: 106.094
+57600/69092	Loss: 107.825
+60800/69092	Loss: 106.022
+64000/69092	Loss: 105.732
+67200/69092	Loss: 106.652
+Training time 0:08:21.033959
+Epoch: 129 Average loss: 106.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 602)
+0/69092	Loss: 104.252
+3200/69092	Loss: 107.029
+6400/69092	Loss: 106.802
+9600/69092	Loss: 106.794
+12800/69092	Loss: 106.811
+16000/69092	Loss: 106.363
+19200/69092	Loss: 104.865
+22400/69092	Loss: 106.846
+25600/69092	Loss: 105.222
+28800/69092	Loss: 107.828
+32000/69092	Loss: 105.689
+35200/69092	Loss: 106.731
+38400/69092	Loss: 106.298
+41600/69092	Loss: 106.902
+44800/69092	Loss: 106.351
+48000/69092	Loss: 106.622
+51200/69092	Loss: 106.934
+54400/69092	Loss: 106.261
+57600/69092	Loss: 106.321
+60800/69092	Loss: 106.988
+64000/69092	Loss: 105.036
+67200/69092	Loss: 104.902
+Training time 0:08:42.086068
+Epoch: 130 Average loss: 106.44
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 603)
+0/69092	Loss: 99.543
+3200/69092	Loss: 104.679
+6400/69092	Loss: 105.977
+9600/69092	Loss: 106.278
+12800/69092	Loss: 106.978
+16000/69092	Loss: 106.384
+19200/69092	Loss: 106.959
+22400/69092	Loss: 106.418
+25600/69092	Loss: 106.715
+28800/69092	Loss: 106.505
+32000/69092	Loss: 106.786
+35200/69092	Loss: 106.298
+38400/69092	Loss: 106.792
+41600/69092	Loss: 106.055
+44800/69092	Loss: 106.440
+48000/69092	Loss: 105.135
+51200/69092	Loss: 106.796
+54400/69092	Loss: 105.947
+57600/69092	Loss: 105.942
+60800/69092	Loss: 106.960
+64000/69092	Loss: 106.913
+67200/69092	Loss: 107.432
+Training time 0:08:16.324414
+Epoch: 131 Average loss: 106.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 604)
+0/69092	Loss: 105.038
+3200/69092	Loss: 107.183
+6400/69092	Loss: 105.946
+9600/69092	Loss: 106.588
+12800/69092	Loss: 105.127
+16000/69092	Loss: 107.115
+19200/69092	Loss: 106.682
+22400/69092	Loss: 105.415
+25600/69092	Loss: 106.875
+28800/69092	Loss: 107.723
+32000/69092	Loss: 107.636
+35200/69092	Loss: 105.725
+38400/69092	Loss: 107.405
+41600/69092	Loss: 105.711
+44800/69092	Loss: 106.147
+48000/69092	Loss: 104.095
+51200/69092	Loss: 105.742
+54400/69092	Loss: 105.099
+57600/69092	Loss: 105.718
+60800/69092	Loss: 106.787
+64000/69092	Loss: 106.759
+67200/69092	Loss: 107.464
+Training time 0:08:16.505574
+Epoch: 132 Average loss: 106.34
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 605)
+0/69092	Loss: 96.708
+3200/69092	Loss: 106.405
+6400/69092	Loss: 104.834
+9600/69092	Loss: 108.773
+12800/69092	Loss: 105.859
+16000/69092	Loss: 107.340
+19200/69092	Loss: 105.542
+22400/69092	Loss: 105.718
+25600/69092	Loss: 106.139
+28800/69092	Loss: 106.453
+32000/69092	Loss: 105.585
+35200/69092	Loss: 105.836
+38400/69092	Loss: 105.845
+41600/69092	Loss: 107.077
+44800/69092	Loss: 107.236
+48000/69092	Loss: 105.610
+51200/69092	Loss: 106.219
+54400/69092	Loss: 107.686
+57600/69092	Loss: 107.099
+60800/69092	Loss: 104.547
+64000/69092	Loss: 107.793
+67200/69092	Loss: 105.780
+Training time 0:08:39.826238
+Epoch: 133 Average loss: 106.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 606)
+0/69092	Loss: 99.716
+3200/69092	Loss: 106.593
+6400/69092	Loss: 106.744
+9600/69092	Loss: 106.524
+12800/69092	Loss: 105.361
+16000/69092	Loss: 106.144
+19200/69092	Loss: 106.262
+22400/69092	Loss: 105.060
+25600/69092	Loss: 105.970
+28800/69092	Loss: 106.904
+32000/69092	Loss: 106.427
+35200/69092	Loss: 106.735
+38400/69092	Loss: 107.290
+41600/69092	Loss: 105.280
+44800/69092	Loss: 107.943
+48000/69092	Loss: 106.406
+51200/69092	Loss: 105.800
+54400/69092	Loss: 105.467
+57600/69092	Loss: 106.627
+60800/69092	Loss: 107.227
+64000/69092	Loss: 105.814
+67200/69092	Loss: 106.085
+Training time 0:08:37.037833
+Epoch: 134 Average loss: 106.32
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 607)
+0/69092	Loss: 108.462
+3200/69092	Loss: 105.953
+6400/69092	Loss: 106.460
+9600/69092	Loss: 106.975
+12800/69092	Loss: 108.791
+16000/69092	Loss: 108.032
+19200/69092	Loss: 105.841
+22400/69092	Loss: 107.681
+25600/69092	Loss: 107.230
+28800/69092	Loss: 105.135
+32000/69092	Loss: 105.796
+35200/69092	Loss: 105.770
+38400/69092	Loss: 107.392
+41600/69092	Loss: 105.437
+44800/69092	Loss: 106.451
+48000/69092	Loss: 105.326
+51200/69092	Loss: 106.773
+54400/69092	Loss: 104.993
+57600/69092	Loss: 107.558
+60800/69092	Loss: 103.042
+64000/69092	Loss: 107.979
+67200/69092	Loss: 106.564
+Training time 0:08:08.090380
+Epoch: 135 Average loss: 106.44
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 608)
+0/69092	Loss: 101.914
+3200/69092	Loss: 106.167
+6400/69092	Loss: 106.149
+9600/69092	Loss: 107.780
+12800/69092	Loss: 106.658
+16000/69092	Loss: 107.444
+19200/69092	Loss: 106.102
+22400/69092	Loss: 105.142
+25600/69092	Loss: 106.027
+28800/69092	Loss: 104.446
+32000/69092	Loss: 107.230
+35200/69092	Loss: 106.812
+38400/69092	Loss: 106.766
+41600/69092	Loss: 106.461
+44800/69092	Loss: 107.803
+48000/69092	Loss: 107.616
+51200/69092	Loss: 106.551
+54400/69092	Loss: 106.260
+57600/69092	Loss: 106.447
+60800/69092	Loss: 107.337
+64000/69092	Loss: 105.952
+67200/69092	Loss: 104.934
+Training time 0:08:26.636746
+Epoch: 136 Average loss: 106.45
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 609)
+0/69092	Loss: 101.575
+3200/69092	Loss: 105.532
+6400/69092	Loss: 106.598
+9600/69092	Loss: 105.126
+12800/69092	Loss: 106.401
+16000/69092	Loss: 105.780
+19200/69092	Loss: 107.407
+22400/69092	Loss: 105.728
+25600/69092	Loss: 108.358
+28800/69092	Loss: 104.707
+32000/69092	Loss: 106.437
+35200/69092	Loss: 107.102
+38400/69092	Loss: 106.530
+41600/69092	Loss: 107.183
+44800/69092	Loss: 106.736
+48000/69092	Loss: 105.565
+51200/69092	Loss: 106.659
+54400/69092	Loss: 106.873
+57600/69092	Loss: 106.344
+60800/69092	Loss: 106.046
+64000/69092	Loss: 107.468
+67200/69092	Loss: 105.486
+Training time 0:08:34.403215
+Epoch: 137 Average loss: 106.38
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 610)
+0/69092	Loss: 107.156
+3200/69092	Loss: 106.627
+6400/69092	Loss: 106.269
+9600/69092	Loss: 106.492
+12800/69092	Loss: 105.058
+16000/69092	Loss: 106.726
+19200/69092	Loss: 106.069
+22400/69092	Loss: 105.511
+25600/69092	Loss: 107.677
+28800/69092	Loss: 107.636
+32000/69092	Loss: 104.413
+35200/69092	Loss: 106.052
+38400/69092	Loss: 106.223
+41600/69092	Loss: 106.668
+44800/69092	Loss: 106.102
+48000/69092	Loss: 104.982
+51200/69092	Loss: 106.572
+54400/69092	Loss: 107.873
+57600/69092	Loss: 106.456
+60800/69092	Loss: 107.378
+64000/69092	Loss: 107.214
+67200/69092	Loss: 104.788
+Training time 0:08:24.705983
+Epoch: 138 Average loss: 106.36
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 611)
+0/69092	Loss: 103.643
+3200/69092	Loss: 106.194
+6400/69092	Loss: 104.763
+9600/69092	Loss: 106.033
+12800/69092	Loss: 106.947
+16000/69092	Loss: 106.770
+19200/69092	Loss: 107.186
+22400/69092	Loss: 106.170
+25600/69092	Loss: 106.241
+28800/69092	Loss: 107.349
+32000/69092	Loss: 106.452
+35200/69092	Loss: 105.886
+38400/69092	Loss: 106.320
+41600/69092	Loss: 107.577
+44800/69092	Loss: 106.197
+48000/69092	Loss: 105.279
+51200/69092	Loss: 106.271
+54400/69092	Loss: 106.254
+57600/69092	Loss: 105.631
+60800/69092	Loss: 104.857
+64000/69092	Loss: 106.817
+67200/69092	Loss: 106.352
+Training time 0:08:12.999556
+Epoch: 139 Average loss: 106.25
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 612)
+0/69092	Loss: 113.564
+3200/69092	Loss: 105.412
+6400/69092	Loss: 108.021
+9600/69092	Loss: 106.346
+12800/69092	Loss: 106.656
+16000/69092	Loss: 105.474
+19200/69092	Loss: 105.172
+22400/69092	Loss: 107.173
+25600/69092	Loss: 105.552
+28800/69092	Loss: 107.890
+32000/69092	Loss: 106.278
+35200/69092	Loss: 106.499
+38400/69092	Loss: 106.431
+41600/69092	Loss: 106.754
+44800/69092	Loss: 105.029
+48000/69092	Loss: 106.255
+51200/69092	Loss: 106.492
+54400/69092	Loss: 106.695
+57600/69092	Loss: 106.687
+60800/69092	Loss: 105.782
+64000/69092	Loss: 107.154
+67200/69092	Loss: 105.823
+Training time 0:08:42.226282
+Epoch: 140 Average loss: 106.38
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 613)
+0/69092	Loss: 111.642
+3200/69092	Loss: 106.180
+6400/69092	Loss: 107.641
+9600/69092	Loss: 106.141
+12800/69092	Loss: 106.160
+16000/69092	Loss: 105.968
+19200/69092	Loss: 105.013
+22400/69092	Loss: 106.176
+25600/69092	Loss: 107.007
+28800/69092	Loss: 104.581
+32000/69092	Loss: 106.638
+35200/69092	Loss: 105.095
+38400/69092	Loss: 107.453
+41600/69092	Loss: 106.475
+44800/69092	Loss: 106.125
+48000/69092	Loss: 104.305
+51200/69092	Loss: 106.699
+54400/69092	Loss: 106.323
+57600/69092	Loss: 106.933
+60800/69092	Loss: 105.928
+64000/69092	Loss: 107.140
+67200/69092	Loss: 105.720
+Training time 0:08:37.687024
+Epoch: 141 Average loss: 106.23
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 614)
+0/69092	Loss: 108.796
+3200/69092	Loss: 107.468
+6400/69092	Loss: 105.921
+9600/69092	Loss: 106.658
+12800/69092	Loss: 106.459
+16000/69092	Loss: 106.300
+19200/69092	Loss: 106.444
+22400/69092	Loss: 107.141
+25600/69092	Loss: 106.612
+28800/69092	Loss: 107.921
+32000/69092	Loss: 105.659
+35200/69092	Loss: 105.728
+38400/69092	Loss: 106.242
+41600/69092	Loss: 106.881
+44800/69092	Loss: 106.298
+48000/69092	Loss: 106.092
+51200/69092	Loss: 106.532
+54400/69092	Loss: 104.145
+57600/69092	Loss: 106.085
+60800/69092	Loss: 107.060
+64000/69092	Loss: 105.750
+67200/69092	Loss: 106.540
+Training time 0:08:22.859666
+Epoch: 142 Average loss: 106.39
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 615)
+0/69092	Loss: 111.678
+3200/69092	Loss: 106.834
+6400/69092	Loss: 106.227
+9600/69092	Loss: 107.401
+12800/69092	Loss: 105.634
+16000/69092	Loss: 106.606
+19200/69092	Loss: 105.371
+22400/69092	Loss: 106.523
+25600/69092	Loss: 106.470
+28800/69092	Loss: 106.625
+32000/69092	Loss: 106.423
+35200/69092	Loss: 106.719
+38400/69092	Loss: 106.401
+41600/69092	Loss: 108.100
+44800/69092	Loss: 105.143
+48000/69092	Loss: 105.925
+51200/69092	Loss: 106.185
+54400/69092	Loss: 107.011
+57600/69092	Loss: 107.522
+60800/69092	Loss: 105.884
+64000/69092	Loss: 106.463
+67200/69092	Loss: 105.846
+Training time 0:08:25.775306
+Epoch: 143 Average loss: 106.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 616)
+0/69092	Loss: 103.589
+3200/69092	Loss: 106.559
+6400/69092	Loss: 105.287
+9600/69092	Loss: 105.772
+12800/69092	Loss: 106.219
+16000/69092	Loss: 107.691
+19200/69092	Loss: 105.949
+22400/69092	Loss: 107.319
+25600/69092	Loss: 106.698
+28800/69092	Loss: 107.620
+32000/69092	Loss: 106.050
+35200/69092	Loss: 106.500
+38400/69092	Loss: 106.633
+41600/69092	Loss: 106.670
+44800/69092	Loss: 106.506
+48000/69092	Loss: 105.151
+51200/69092	Loss: 106.134
+54400/69092	Loss: 105.899
+57600/69092	Loss: 106.461
+60800/69092	Loss: 109.485
+64000/69092	Loss: 104.659
+67200/69092	Loss: 105.670
+Training time 0:08:38.139192
+Epoch: 144 Average loss: 106.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 617)
+0/69092	Loss: 107.307
+3200/69092	Loss: 106.609
+6400/69092	Loss: 107.364
+9600/69092	Loss: 106.176
+12800/69092	Loss: 105.491
+16000/69092	Loss: 104.753
+19200/69092	Loss: 107.109
+22400/69092	Loss: 106.196
+25600/69092	Loss: 107.115
+28800/69092	Loss: 107.063
+32000/69092	Loss: 105.674
+35200/69092	Loss: 106.065
+38400/69092	Loss: 106.408
+41600/69092	Loss: 106.739
+44800/69092	Loss: 105.355
+48000/69092	Loss: 106.797
+51200/69092	Loss: 106.939
+54400/69092	Loss: 107.264
+57600/69092	Loss: 105.452
+60800/69092	Loss: 105.418
+64000/69092	Loss: 106.218
+67200/69092	Loss: 106.495
+Training time 0:08:43.183328
+Epoch: 145 Average loss: 106.34
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 618)
+0/69092	Loss: 118.166
+3200/69092	Loss: 108.248
+6400/69092	Loss: 105.946
+9600/69092	Loss: 106.232
+12800/69092	Loss: 106.777
+16000/69092	Loss: 107.487
+19200/69092	Loss: 105.836
+22400/69092	Loss: 106.183
+25600/69092	Loss: 104.862
+28800/69092	Loss: 103.776
+32000/69092	Loss: 104.604
+35200/69092	Loss: 105.622
+38400/69092	Loss: 106.399
+41600/69092	Loss: 106.023
+44800/69092	Loss: 105.882
+48000/69092	Loss: 108.274
+51200/69092	Loss: 107.866
+54400/69092	Loss: 107.289
+57600/69092	Loss: 106.942
+60800/69092	Loss: 106.512
+64000/69092	Loss: 105.591
+67200/69092	Loss: 105.986
+Training time 0:08:18.399874
+Epoch: 146 Average loss: 106.32
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 619)
+0/69092	Loss: 91.033
+3200/69092	Loss: 105.303
+6400/69092	Loss: 105.894
+9600/69092	Loss: 104.790
+12800/69092	Loss: 106.725
+16000/69092	Loss: 107.019
+19200/69092	Loss: 105.843
+22400/69092	Loss: 107.518
+25600/69092	Loss: 106.697
+28800/69092	Loss: 107.069
+32000/69092	Loss: 106.438
+35200/69092	Loss: 105.452
+38400/69092	Loss: 105.375
+41600/69092	Loss: 105.868
+44800/69092	Loss: 106.021
+48000/69092	Loss: 106.487
+51200/69092	Loss: 106.224
+54400/69092	Loss: 105.844
+57600/69092	Loss: 107.270
+60800/69092	Loss: 106.462
+64000/69092	Loss: 108.079
+67200/69092	Loss: 106.537
+Training time 0:08:15.985489
+Epoch: 147 Average loss: 106.36
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 620)
+0/69092	Loss: 103.090
+3200/69092	Loss: 107.557
+6400/69092	Loss: 106.116
+9600/69092	Loss: 105.086
+12800/69092	Loss: 105.961
+16000/69092	Loss: 105.557
+19200/69092	Loss: 105.440
+22400/69092	Loss: 106.793
+25600/69092	Loss: 107.227
+28800/69092	Loss: 108.228
+32000/69092	Loss: 107.334
+35200/69092	Loss: 106.873
+38400/69092	Loss: 106.799
+41600/69092	Loss: 105.144
+44800/69092	Loss: 106.008
+48000/69092	Loss: 106.832
+51200/69092	Loss: 104.217
+54400/69092	Loss: 106.799
+57600/69092	Loss: 104.853
+60800/69092	Loss: 106.075
+64000/69092	Loss: 104.721
+67200/69092	Loss: 106.609
+Training time 0:08:34.452690
+Epoch: 148 Average loss: 106.16
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 621)
+0/69092	Loss: 103.947
+3200/69092	Loss: 107.375
+6400/69092	Loss: 106.868
+9600/69092	Loss: 106.013
+12800/69092	Loss: 106.012
+16000/69092	Loss: 105.344
+19200/69092	Loss: 104.824
+22400/69092	Loss: 106.123
+25600/69092	Loss: 106.322
+28800/69092	Loss: 105.007
+32000/69092	Loss: 107.555
+35200/69092	Loss: 107.611
+38400/69092	Loss: 104.756
+41600/69092	Loss: 106.276
+44800/69092	Loss: 106.279
+48000/69092	Loss: 107.064
+51200/69092	Loss: 106.648
+54400/69092	Loss: 106.109
+57600/69092	Loss: 105.015
+60800/69092	Loss: 107.683
+64000/69092	Loss: 106.661
+67200/69092	Loss: 107.035
+Training time 0:08:16.543387
+Epoch: 149 Average loss: 106.31
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 622)
+0/69092	Loss: 114.599
+3200/69092	Loss: 106.866
+6400/69092	Loss: 105.930
+9600/69092	Loss: 105.977
+12800/69092	Loss: 106.724
+16000/69092	Loss: 105.056
+19200/69092	Loss: 107.604
+22400/69092	Loss: 106.229
+25600/69092	Loss: 105.807
+28800/69092	Loss: 105.189
+32000/69092	Loss: 105.421
+35200/69092	Loss: 105.684
+38400/69092	Loss: 106.346
+41600/69092	Loss: 106.292
+44800/69092	Loss: 106.443
+48000/69092	Loss: 105.208
+51200/69092	Loss: 106.628
+54400/69092	Loss: 107.195
+57600/69092	Loss: 106.429
+60800/69092	Loss: 106.738
+64000/69092	Loss: 106.217
+67200/69092	Loss: 104.911
+Training time 0:08:22.248470
+Epoch: 150 Average loss: 106.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 623)
+0/69092	Loss: 104.065
+3200/69092	Loss: 105.674
+6400/69092	Loss: 105.507
+9600/69092	Loss: 107.979
+12800/69092	Loss: 105.907
+16000/69092	Loss: 105.868
+19200/69092	Loss: 104.409
+22400/69092	Loss: 107.326
+25600/69092	Loss: 106.426
+28800/69092	Loss: 105.926
+32000/69092	Loss: 105.391
+35200/69092	Loss: 106.836
+38400/69092	Loss: 106.695
+41600/69092	Loss: 107.574
+44800/69092	Loss: 105.841
+48000/69092	Loss: 106.130
+51200/69092	Loss: 107.225
+54400/69092	Loss: 106.852
+57600/69092	Loss: 107.106
+60800/69092	Loss: 107.048
+64000/69092	Loss: 107.266
+67200/69092	Loss: 105.593
+Training time 0:08:31.629004
+Epoch: 151 Average loss: 106.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 624)
+0/69092	Loss: 101.019
+3200/69092	Loss: 107.271
+6400/69092	Loss: 106.377
+9600/69092	Loss: 104.875
+12800/69092	Loss: 106.455
+16000/69092	Loss: 105.267
+19200/69092	Loss: 106.775
+22400/69092	Loss: 106.340
+25600/69092	Loss: 107.269
+28800/69092	Loss: 108.377
+32000/69092	Loss: 108.174
+35200/69092	Loss: 106.464
+38400/69092	Loss: 107.017
+41600/69092	Loss: 105.652
+44800/69092	Loss: 106.126
+48000/69092	Loss: 107.427
+51200/69092	Loss: 106.495
+54400/69092	Loss: 105.070
+57600/69092	Loss: 105.258
+60800/69092	Loss: 106.094
+64000/69092	Loss: 103.244
+67200/69092	Loss: 107.117
+Training time 0:08:38.422099
+Epoch: 152 Average loss: 106.36
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 625)
+0/69092	Loss: 104.087
+3200/69092	Loss: 104.994
+6400/69092	Loss: 106.283
+9600/69092	Loss: 107.426
+12800/69092	Loss: 107.016
+16000/69092	Loss: 105.175
+19200/69092	Loss: 105.616
+22400/69092	Loss: 106.631
+25600/69092	Loss: 106.958
+28800/69092	Loss: 106.397
+32000/69092	Loss: 105.247
+35200/69092	Loss: 103.924
+38400/69092	Loss: 105.895
+41600/69092	Loss: 106.890
+44800/69092	Loss: 107.576
+48000/69092	Loss: 107.275
+51200/69092	Loss: 106.932
+54400/69092	Loss: 107.117
+57600/69092	Loss: 106.378
+60800/69092	Loss: 106.298
+64000/69092	Loss: 107.264
+67200/69092	Loss: 106.644
+Training time 0:08:25.353461
+Epoch: 153 Average loss: 106.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 626)
+0/69092	Loss: 112.910
+3200/69092	Loss: 106.849
+6400/69092	Loss: 107.942
+9600/69092	Loss: 105.090
+12800/69092	Loss: 104.768
+16000/69092	Loss: 107.669
+19200/69092	Loss: 109.046
+22400/69092	Loss: 104.983
+25600/69092	Loss: 105.862
+28800/69092	Loss: 104.873
+32000/69092	Loss: 104.740
+35200/69092	Loss: 107.301
+38400/69092	Loss: 108.264
+41600/69092	Loss: 106.906
+44800/69092	Loss: 106.016
+48000/69092	Loss: 105.364
+51200/69092	Loss: 105.209
+54400/69092	Loss: 107.008
+57600/69092	Loss: 107.327
+60800/69092	Loss: 105.538
+64000/69092	Loss: 105.477
+67200/69092	Loss: 107.230
+Training time 0:08:13.558508
+Epoch: 154 Average loss: 106.35
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 627)
+0/69092	Loss: 112.831
+3200/69092	Loss: 105.354
+6400/69092	Loss: 105.560
+9600/69092	Loss: 107.356
+12800/69092	Loss: 106.602
+16000/69092	Loss: 106.148
+19200/69092	Loss: 106.547
+22400/69092	Loss: 107.677
+25600/69092	Loss: 106.524
+28800/69092	Loss: 105.977
+32000/69092	Loss: 105.667
+35200/69092	Loss: 106.275
+38400/69092	Loss: 105.988
+41600/69092	Loss: 105.503
+44800/69092	Loss: 106.181
+48000/69092	Loss: 105.640
+51200/69092	Loss: 106.136
+54400/69092	Loss: 106.349
+57600/69092	Loss: 106.623
+60800/69092	Loss: 107.047
+64000/69092	Loss: 106.716
+67200/69092	Loss: 106.919
+Training time 0:08:39.579683
+Epoch: 155 Average loss: 106.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 628)
+0/69092	Loss: 106.791
+3200/69092	Loss: 105.759
+6400/69092	Loss: 106.296
+9600/69092	Loss: 106.131
+12800/69092	Loss: 106.034
+16000/69092	Loss: 108.019
+19200/69092	Loss: 106.410
+22400/69092	Loss: 105.982
+25600/69092	Loss: 108.167
+28800/69092	Loss: 104.943
+32000/69092	Loss: 106.737
+35200/69092	Loss: 107.003
+38400/69092	Loss: 106.389
+41600/69092	Loss: 106.474
+44800/69092	Loss: 108.025
+48000/69092	Loss: 105.631
+51200/69092	Loss: 105.088
+54400/69092	Loss: 105.338
+57600/69092	Loss: 107.064
+60800/69092	Loss: 106.084
+64000/69092	Loss: 106.163
+67200/69092	Loss: 107.051
+Training time 0:08:21.832192
+Epoch: 156 Average loss: 106.41
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 629)
+0/69092	Loss: 123.707
+3200/69092	Loss: 107.526
+6400/69092	Loss: 106.226
+9600/69092	Loss: 105.490
+12800/69092	Loss: 106.645
+16000/69092	Loss: 106.121
+19200/69092	Loss: 105.477
+22400/69092	Loss: 105.842
+25600/69092	Loss: 105.931
+28800/69092	Loss: 104.568
+32000/69092	Loss: 105.756
+35200/69092	Loss: 107.412
+38400/69092	Loss: 105.123
+41600/69092	Loss: 105.608
+44800/69092	Loss: 107.481
+48000/69092	Loss: 106.902
+51200/69092	Loss: 105.679
+54400/69092	Loss: 107.386
+57600/69092	Loss: 105.921
+60800/69092	Loss: 107.146
+64000/69092	Loss: 107.076
+67200/69092	Loss: 106.559
+Training time 0:08:08.376544
+Epoch: 157 Average loss: 106.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 630)
+0/69092	Loss: 111.108
+3200/69092	Loss: 106.194
+6400/69092	Loss: 105.758
+9600/69092	Loss: 107.273
+12800/69092	Loss: 105.600
+16000/69092	Loss: 107.264
+19200/69092	Loss: 107.281
+22400/69092	Loss: 106.857
+25600/69092	Loss: 105.594
+28800/69092	Loss: 106.675
+32000/69092	Loss: 105.002
+35200/69092	Loss: 107.134
+38400/69092	Loss: 104.871
+41600/69092	Loss: 105.858
+44800/69092	Loss: 104.821
+48000/69092	Loss: 107.591
+51200/69092	Loss: 104.520
+54400/69092	Loss: 106.111
+57600/69092	Loss: 105.793
+60800/69092	Loss: 105.154
+64000/69092	Loss: 106.807
+67200/69092	Loss: 105.789
+Training time 0:08:21.520761
+Epoch: 158 Average loss: 106.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 631)
+0/69092	Loss: 113.612
+3200/69092	Loss: 107.260
+6400/69092	Loss: 106.513
+9600/69092	Loss: 104.958
+12800/69092	Loss: 106.151
+16000/69092	Loss: 106.089
+19200/69092	Loss: 105.652
+22400/69092	Loss: 105.481
+25600/69092	Loss: 105.723
+28800/69092	Loss: 105.451
+32000/69092	Loss: 108.005
+35200/69092	Loss: 106.453
+38400/69092	Loss: 106.414
+41600/69092	Loss: 105.789
+44800/69092	Loss: 106.162
+48000/69092	Loss: 104.757
+51200/69092	Loss: 107.299
+54400/69092	Loss: 104.893
+57600/69092	Loss: 107.049
+60800/69092	Loss: 105.553
+64000/69092	Loss: 106.189
+67200/69092	Loss: 106.842
+Training time 0:08:37.048002
+Epoch: 159 Average loss: 106.16
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 632)
+0/69092	Loss: 99.175
+3200/69092	Loss: 105.730
+6400/69092	Loss: 104.835
+9600/69092	Loss: 106.859
+12800/69092	Loss: 106.440
+16000/69092	Loss: 105.655
+19200/69092	Loss: 107.942
+22400/69092	Loss: 106.235
+25600/69092	Loss: 106.242
+28800/69092	Loss: 107.423
+32000/69092	Loss: 103.999
+35200/69092	Loss: 103.961
+38400/69092	Loss: 105.326
+41600/69092	Loss: 106.280
+44800/69092	Loss: 107.865
+48000/69092	Loss: 106.718
+51200/69092	Loss: 106.364
+54400/69092	Loss: 106.402
+57600/69092	Loss: 106.456
+60800/69092	Loss: 106.265
+64000/69092	Loss: 106.396
+67200/69092	Loss: 105.726
+Training time 0:08:19.228089
+Epoch: 160 Average loss: 106.15
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 633)
+0/69092	Loss: 101.499
+3200/69092	Loss: 106.536
+6400/69092	Loss: 104.710
+9600/69092	Loss: 105.313
+12800/69092	Loss: 106.060
+16000/69092	Loss: 105.105
+19200/69092	Loss: 105.808
+22400/69092	Loss: 105.693
+25600/69092	Loss: 105.092
+28800/69092	Loss: 104.230
+32000/69092	Loss: 106.200
+35200/69092	Loss: 107.685
+38400/69092	Loss: 107.772
+41600/69092	Loss: 106.738
+44800/69092	Loss: 106.580
+48000/69092	Loss: 107.038
+51200/69092	Loss: 104.568
+54400/69092	Loss: 105.250
+57600/69092	Loss: 108.956
+60800/69092	Loss: 107.426
+64000/69092	Loss: 108.206
+67200/69092	Loss: 107.729
+Training time 0:08:27.473838
+Epoch: 161 Average loss: 106.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 634)
+0/69092	Loss: 103.104
+3200/69092	Loss: 105.581
+6400/69092	Loss: 107.549
+9600/69092	Loss: 106.213
+12800/69092	Loss: 106.159
+16000/69092	Loss: 106.786
+19200/69092	Loss: 106.404
+22400/69092	Loss: 106.502
+25600/69092	Loss: 105.334
+28800/69092	Loss: 105.553
+32000/69092	Loss: 106.382
+35200/69092	Loss: 106.532
+38400/69092	Loss: 107.053
+41600/69092	Loss: 106.794
+44800/69092	Loss: 105.866
+48000/69092	Loss: 103.564
+51200/69092	Loss: 107.239
+54400/69092	Loss: 105.693
+57600/69092	Loss: 108.131
+60800/69092	Loss: 106.163
+64000/69092	Loss: 107.144
+67200/69092	Loss: 105.549
+Training time 0:08:32.504036
+Epoch: 162 Average loss: 106.34
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 635)
+0/69092	Loss: 114.729
+3200/69092	Loss: 105.933
+6400/69092	Loss: 106.045
+9600/69092	Loss: 105.880
+12800/69092	Loss: 108.005
+16000/69092	Loss: 107.339
+19200/69092	Loss: 106.500
+22400/69092	Loss: 107.307
+25600/69092	Loss: 105.699
+28800/69092	Loss: 105.272
+32000/69092	Loss: 106.882
+35200/69092	Loss: 106.098
+38400/69092	Loss: 106.675
+41600/69092	Loss: 105.165
+44800/69092	Loss: 106.053
+48000/69092	Loss: 106.396
+51200/69092	Loss: 106.518
+54400/69092	Loss: 106.671
+57600/69092	Loss: 104.725
+60800/69092	Loss: 106.148
+64000/69092	Loss: 106.251
+67200/69092	Loss: 107.675
+Training time 0:08:29.995960
+Epoch: 163 Average loss: 106.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 636)
+0/69092	Loss: 113.876
+3200/69092	Loss: 106.557
+6400/69092	Loss: 105.789
+9600/69092	Loss: 106.629
+12800/69092	Loss: 105.523
+16000/69092	Loss: 105.887
+19200/69092	Loss: 106.711
+22400/69092	Loss: 106.003
+25600/69092	Loss: 106.695
+28800/69092	Loss: 106.786
+32000/69092	Loss: 105.858
+35200/69092	Loss: 107.559
+38400/69092	Loss: 107.610
+41600/69092	Loss: 106.049
+44800/69092	Loss: 106.416
+48000/69092	Loss: 105.589
+51200/69092	Loss: 107.041
+54400/69092	Loss: 106.527
+57600/69092	Loss: 107.595
+60800/69092	Loss: 105.678
+64000/69092	Loss: 104.753
+67200/69092	Loss: 105.369
+Training time 0:08:03.835941
+Epoch: 164 Average loss: 106.28
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 637)
+0/69092	Loss: 112.605
+3200/69092	Loss: 105.648
+6400/69092	Loss: 105.620
+9600/69092	Loss: 103.891
+12800/69092	Loss: 106.706
+16000/69092	Loss: 107.004
+19200/69092	Loss: 104.920
+22400/69092	Loss: 109.076
+25600/69092	Loss: 105.552
+28800/69092	Loss: 105.813
+32000/69092	Loss: 105.789
+35200/69092	Loss: 105.230
+38400/69092	Loss: 105.678
+41600/69092	Loss: 106.788
+44800/69092	Loss: 106.565
+48000/69092	Loss: 105.815
+51200/69092	Loss: 107.664
+54400/69092	Loss: 105.155
+57600/69092	Loss: 107.443
+60800/69092	Loss: 106.976
+64000/69092	Loss: 104.528
+67200/69092	Loss: 107.764
+Training time 0:08:33.306799
+Epoch: 165 Average loss: 106.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 638)
+0/69092	Loss: 110.511
+3200/69092	Loss: 105.141
+6400/69092	Loss: 106.911
+9600/69092	Loss: 106.732
+12800/69092	Loss: 107.680
+16000/69092	Loss: 105.404
+19200/69092	Loss: 105.394
+22400/69092	Loss: 106.448
+25600/69092	Loss: 106.402
+28800/69092	Loss: 106.346
+32000/69092	Loss: 108.766
+35200/69092	Loss: 103.543
+38400/69092	Loss: 105.832
+41600/69092	Loss: 106.723
+44800/69092	Loss: 105.981
+48000/69092	Loss: 106.328
+51200/69092	Loss: 107.691
+54400/69092	Loss: 107.114
+57600/69092	Loss: 105.868
+60800/69092	Loss: 103.995
+64000/69092	Loss: 107.094
+67200/69092	Loss: 104.498
+Training time 0:08:25.923331
+Epoch: 166 Average loss: 106.25
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 639)
+0/69092	Loss: 119.198
+3200/69092	Loss: 106.737
+6400/69092	Loss: 105.527
+9600/69092	Loss: 107.486
+12800/69092	Loss: 105.919
+16000/69092	Loss: 107.945
+19200/69092	Loss: 105.816
+22400/69092	Loss: 106.888
+25600/69092	Loss: 105.539
+28800/69092	Loss: 105.991
+32000/69092	Loss: 105.468
+35200/69092	Loss: 107.024
+38400/69092	Loss: 107.114
+41600/69092	Loss: 105.403
+44800/69092	Loss: 105.742
+48000/69092	Loss: 105.142
+51200/69092	Loss: 107.458
+54400/69092	Loss: 105.856
+57600/69092	Loss: 107.611
+60800/69092	Loss: 105.448
+64000/69092	Loss: 105.525
+67200/69092	Loss: 106.793
+Training time 0:08:21.650338
+Epoch: 167 Average loss: 106.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 640)
+0/69092	Loss: 112.421
+3200/69092	Loss: 105.626
+6400/69092	Loss: 106.442
+9600/69092	Loss: 106.056
+12800/69092	Loss: 105.935
+16000/69092	Loss: 104.975
+19200/69092	Loss: 106.532
+22400/69092	Loss: 108.227
+25600/69092	Loss: 107.582
+28800/69092	Loss: 107.706
+32000/69092	Loss: 108.707
+35200/69092	Loss: 106.561
+38400/69092	Loss: 106.332
+41600/69092	Loss: 106.955
+44800/69092	Loss: 106.615
+48000/69092	Loss: 105.365
+51200/69092	Loss: 106.889
+54400/69092	Loss: 104.038
+57600/69092	Loss: 106.275
+60800/69092	Loss: 106.115
+64000/69092	Loss: 105.630
+67200/69092	Loss: 105.237
+Training time 0:08:17.934448
+Epoch: 168 Average loss: 106.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 641)
+0/69092	Loss: 119.286
+3200/69092	Loss: 105.703
+6400/69092	Loss: 104.759
+9600/69092	Loss: 106.928
+12800/69092	Loss: 106.573
+16000/69092	Loss: 105.933
+19200/69092	Loss: 105.553
+22400/69092	Loss: 104.980
+25600/69092	Loss: 106.173
+28800/69092	Loss: 107.519
+32000/69092	Loss: 105.865
+35200/69092	Loss: 105.603
+38400/69092	Loss: 106.265
+41600/69092	Loss: 104.790
+44800/69092	Loss: 107.345
+48000/69092	Loss: 106.041
+51200/69092	Loss: 106.506
+54400/69092	Loss: 106.642
+57600/69092	Loss: 107.894
+60800/69092	Loss: 106.745
+64000/69092	Loss: 105.603
+67200/69092	Loss: 105.327
+Training time 0:08:29.840809
+Epoch: 169 Average loss: 106.20
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 642)
+0/69092	Loss: 111.407
+3200/69092	Loss: 105.978
+6400/69092	Loss: 106.141
+9600/69092	Loss: 105.839
+12800/69092	Loss: 106.573
+16000/69092	Loss: 104.863
+19200/69092	Loss: 106.344
+22400/69092	Loss: 106.114
+25600/69092	Loss: 105.481
+28800/69092	Loss: 105.784
+32000/69092	Loss: 105.421
+35200/69092	Loss: 104.894
+38400/69092	Loss: 105.867
+41600/69092	Loss: 106.710
+44800/69092	Loss: 106.871
+48000/69092	Loss: 106.657
+51200/69092	Loss: 104.890
+54400/69092	Loss: 106.857
+57600/69092	Loss: 107.301
+60800/69092	Loss: 107.939
+64000/69092	Loss: 106.845
+67200/69092	Loss: 107.290
+Training time 0:08:29.747814
+Epoch: 170 Average loss: 106.27
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 643)
+0/69092	Loss: 115.918
+3200/69092	Loss: 105.632
+6400/69092	Loss: 106.979
+9600/69092	Loss: 107.617
+12800/69092	Loss: 104.661
+16000/69092	Loss: 105.708
+19200/69092	Loss: 106.840
+22400/69092	Loss: 106.674
+25600/69092	Loss: 106.787
+28800/69092	Loss: 106.033
+32000/69092	Loss: 104.585
+35200/69092	Loss: 106.252
+38400/69092	Loss: 105.477
+41600/69092	Loss: 106.333
+44800/69092	Loss: 106.297
+48000/69092	Loss: 107.628
+51200/69092	Loss: 105.891
+54400/69092	Loss: 106.921
+57600/69092	Loss: 106.832
+60800/69092	Loss: 106.293
+64000/69092	Loss: 104.330
+67200/69092	Loss: 107.470
+Training time 0:08:14.275672
+Epoch: 171 Average loss: 106.25
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 644)
+0/69092	Loss: 114.956
+3200/69092	Loss: 106.346
+6400/69092	Loss: 105.487
+9600/69092	Loss: 104.452
+12800/69092	Loss: 104.639
+16000/69092	Loss: 106.510
+19200/69092	Loss: 106.035
+22400/69092	Loss: 105.798
+25600/69092	Loss: 105.150
+28800/69092	Loss: 106.474
+32000/69092	Loss: 105.409
+35200/69092	Loss: 106.078
+38400/69092	Loss: 105.853
+41600/69092	Loss: 105.997
+44800/69092	Loss: 106.067
+48000/69092	Loss: 107.257
+51200/69092	Loss: 106.668
+54400/69092	Loss: 105.918
+57600/69092	Loss: 106.297
+60800/69092	Loss: 107.519
+64000/69092	Loss: 106.230
+67200/69092	Loss: 107.361
+Training time 0:08:20.688106
+Epoch: 172 Average loss: 106.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 645)
+0/69092	Loss: 113.568
+3200/69092	Loss: 105.951
+6400/69092	Loss: 106.892
+9600/69092	Loss: 105.094
+12800/69092	Loss: 105.464
+16000/69092	Loss: 106.138
+19200/69092	Loss: 105.782
+22400/69092	Loss: 107.610
+25600/69092	Loss: 104.289
+28800/69092	Loss: 106.648
+32000/69092	Loss: 106.911
+35200/69092	Loss: 106.891
+38400/69092	Loss: 107.523
+41600/69092	Loss: 107.910
+44800/69092	Loss: 106.836
+48000/69092	Loss: 106.664
+51200/69092	Loss: 107.208
+54400/69092	Loss: 104.447
+57600/69092	Loss: 106.562
+60800/69092	Loss: 105.034
+64000/69092	Loss: 105.915
+67200/69092	Loss: 106.870
+Training time 0:08:42.419094
+Epoch: 173 Average loss: 106.28
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 646)
+0/69092	Loss: 106.192
+3200/69092	Loss: 106.345
+6400/69092	Loss: 105.661
+9600/69092	Loss: 105.997
+12800/69092	Loss: 106.460
+16000/69092	Loss: 104.251
+19200/69092	Loss: 105.373
+22400/69092	Loss: 106.509
+25600/69092	Loss: 106.460
+28800/69092	Loss: 105.586
+32000/69092	Loss: 106.393
+35200/69092	Loss: 106.056
+38400/69092	Loss: 106.845
+41600/69092	Loss: 105.712
+44800/69092	Loss: 106.367
+48000/69092	Loss: 106.048
+51200/69092	Loss: 106.720
+54400/69092	Loss: 106.660
+57600/69092	Loss: 106.654
+60800/69092	Loss: 105.900
+64000/69092	Loss: 107.156
+67200/69092	Loss: 108.004
+Training time 0:08:36.606066
+Epoch: 174 Average loss: 106.26
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 647)
+0/69092	Loss: 101.648
+3200/69092	Loss: 106.331
+6400/69092	Loss: 105.194
+9600/69092	Loss: 105.898
+12800/69092	Loss: 106.454
+16000/69092	Loss: 105.316
+19200/69092	Loss: 105.719
+22400/69092	Loss: 105.500
+25600/69092	Loss: 105.375
+28800/69092	Loss: 105.662
+32000/69092	Loss: 107.120
+35200/69092	Loss: 107.355
+38400/69092	Loss: 105.944
+41600/69092	Loss: 106.107
+44800/69092	Loss: 105.893
+48000/69092	Loss: 107.473
+51200/69092	Loss: 104.945
+54400/69092	Loss: 107.269
+57600/69092	Loss: 107.693
+60800/69092	Loss: 105.258
+64000/69092	Loss: 107.064
+67200/69092	Loss: 106.537
+Training time 0:08:24.032807
+Epoch: 175 Average loss: 106.25
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 648)
+0/69092	Loss: 106.738
+3200/69092	Loss: 105.884
+6400/69092	Loss: 106.055
+9600/69092	Loss: 105.565
+12800/69092	Loss: 107.312
+16000/69092	Loss: 104.994
+19200/69092	Loss: 106.457
+22400/69092	Loss: 105.945
+25600/69092	Loss: 107.124
+28800/69092	Loss: 107.976
+32000/69092	Loss: 105.539
+35200/69092	Loss: 107.506
+38400/69092	Loss: 104.254
+41600/69092	Loss: 106.009
+44800/69092	Loss: 106.371
+48000/69092	Loss: 105.289
+51200/69092	Loss: 105.468
+54400/69092	Loss: 105.606
+57600/69092	Loss: 107.179
+60800/69092	Loss: 105.632
+64000/69092	Loss: 107.227
+67200/69092	Loss: 106.591
+Training time 0:08:23.464363
+Epoch: 176 Average loss: 106.14
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 649)
+0/69092	Loss: 114.687
+3200/69092	Loss: 106.509
+6400/69092	Loss: 106.485
+9600/69092	Loss: 106.079
+12800/69092	Loss: 106.546
+16000/69092	Loss: 107.287
+19200/69092	Loss: 105.287
+22400/69092	Loss: 106.512
+25600/69092	Loss: 105.958
+28800/69092	Loss: 105.841
+32000/69092	Loss: 105.776
+35200/69092	Loss: 106.429
+38400/69092	Loss: 107.060
+41600/69092	Loss: 108.003
+44800/69092	Loss: 106.185
+48000/69092	Loss: 107.813
+51200/69092	Loss: 105.801
+54400/69092	Loss: 103.957
+57600/69092	Loss: 106.232
+60800/69092	Loss: 105.615
+64000/69092	Loss: 106.377
+67200/69092	Loss: 106.752
+Training time 0:08:31.896691
+Epoch: 177 Average loss: 106.28
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 650)
+0/69092	Loss: 104.687
+3200/69092	Loss: 105.704
+6400/69092	Loss: 106.365
+9600/69092	Loss: 105.290
+12800/69092	Loss: 106.102
+16000/69092	Loss: 105.630
+19200/69092	Loss: 105.288
+22400/69092	Loss: 107.092
+25600/69092	Loss: 104.434
+28800/69092	Loss: 106.113
+32000/69092	Loss: 106.087
+35200/69092	Loss: 105.684
+38400/69092	Loss: 106.555
+41600/69092	Loss: 106.947
+44800/69092	Loss: 104.299
+48000/69092	Loss: 108.113
+51200/69092	Loss: 107.524
+54400/69092	Loss: 105.757
+57600/69092	Loss: 106.317
+60800/69092	Loss: 106.831
+64000/69092	Loss: 106.129
+67200/69092	Loss: 106.901
+Training time 0:08:31.488343
+Epoch: 178 Average loss: 106.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 651)
+0/69092	Loss: 96.227
+3200/69092	Loss: 106.056
+6400/69092	Loss: 106.925
+9600/69092	Loss: 105.806
+12800/69092	Loss: 105.606
+16000/69092	Loss: 104.951
+19200/69092	Loss: 104.468
+22400/69092	Loss: 105.716
+25600/69092	Loss: 105.503
+28800/69092	Loss: 107.245
+32000/69092	Loss: 106.466
+35200/69092	Loss: 105.531
+38400/69092	Loss: 105.055
+41600/69092	Loss: 106.715
+44800/69092	Loss: 104.756
+48000/69092	Loss: 105.615
+51200/69092	Loss: 106.280
+54400/69092	Loss: 105.221
+57600/69092	Loss: 106.246
+60800/69092	Loss: 107.447
+64000/69092	Loss: 107.442
+67200/69092	Loss: 107.430
+Training time 0:08:20.345816
+Epoch: 179 Average loss: 106.09
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 652)
+0/69092	Loss: 99.658
+3200/69092	Loss: 104.520
+6400/69092	Loss: 106.737
+9600/69092	Loss: 106.669
+12800/69092	Loss: 105.889
+16000/69092	Loss: 106.393
+19200/69092	Loss: 107.050
+22400/69092	Loss: 106.392
+25600/69092	Loss: 105.461
+28800/69092	Loss: 105.702
+32000/69092	Loss: 107.226
+35200/69092	Loss: 104.355
+38400/69092	Loss: 107.219
+41600/69092	Loss: 105.363
+44800/69092	Loss: 105.420
+48000/69092	Loss: 107.675
+51200/69092	Loss: 105.255
+54400/69092	Loss: 107.612
+57600/69092	Loss: 107.036
+60800/69092	Loss: 106.792
+64000/69092	Loss: 105.676
+67200/69092	Loss: 105.658
+Training time 0:08:28.190321
+Epoch: 180 Average loss: 106.21
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 653)
+0/69092	Loss: 104.538
+3200/69092	Loss: 106.888
+6400/69092	Loss: 107.114
+9600/69092	Loss: 104.938
+12800/69092	Loss: 106.017
+16000/69092	Loss: 106.870
+19200/69092	Loss: 105.833
+22400/69092	Loss: 106.439
+25600/69092	Loss: 106.345
+28800/69092	Loss: 106.883
+32000/69092	Loss: 105.520
+35200/69092	Loss: 106.427
+38400/69092	Loss: 106.069
+41600/69092	Loss: 107.284
+44800/69092	Loss: 105.862
+48000/69092	Loss: 105.435
+51200/69092	Loss: 105.858
+54400/69092	Loss: 106.808
+57600/69092	Loss: 106.924
+60800/69092	Loss: 105.874
+64000/69092	Loss: 107.083
+67200/69092	Loss: 106.573
+Training time 0:08:49.301589
+Epoch: 181 Average loss: 106.33
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 654)
+0/69092	Loss: 99.589
+3200/69092	Loss: 105.879
+6400/69092	Loss: 105.663
+9600/69092	Loss: 104.516
+12800/69092	Loss: 105.185
+16000/69092	Loss: 106.581
+19200/69092	Loss: 107.397
+22400/69092	Loss: 105.517
+25600/69092	Loss: 106.952
+28800/69092	Loss: 107.122
+32000/69092	Loss: 106.775
+35200/69092	Loss: 105.639
+38400/69092	Loss: 106.474
+41600/69092	Loss: 103.631
+44800/69092	Loss: 105.929
+48000/69092	Loss: 108.040
+51200/69092	Loss: 105.129
+54400/69092	Loss: 105.851
+57600/69092	Loss: 108.116
+60800/69092	Loss: 105.640
+64000/69092	Loss: 104.543
+67200/69092	Loss: 107.084
+Training time 0:08:26.750377
+Epoch: 182 Average loss: 106.15
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 655)
+0/69092	Loss: 109.438
+3200/69092	Loss: 106.124
+6400/69092	Loss: 107.405
+9600/69092	Loss: 105.758
+12800/69092	Loss: 105.600
+16000/69092	Loss: 105.296
+19200/69092	Loss: 106.407
+22400/69092	Loss: 107.188
+25600/69092	Loss: 106.151
+28800/69092	Loss: 107.008
+32000/69092	Loss: 106.099
+35200/69092	Loss: 106.690
+38400/69092	Loss: 106.545
+41600/69092	Loss: 106.126
+44800/69092	Loss: 105.617
+48000/69092	Loss: 106.194
+51200/69092	Loss: 105.447
+54400/69092	Loss: 105.896
+57600/69092	Loss: 106.638
+60800/69092	Loss: 106.794
+64000/69092	Loss: 105.825
+67200/69092	Loss: 104.562
+Training time 0:08:25.071642
+Epoch: 183 Average loss: 106.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 656)
+0/69092	Loss: 100.594
+3200/69092	Loss: 107.020
+6400/69092	Loss: 107.429
+9600/69092	Loss: 105.480
+12800/69092	Loss: 107.552
+16000/69092	Loss: 104.795
+19200/69092	Loss: 106.994
+22400/69092	Loss: 105.302
+25600/69092	Loss: 104.263
+28800/69092	Loss: 106.352
+32000/69092	Loss: 105.634
+35200/69092	Loss: 106.360
+38400/69092	Loss: 106.514
+41600/69092	Loss: 106.477
+44800/69092	Loss: 105.800
+48000/69092	Loss: 106.264
+51200/69092	Loss: 105.476
+54400/69092	Loss: 106.184
+57600/69092	Loss: 107.339
+60800/69092	Loss: 104.739
+64000/69092	Loss: 107.735
+67200/69092	Loss: 106.082
+Training time 0:08:32.600178
+Epoch: 184 Average loss: 106.19
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 657)
+0/69092	Loss: 106.166
+3200/69092	Loss: 107.171
+6400/69092	Loss: 105.457
+9600/69092	Loss: 107.010
+12800/69092	Loss: 105.664
+16000/69092	Loss: 105.292
+19200/69092	Loss: 106.641
+22400/69092	Loss: 106.605
+25600/69092	Loss: 106.073
+28800/69092	Loss: 104.203
+32000/69092	Loss: 105.311
+35200/69092	Loss: 106.064
+38400/69092	Loss: 106.548
+41600/69092	Loss: 105.081
+44800/69092	Loss: 107.079
+48000/69092	Loss: 105.305
+51200/69092	Loss: 106.892
+54400/69092	Loss: 106.656
+57600/69092	Loss: 106.890
+60800/69092	Loss: 105.171
+64000/69092	Loss: 107.462
+67200/69092	Loss: 106.277
+Training time 0:08:45.422148
+Epoch: 185 Average loss: 106.14
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 658)
+0/69092	Loss: 107.112
+3200/69092	Loss: 106.577
+6400/69092	Loss: 105.211
+9600/69092	Loss: 105.759
+12800/69092	Loss: 107.173
+16000/69092	Loss: 105.580
+19200/69092	Loss: 105.172
+22400/69092	Loss: 104.954
+25600/69092	Loss: 104.585
+28800/69092	Loss: 107.556
+32000/69092	Loss: 106.528
+35200/69092	Loss: 106.396
+38400/69092	Loss: 105.812
+41600/69092	Loss: 106.657
+44800/69092	Loss: 106.313
+48000/69092	Loss: 106.548
+51200/69092	Loss: 107.501
+54400/69092	Loss: 107.137
+57600/69092	Loss: 106.477
+60800/69092	Loss: 106.822
+64000/69092	Loss: 104.379
+67200/69092	Loss: 105.673
+Training time 0:08:28.390628
+Epoch: 186 Average loss: 106.12
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 659)
+0/69092	Loss: 102.416
+3200/69092	Loss: 104.570
+6400/69092	Loss: 106.035
+9600/69092	Loss: 106.506
+12800/69092	Loss: 107.174
+16000/69092	Loss: 107.193
+19200/69092	Loss: 105.039
+22400/69092	Loss: 107.687
+25600/69092	Loss: 106.161
+28800/69092	Loss: 104.646
+32000/69092	Loss: 105.247
+35200/69092	Loss: 105.952
+38400/69092	Loss: 107.302
+41600/69092	Loss: 105.439
+44800/69092	Loss: 107.263
+48000/69092	Loss: 106.918
+51200/69092	Loss: 106.889
+54400/69092	Loss: 105.596
+57600/69092	Loss: 107.068
+60800/69092	Loss: 104.568
+64000/69092	Loss: 105.991
+67200/69092	Loss: 106.859
+Training time 0:08:18.036083
+Epoch: 187 Average loss: 106.16
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 660)
+0/69092	Loss: 104.139
+3200/69092	Loss: 105.068
+6400/69092	Loss: 105.863
+9600/69092	Loss: 105.486
+12800/69092	Loss: 105.535
+16000/69092	Loss: 105.958
+19200/69092	Loss: 107.501
+22400/69092	Loss: 105.112
+25600/69092	Loss: 107.498
+28800/69092	Loss: 106.341
+32000/69092	Loss: 104.306
+35200/69092	Loss: 105.726
+38400/69092	Loss: 109.437
+41600/69092	Loss: 106.546
+44800/69092	Loss: 106.107
+48000/69092	Loss: 105.707
+51200/69092	Loss: 106.536
+54400/69092	Loss: 104.779
+57600/69092	Loss: 106.826
+60800/69092	Loss: 107.336
+64000/69092	Loss: 105.776
+67200/69092	Loss: 106.477
+Training time 0:08:29.714514
+Epoch: 188 Average loss: 106.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 661)
+0/69092	Loss: 119.480
+3200/69092	Loss: 106.908
+6400/69092	Loss: 106.206
+9600/69092	Loss: 105.326
+12800/69092	Loss: 106.525
+16000/69092	Loss: 106.218
+19200/69092	Loss: 105.695
+22400/69092	Loss: 105.194
+25600/69092	Loss: 107.715
+28800/69092	Loss: 106.304
+32000/69092	Loss: 106.407
+35200/69092	Loss: 104.883
+38400/69092	Loss: 105.244
+41600/69092	Loss: 105.946
+44800/69092	Loss: 106.724
+48000/69092	Loss: 105.583
+51200/69092	Loss: 105.445
+54400/69092	Loss: 106.614
+57600/69092	Loss: 106.551
+60800/69092	Loss: 105.417
+64000/69092	Loss: 106.266
+67200/69092	Loss: 107.410
+Training time 0:08:38.499331
+Epoch: 189 Average loss: 106.12
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 662)
+0/69092	Loss: 105.448
+3200/69092	Loss: 106.199
+6400/69092	Loss: 105.448
+9600/69092	Loss: 105.277
+12800/69092	Loss: 105.208
+16000/69092	Loss: 106.065
+19200/69092	Loss: 104.734
+22400/69092	Loss: 107.310
+25600/69092	Loss: 104.693
+28800/69092	Loss: 107.195
+32000/69092	Loss: 105.983
+35200/69092	Loss: 106.780
+38400/69092	Loss: 106.275
+41600/69092	Loss: 107.210
+44800/69092	Loss: 105.627
+48000/69092	Loss: 105.083
+51200/69092	Loss: 106.390
+54400/69092	Loss: 106.531
+57600/69092	Loss: 105.497
+60800/69092	Loss: 106.916
+64000/69092	Loss: 106.789
+67200/69092	Loss: 106.335
+Training time 0:08:24.794916
+Epoch: 190 Average loss: 106.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 663)
+0/69092	Loss: 99.549
+3200/69092	Loss: 106.645
+6400/69092	Loss: 106.727
+9600/69092	Loss: 106.556
+12800/69092	Loss: 105.403
+16000/69092	Loss: 105.275
+19200/69092	Loss: 105.806
+22400/69092	Loss: 106.810
+25600/69092	Loss: 106.992
+28800/69092	Loss: 107.262
+32000/69092	Loss: 104.433
+35200/69092	Loss: 107.483
+38400/69092	Loss: 106.451
+41600/69092	Loss: 105.209
+44800/69092	Loss: 105.420
+48000/69092	Loss: 104.695
+51200/69092	Loss: 106.091
+54400/69092	Loss: 107.128
+57600/69092	Loss: 105.385
+60800/69092	Loss: 106.719
+64000/69092	Loss: 105.708
+67200/69092	Loss: 105.497
+Training time 0:08:19.924878
+Epoch: 191 Average loss: 106.14
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 664)
+0/69092	Loss: 103.010
+3200/69092	Loss: 106.415
+6400/69092	Loss: 107.568
+9600/69092	Loss: 105.397
+12800/69092	Loss: 105.452
+16000/69092	Loss: 106.455
+19200/69092	Loss: 106.753
+22400/69092	Loss: 107.345
+25600/69092	Loss: 105.453
+28800/69092	Loss: 105.963
+32000/69092	Loss: 107.193
+35200/69092	Loss: 105.801
+38400/69092	Loss: 103.815
+41600/69092	Loss: 106.387
+44800/69092	Loss: 106.168
+48000/69092	Loss: 105.358
+51200/69092	Loss: 106.163
+54400/69092	Loss: 107.001
+57600/69092	Loss: 107.839
+60800/69092	Loss: 105.164
+64000/69092	Loss: 104.895
+67200/69092	Loss: 106.975
+Training time 0:08:38.482680
+Epoch: 192 Average loss: 106.18
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 665)
+0/69092	Loss: 99.711
+3200/69092	Loss: 108.436
+6400/69092	Loss: 107.932
+9600/69092	Loss: 107.837
+12800/69092	Loss: 106.871
+16000/69092	Loss: 105.688
+19200/69092	Loss: 105.377
+22400/69092	Loss: 105.018
+25600/69092	Loss: 107.176
+28800/69092	Loss: 106.759
+32000/69092	Loss: 106.322
+35200/69092	Loss: 105.512
+38400/69092	Loss: 105.156
+41600/69092	Loss: 105.043
+44800/69092	Loss: 106.001
+48000/69092	Loss: 105.589
+51200/69092	Loss: 106.003
+54400/69092	Loss: 105.280
+57600/69092	Loss: 106.445
+60800/69092	Loss: 105.175
+64000/69092	Loss: 106.450
+67200/69092	Loss: 106.990
+Training time 0:08:28.728471
+Epoch: 193 Average loss: 106.25
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 666)
+0/69092	Loss: 105.720
+3200/69092	Loss: 106.953
+6400/69092	Loss: 105.272
+9600/69092	Loss: 105.651
+12800/69092	Loss: 107.326
+16000/69092	Loss: 107.468
+19200/69092	Loss: 105.752
+22400/69092	Loss: 106.624
+25600/69092	Loss: 105.700
+28800/69092	Loss: 106.212
+32000/69092	Loss: 106.396
+35200/69092	Loss: 105.115
+38400/69092	Loss: 105.757
+41600/69092	Loss: 105.604
+44800/69092	Loss: 105.923
+48000/69092	Loss: 104.357
+51200/69092	Loss: 107.543
+54400/69092	Loss: 106.943
+57600/69092	Loss: 105.308
+60800/69092	Loss: 105.873
+64000/69092	Loss: 106.679
+67200/69092	Loss: 106.177
+Training time 0:08:23.362523
+Epoch: 194 Average loss: 106.15
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 667)
+0/69092	Loss: 117.186
+3200/69092	Loss: 105.083
+6400/69092	Loss: 104.901
+9600/69092	Loss: 106.511
+12800/69092	Loss: 105.820
+16000/69092	Loss: 106.272
+19200/69092	Loss: 106.466
+22400/69092	Loss: 106.386
+25600/69092	Loss: 105.605
+28800/69092	Loss: 107.406
+32000/69092	Loss: 105.519
+35200/69092	Loss: 105.925
+38400/69092	Loss: 106.002
+41600/69092	Loss: 106.262
+44800/69092	Loss: 106.197
+48000/69092	Loss: 106.746
+51200/69092	Loss: 104.917
+54400/69092	Loss: 107.122
+57600/69092	Loss: 106.792
+60800/69092	Loss: 106.355
+64000/69092	Loss: 106.310
+67200/69092	Loss: 106.834
+Training time 0:08:21.710524
+Epoch: 195 Average loss: 106.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 668)
+0/69092	Loss: 102.378
+3200/69092	Loss: 103.782
+6400/69092	Loss: 104.434
+9600/69092	Loss: 106.541
+12800/69092	Loss: 105.774
+16000/69092	Loss: 106.840
+19200/69092	Loss: 105.144
+22400/69092	Loss: 105.261
+25600/69092	Loss: 106.820
+28800/69092	Loss: 105.726
+32000/69092	Loss: 106.252
+35200/69092	Loss: 107.570
+38400/69092	Loss: 106.036
+41600/69092	Loss: 105.815
+44800/69092	Loss: 107.667
+48000/69092	Loss: 106.155
+51200/69092	Loss: 106.449
+54400/69092	Loss: 107.092
+57600/69092	Loss: 105.226
+60800/69092	Loss: 107.883
+64000/69092	Loss: 106.340
+67200/69092	Loss: 106.775
+Training time 0:08:45.796416
+Epoch: 196 Average loss: 106.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 669)
+0/69092	Loss: 112.239
+3200/69092	Loss: 108.098
+6400/69092	Loss: 105.860
+9600/69092	Loss: 106.772
+12800/69092	Loss: 105.683
+16000/69092	Loss: 105.731
+19200/69092	Loss: 105.006
+22400/69092	Loss: 107.343
+25600/69092	Loss: 108.182
+28800/69092	Loss: 105.227
+32000/69092	Loss: 107.551
+35200/69092	Loss: 104.940
+38400/69092	Loss: 106.237
+41600/69092	Loss: 107.347
+44800/69092	Loss: 105.981
+48000/69092	Loss: 107.545
+51200/69092	Loss: 108.209
+54400/69092	Loss: 104.848
+57600/69092	Loss: 104.047
+60800/69092	Loss: 106.339
+64000/69092	Loss: 104.290
+67200/69092	Loss: 105.681
+Training time 0:08:35.358769
+Epoch: 197 Average loss: 106.26
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 670)
+0/69092	Loss: 107.090
+3200/69092	Loss: 106.185
+6400/69092	Loss: 107.787
+9600/69092	Loss: 105.124
+12800/69092	Loss: 104.516
+16000/69092	Loss: 106.961
+19200/69092	Loss: 107.162
+22400/69092	Loss: 105.233
+25600/69092	Loss: 104.723
+28800/69092	Loss: 107.320
+32000/69092	Loss: 106.455
+35200/69092	Loss: 106.477
+38400/69092	Loss: 108.214
+41600/69092	Loss: 105.999
+44800/69092	Loss: 105.617
+48000/69092	Loss: 105.380
+51200/69092	Loss: 105.177
+54400/69092	Loss: 105.102
+57600/69092	Loss: 108.021
+60800/69092	Loss: 106.790
+64000/69092	Loss: 106.070
+67200/69092	Loss: 105.831
+Training time 0:08:38.048329
+Epoch: 198 Average loss: 106.19
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 671)
+0/69092	Loss: 107.594
+3200/69092	Loss: 106.591
+6400/69092	Loss: 105.184
+9600/69092	Loss: 105.343
+12800/69092	Loss: 107.480
+16000/69092	Loss: 104.947
+19200/69092	Loss: 106.170
+22400/69092	Loss: 107.320
+25600/69092	Loss: 106.635
+28800/69092	Loss: 104.300
+32000/69092	Loss: 107.820
+35200/69092	Loss: 106.222
+38400/69092	Loss: 106.807
+41600/69092	Loss: 105.934
+44800/69092	Loss: 106.453
+48000/69092	Loss: 106.923
+51200/69092	Loss: 107.599
+54400/69092	Loss: 106.105
+57600/69092	Loss: 106.689
+60800/69092	Loss: 105.894
+64000/69092	Loss: 107.407
+67200/69092	Loss: 102.526
+Training time 0:08:58.569841
+Epoch: 199 Average loss: 106.20
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 672)
+0/69092	Loss: 114.221
+3200/69092	Loss: 105.551
+6400/69092	Loss: 105.473
+9600/69092	Loss: 105.980
+12800/69092	Loss: 106.950
+16000/69092	Loss: 106.558
+19200/69092	Loss: 106.480
+22400/69092	Loss: 107.196
+25600/69092	Loss: 105.341
+28800/69092	Loss: 105.787
+32000/69092	Loss: 105.097
+35200/69092	Loss: 106.568
+38400/69092	Loss: 105.260
+41600/69092	Loss: 107.290
+44800/69092	Loss: 105.960
+48000/69092	Loss: 104.384
+51200/69092	Loss: 108.049
+54400/69092	Loss: 105.834
+57600/69092	Loss: 107.466
+60800/69092	Loss: 105.410
+64000/69092	Loss: 105.985
+67200/69092	Loss: 105.895
+Training time 0:08:34.109477
+Epoch: 200 Average loss: 106.13
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 673)
+0/69092	Loss: 100.111
+3200/69092	Loss: 106.554
+6400/69092	Loss: 106.436
+9600/69092	Loss: 106.748
+12800/69092	Loss: 106.875
+16000/69092	Loss: 106.669
+19200/69092	Loss: 106.811
+22400/69092	Loss: 106.360
+25600/69092	Loss: 105.547
+28800/69092	Loss: 105.962
+32000/69092	Loss: 106.787
+35200/69092	Loss: 106.112
+38400/69092	Loss: 107.323
+41600/69092	Loss: 105.667
+44800/69092	Loss: 105.438
+48000/69092	Loss: 106.437
+51200/69092	Loss: 106.012
+54400/69092	Loss: 104.367
+57600/69092	Loss: 107.330
+60800/69092	Loss: 106.577
+64000/69092	Loss: 104.496
+67200/69092	Loss: 104.959
+Training time 0:09:09.886758
+Epoch: 201 Average loss: 106.20
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 674)
+0/69092	Loss: 105.570
+3200/69092	Loss: 106.903
+6400/69092	Loss: 105.812
+9600/69092	Loss: 105.861
+12800/69092	Loss: 105.339
+16000/69092	Loss: 105.430
+19200/69092	Loss: 105.632
+22400/69092	Loss: 106.248
+25600/69092	Loss: 107.342
+28800/69092	Loss: 106.111
+32000/69092	Loss: 105.399
+35200/69092	Loss: 106.580
+38400/69092	Loss: 106.962
+41600/69092	Loss: 107.342
+44800/69092	Loss: 106.672
+48000/69092	Loss: 105.014
+51200/69092	Loss: 107.217
+54400/69092	Loss: 105.992
+57600/69092	Loss: 107.533
+60800/69092	Loss: 105.466
+64000/69092	Loss: 105.419
+67200/69092	Loss: 106.091
+Training time 0:09:03.665884
+Epoch: 202 Average loss: 106.22
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 675)
+0/69092	Loss: 108.536
+3200/69092	Loss: 106.355
+6400/69092	Loss: 105.792
+9600/69092	Loss: 105.608
+12800/69092	Loss: 106.305
+16000/69092	Loss: 107.612
+19200/69092	Loss: 106.612
+22400/69092	Loss: 106.436
+25600/69092	Loss: 105.181
+28800/69092	Loss: 105.203
+32000/69092	Loss: 105.896
+35200/69092	Loss: 105.526
+38400/69092	Loss: 106.994
+41600/69092	Loss: 106.498
+44800/69092	Loss: 106.499
+48000/69092	Loss: 106.659
+51200/69092	Loss: 105.318
+54400/69092	Loss: 105.875
+57600/69092	Loss: 107.110
+60800/69092	Loss: 105.699
+64000/69092	Loss: 105.360
+67200/69092	Loss: 106.302
+Training time 0:08:38.337861
+Epoch: 203 Average loss: 106.09
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 676)
+0/69092	Loss: 95.968
+3200/69092	Loss: 106.237
+6400/69092	Loss: 105.674
+9600/69092	Loss: 107.303
+12800/69092	Loss: 106.123
+16000/69092	Loss: 106.304
+19200/69092	Loss: 104.477
+22400/69092	Loss: 105.209
+25600/69092	Loss: 105.537
+28800/69092	Loss: 105.080
+32000/69092	Loss: 107.115
+35200/69092	Loss: 106.626
+38400/69092	Loss: 105.271
+41600/69092	Loss: 106.892
+44800/69092	Loss: 105.968
+48000/69092	Loss: 106.940
+51200/69092	Loss: 106.244
+54400/69092	Loss: 105.880
+57600/69092	Loss: 106.563
+60800/69092	Loss: 106.824
+64000/69092	Loss: 106.329
+67200/69092	Loss: 105.471
+Training time 0:09:39.057489
+Epoch: 204 Average loss: 106.14
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 677)
+0/69092	Loss: 107.533
+3200/69092	Loss: 106.341
+6400/69092	Loss: 106.076
+9600/69092	Loss: 105.038
+12800/69092	Loss: 104.677
+16000/69092	Loss: 107.202
+19200/69092	Loss: 106.879
+22400/69092	Loss: 105.534
+25600/69092	Loss: 107.379
+28800/69092	Loss: 106.164
+32000/69092	Loss: 105.998
+35200/69092	Loss: 107.966
+38400/69092	Loss: 105.716
+41600/69092	Loss: 107.191
+44800/69092	Loss: 104.897
+48000/69092	Loss: 105.008
+51200/69092	Loss: 106.276
+54400/69092	Loss: 106.786
+57600/69092	Loss: 105.764
+60800/69092	Loss: 106.421
+64000/69092	Loss: 107.108
+67200/69092	Loss: 105.787
+Training time 0:09:07.050937
+Epoch: 205 Average loss: 106.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 678)
+0/69092	Loss: 104.150
+3200/69092	Loss: 105.862
+6400/69092	Loss: 106.983
+9600/69092	Loss: 104.889
+12800/69092	Loss: 105.411
+16000/69092	Loss: 106.756
+19200/69092	Loss: 104.498
+22400/69092	Loss: 106.149
+25600/69092	Loss: 107.776
+28800/69092	Loss: 106.858
+32000/69092	Loss: 107.564
+35200/69092	Loss: 106.990
+38400/69092	Loss: 104.576
+41600/69092	Loss: 105.988
+44800/69092	Loss: 104.337
+48000/69092	Loss: 106.420
+51200/69092	Loss: 105.755
+54400/69092	Loss: 106.876
+57600/69092	Loss: 105.743
+60800/69092	Loss: 105.341
+64000/69092	Loss: 106.098
+67200/69092	Loss: 106.183
+Training time 0:11:15.706959
+Epoch: 206 Average loss: 106.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 679)
+0/69092	Loss: 98.526
+3200/69092	Loss: 104.751
+6400/69092	Loss: 106.744
+9600/69092	Loss: 105.331
+12800/69092	Loss: 105.142
+16000/69092	Loss: 106.609
+19200/69092	Loss: 105.452
+22400/69092	Loss: 107.274
+25600/69092	Loss: 106.659
+28800/69092	Loss: 104.937
+32000/69092	Loss: 104.592
+35200/69092	Loss: 106.767
+38400/69092	Loss: 107.541
+41600/69092	Loss: 107.236
+44800/69092	Loss: 106.310
+48000/69092	Loss: 107.376
+51200/69092	Loss: 106.051
+54400/69092	Loss: 103.711
+57600/69092	Loss: 106.548
+60800/69092	Loss: 105.714
+64000/69092	Loss: 107.636
+67200/69092	Loss: 105.549
+Training time 0:10:10.872015
+Epoch: 207 Average loss: 106.13
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 680)
+0/69092	Loss: 106.114
+3200/69092	Loss: 107.902
+6400/69092	Loss: 105.140
+9600/69092	Loss: 106.187
+12800/69092	Loss: 107.796
+16000/69092	Loss: 106.642
+19200/69092	Loss: 106.478
+22400/69092	Loss: 106.520
+25600/69092	Loss: 106.188
+28800/69092	Loss: 105.268
+32000/69092	Loss: 103.113
+35200/69092	Loss: 106.057
+38400/69092	Loss: 107.559
+41600/69092	Loss: 104.893
+44800/69092	Loss: 106.978
+48000/69092	Loss: 106.655
+51200/69092	Loss: 106.218
+54400/69092	Loss: 105.667
+57600/69092	Loss: 107.085
+60800/69092	Loss: 105.439
+64000/69092	Loss: 106.023
+67200/69092	Loss: 105.672
+Training time 0:08:37.520492
+Epoch: 208 Average loss: 106.16
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 681)
+0/69092	Loss: 97.864
+3200/69092	Loss: 104.191
+6400/69092	Loss: 104.975
+9600/69092	Loss: 104.979
+12800/69092	Loss: 107.352
+16000/69092	Loss: 108.064
+19200/69092	Loss: 105.332
+22400/69092	Loss: 106.588
+25600/69092	Loss: 105.088
+28800/69092	Loss: 105.539
+32000/69092	Loss: 105.989
+35200/69092	Loss: 105.752
+38400/69092	Loss: 107.513
+41600/69092	Loss: 106.167
+44800/69092	Loss: 107.534
+48000/69092	Loss: 107.268
+51200/69092	Loss: 106.194
+54400/69092	Loss: 106.051
+57600/69092	Loss: 105.487
+60800/69092	Loss: 105.246
+64000/69092	Loss: 106.080
+67200/69092	Loss: 105.144
+Training time 0:08:21.637100
+Epoch: 209 Average loss: 106.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 682)
+0/69092	Loss: 101.644
+3200/69092	Loss: 107.240
+6400/69092	Loss: 106.745
+9600/69092	Loss: 106.481
+12800/69092	Loss: 105.539
+16000/69092	Loss: 105.696
+19200/69092	Loss: 105.399
+22400/69092	Loss: 106.175
+25600/69092	Loss: 105.270
+28800/69092	Loss: 106.157
+32000/69092	Loss: 106.058
+35200/69092	Loss: 107.754
+38400/69092	Loss: 106.581
+41600/69092	Loss: 106.781
+44800/69092	Loss: 104.632
+48000/69092	Loss: 105.320
+51200/69092	Loss: 104.862
+54400/69092	Loss: 104.935
+57600/69092	Loss: 106.590
+60800/69092	Loss: 105.153
+64000/69092	Loss: 107.518
+67200/69092	Loss: 105.980
+Training time 0:08:17.855011
+Epoch: 210 Average loss: 106.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 683)
+0/69092	Loss: 105.595
+3200/69092	Loss: 106.317
+6400/69092	Loss: 106.760
+9600/69092	Loss: 107.256
+12800/69092	Loss: 105.839
+16000/69092	Loss: 104.460
+19200/69092	Loss: 106.646
+22400/69092	Loss: 104.129
+25600/69092	Loss: 105.970
+28800/69092	Loss: 105.486
+32000/69092	Loss: 105.821
+35200/69092	Loss: 104.974
+38400/69092	Loss: 106.364
+41600/69092	Loss: 105.662
+44800/69092	Loss: 106.782
+48000/69092	Loss: 105.389
+51200/69092	Loss: 105.809
+54400/69092	Loss: 107.279
+57600/69092	Loss: 106.374
+60800/69092	Loss: 105.435
+64000/69092	Loss: 108.462
+67200/69092	Loss: 105.415
+Training time 0:08:41.386676
+Epoch: 211 Average loss: 106.04
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 684)
+0/69092	Loss: 107.870
+3200/69092	Loss: 106.598
+6400/69092	Loss: 104.845
+9600/69092	Loss: 106.711
+12800/69092	Loss: 105.128
+16000/69092	Loss: 108.148
+19200/69092	Loss: 105.373
+22400/69092	Loss: 106.594
+25600/69092	Loss: 105.443
+28800/69092	Loss: 103.370
+32000/69092	Loss: 107.295
+35200/69092	Loss: 105.968
+38400/69092	Loss: 106.059
+41600/69092	Loss: 105.369
+44800/69092	Loss: 104.647
+48000/69092	Loss: 106.310
+51200/69092	Loss: 104.580
+54400/69092	Loss: 106.459
+57600/69092	Loss: 106.630
+60800/69092	Loss: 106.572
+64000/69092	Loss: 105.803
+67200/69092	Loss: 105.798
+Training time 0:08:36.739791
+Epoch: 212 Average loss: 105.93
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 685)
+0/69092	Loss: 110.722
+3200/69092	Loss: 106.997
+6400/69092	Loss: 106.885
+9600/69092	Loss: 106.312
+12800/69092	Loss: 106.300
+16000/69092	Loss: 107.280
+19200/69092	Loss: 105.844
+22400/69092	Loss: 104.333
+25600/69092	Loss: 106.650
+28800/69092	Loss: 106.134
+32000/69092	Loss: 105.019
+35200/69092	Loss: 105.486
+38400/69092	Loss: 105.753
+41600/69092	Loss: 106.191
+44800/69092	Loss: 106.057
+48000/69092	Loss: 105.717
+51200/69092	Loss: 106.168
+54400/69092	Loss: 106.251
+57600/69092	Loss: 105.343
+60800/69092	Loss: 107.037
+64000/69092	Loss: 106.417
+67200/69092	Loss: 105.958
+Training time 0:08:27.109254
+Epoch: 213 Average loss: 106.14
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 686)
+0/69092	Loss: 100.030
+3200/69092	Loss: 105.554
+6400/69092	Loss: 106.411
+9600/69092	Loss: 104.240
+12800/69092	Loss: 106.683
+16000/69092	Loss: 105.489
+19200/69092	Loss: 106.763
+22400/69092	Loss: 105.423
+25600/69092	Loss: 108.782
+28800/69092	Loss: 106.133
+32000/69092	Loss: 106.438
+35200/69092	Loss: 108.585
+38400/69092	Loss: 106.233
+41600/69092	Loss: 106.696
+44800/69092	Loss: 106.417
+48000/69092	Loss: 106.954
+51200/69092	Loss: 104.761
+54400/69092	Loss: 105.490
+57600/69092	Loss: 104.645
+60800/69092	Loss: 106.496
+64000/69092	Loss: 106.473
+67200/69092	Loss: 105.437
+Training time 0:08:21.003754
+Epoch: 214 Average loss: 106.22
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 687)
+0/69092	Loss: 107.171
+3200/69092	Loss: 105.782
+6400/69092	Loss: 105.711
+9600/69092	Loss: 107.709
+12800/69092	Loss: 104.562
+16000/69092	Loss: 106.016
+19200/69092	Loss: 105.089
+22400/69092	Loss: 106.298
+25600/69092	Loss: 106.804
+28800/69092	Loss: 106.865
+32000/69092	Loss: 107.824
+35200/69092	Loss: 105.344
+38400/69092	Loss: 106.587
+41600/69092	Loss: 104.435
+44800/69092	Loss: 106.749
+48000/69092	Loss: 108.496
+51200/69092	Loss: 107.333
+54400/69092	Loss: 105.013
+57600/69092	Loss: 106.827
+60800/69092	Loss: 107.152
+64000/69092	Loss: 107.402
+67200/69092	Loss: 104.654
+Training time 0:08:30.695034
+Epoch: 215 Average loss: 106.29
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 688)
+0/69092	Loss: 104.460
+3200/69092	Loss: 105.401
+6400/69092	Loss: 105.414
+9600/69092	Loss: 105.987
+12800/69092	Loss: 107.507
+16000/69092	Loss: 106.385
+19200/69092	Loss: 107.787
+22400/69092	Loss: 105.225
+25600/69092	Loss: 104.770
+28800/69092	Loss: 105.634
+32000/69092	Loss: 106.315
+35200/69092	Loss: 104.373
+38400/69092	Loss: 106.823
+41600/69092	Loss: 106.110
+44800/69092	Loss: 106.034
+48000/69092	Loss: 105.173
+51200/69092	Loss: 107.879
+54400/69092	Loss: 108.120
+57600/69092	Loss: 105.581
+60800/69092	Loss: 107.200
+64000/69092	Loss: 105.132
+67200/69092	Loss: 105.154
+Training time 0:08:45.636566
+Epoch: 216 Average loss: 106.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 689)
+0/69092	Loss: 103.852
+3200/69092	Loss: 106.568
+6400/69092	Loss: 106.234
+9600/69092	Loss: 105.931
+12800/69092	Loss: 105.723
+16000/69092	Loss: 107.210
+19200/69092	Loss: 107.477
+22400/69092	Loss: 106.032
+25600/69092	Loss: 106.228
+28800/69092	Loss: 105.423
+32000/69092	Loss: 105.676
+35200/69092	Loss: 105.932
+38400/69092	Loss: 107.486
+41600/69092	Loss: 105.745
+44800/69092	Loss: 104.582
+48000/69092	Loss: 104.440
+51200/69092	Loss: 105.329
+54400/69092	Loss: 106.079
+57600/69092	Loss: 108.275
+60800/69092	Loss: 107.027
+64000/69092	Loss: 106.300
+67200/69092	Loss: 106.135
+Training time 0:08:11.376382
+Epoch: 217 Average loss: 106.14
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 690)
+0/69092	Loss: 98.262
+3200/69092	Loss: 105.190
+6400/69092	Loss: 106.933
+9600/69092	Loss: 104.478
+12800/69092	Loss: 105.731
+16000/69092	Loss: 104.624
+19200/69092	Loss: 105.099
+22400/69092	Loss: 106.298
+25600/69092	Loss: 106.807
+28800/69092	Loss: 103.922
+32000/69092	Loss: 106.628
+35200/69092	Loss: 106.152
+38400/69092	Loss: 105.360
+41600/69092	Loss: 106.529
+44800/69092	Loss: 105.324
+48000/69092	Loss: 106.512
+51200/69092	Loss: 106.377
+54400/69092	Loss: 106.532
+57600/69092	Loss: 106.096
+60800/69092	Loss: 106.902
+64000/69092	Loss: 107.584
+67200/69092	Loss: 106.248
+Training time 0:08:29.352166
+Epoch: 218 Average loss: 105.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 691)
+0/69092	Loss: 100.858
+3200/69092	Loss: 107.245
+6400/69092	Loss: 105.312
+9600/69092	Loss: 105.937
+12800/69092	Loss: 105.353
+16000/69092	Loss: 105.148
+19200/69092	Loss: 106.627
+22400/69092	Loss: 105.734
+25600/69092	Loss: 106.111
+28800/69092	Loss: 106.979
+32000/69092	Loss: 106.641
+35200/69092	Loss: 106.915
+38400/69092	Loss: 105.993
+41600/69092	Loss: 106.656
+44800/69092	Loss: 105.972
+48000/69092	Loss: 104.277
+51200/69092	Loss: 106.087
+54400/69092	Loss: 105.880
+57600/69092	Loss: 106.988
+60800/69092	Loss: 106.971
+64000/69092	Loss: 105.527
+67200/69092	Loss: 105.333
+Training time 0:08:26.506137
+Epoch: 219 Average loss: 106.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 692)
+0/69092	Loss: 112.029
+3200/69092	Loss: 105.526
+6400/69092	Loss: 106.184
+9600/69092	Loss: 106.399
+12800/69092	Loss: 106.229
+16000/69092	Loss: 105.846
+19200/69092	Loss: 106.071
+22400/69092	Loss: 106.127
+25600/69092	Loss: 106.256
+28800/69092	Loss: 105.038
+32000/69092	Loss: 105.574
+35200/69092	Loss: 104.691
+38400/69092	Loss: 106.185
+41600/69092	Loss: 106.651
+44800/69092	Loss: 105.830
+48000/69092	Loss: 105.174
+51200/69092	Loss: 106.295
+54400/69092	Loss: 106.784
+57600/69092	Loss: 105.082
+60800/69092	Loss: 104.995
+64000/69092	Loss: 106.648
+67200/69092	Loss: 106.150
+Training time 0:08:40.404256
+Epoch: 220 Average loss: 105.99
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 693)
+0/69092	Loss: 108.426
+3200/69092	Loss: 105.306
+6400/69092	Loss: 107.059
+9600/69092	Loss: 104.770
+12800/69092	Loss: 106.714
+16000/69092	Loss: 105.264
+19200/69092	Loss: 106.453
+22400/69092	Loss: 105.886
+25600/69092	Loss: 106.175
+28800/69092	Loss: 105.648
+32000/69092	Loss: 105.804
+35200/69092	Loss: 106.389
+38400/69092	Loss: 106.489
+41600/69092	Loss: 105.980
+44800/69092	Loss: 106.300
+48000/69092	Loss: 105.558
+51200/69092	Loss: 107.025
+54400/69092	Loss: 106.197
+57600/69092	Loss: 106.232
+60800/69092	Loss: 106.009
+64000/69092	Loss: 107.813
+67200/69092	Loss: 105.844
+Training time 0:08:16.025544
+Epoch: 221 Average loss: 106.17
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 694)
+0/69092	Loss: 104.104
+3200/69092	Loss: 107.157
+6400/69092	Loss: 104.536
+9600/69092	Loss: 105.083
+12800/69092	Loss: 104.975
+16000/69092	Loss: 106.487
+19200/69092	Loss: 106.652
+22400/69092	Loss: 107.389
+25600/69092	Loss: 105.636
+28800/69092	Loss: 106.063
+32000/69092	Loss: 106.297
+35200/69092	Loss: 106.514
+38400/69092	Loss: 106.602
+41600/69092	Loss: 106.841
+44800/69092	Loss: 104.714
+48000/69092	Loss: 105.413
+51200/69092	Loss: 106.980
+54400/69092	Loss: 105.189
+57600/69092	Loss: 105.073
+60800/69092	Loss: 106.733
+64000/69092	Loss: 105.855
+67200/69092	Loss: 107.041
+Training time 0:08:29.128863
+Epoch: 222 Average loss: 106.02
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 695)
+0/69092	Loss: 103.624
+3200/69092	Loss: 108.448
+6400/69092	Loss: 104.844
+9600/69092	Loss: 106.026
+12800/69092	Loss: 107.180
+16000/69092	Loss: 105.072
+19200/69092	Loss: 107.198
+22400/69092	Loss: 106.112
+25600/69092	Loss: 105.471
+28800/69092	Loss: 106.232
+32000/69092	Loss: 103.121
+35200/69092	Loss: 105.590
+38400/69092	Loss: 105.702
+41600/69092	Loss: 106.110
+44800/69092	Loss: 106.138
+48000/69092	Loss: 105.171
+51200/69092	Loss: 107.147
+54400/69092	Loss: 105.153
+57600/69092	Loss: 105.174
+60800/69092	Loss: 104.807
+64000/69092	Loss: 106.330
+67200/69092	Loss: 107.014
+Training time 0:08:39.588361
+Epoch: 223 Average loss: 105.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 696)
+0/69092	Loss: 112.390
+3200/69092	Loss: 107.431
+6400/69092	Loss: 106.338
+9600/69092	Loss: 105.140
+12800/69092	Loss: 104.812
+16000/69092	Loss: 105.040
+19200/69092	Loss: 107.810
+22400/69092	Loss: 106.580
+25600/69092	Loss: 106.715
+28800/69092	Loss: 105.872
+32000/69092	Loss: 106.548
+35200/69092	Loss: 106.040
+38400/69092	Loss: 105.529
+41600/69092	Loss: 105.437
+44800/69092	Loss: 105.323
+48000/69092	Loss: 106.880
+51200/69092	Loss: 107.134
+54400/69092	Loss: 103.431
+57600/69092	Loss: 104.878
+60800/69092	Loss: 106.090
+64000/69092	Loss: 106.290
+67200/69092	Loss: 105.654
+Training time 0:08:33.948499
+Epoch: 224 Average loss: 105.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 697)
+0/69092	Loss: 100.900
+3200/69092	Loss: 105.218
+6400/69092	Loss: 104.900
+9600/69092	Loss: 106.023
+12800/69092	Loss: 105.211
+16000/69092	Loss: 104.703
+19200/69092	Loss: 106.668
+22400/69092	Loss: 105.399
+25600/69092	Loss: 104.523
+28800/69092	Loss: 103.687
+32000/69092	Loss: 106.032
+35200/69092	Loss: 106.210
+38400/69092	Loss: 105.403
+41600/69092	Loss: 104.469
+44800/69092	Loss: 107.046
+48000/69092	Loss: 106.881
+51200/69092	Loss: 104.785
+54400/69092	Loss: 107.651
+57600/69092	Loss: 106.493
+60800/69092	Loss: 107.077
+64000/69092	Loss: 107.788
+67200/69092	Loss: 106.537
+Training time 0:08:10.624329
+Epoch: 225 Average loss: 105.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 698)
+0/69092	Loss: 104.673
+3200/69092	Loss: 106.011
+6400/69092	Loss: 105.585
+9600/69092	Loss: 106.538
+12800/69092	Loss: 104.660
+16000/69092	Loss: 105.559
+19200/69092	Loss: 105.202
+22400/69092	Loss: 104.866
+25600/69092	Loss: 104.772
+28800/69092	Loss: 105.247
+32000/69092	Loss: 108.565
+35200/69092	Loss: 106.270
+38400/69092	Loss: 104.435
+41600/69092	Loss: 105.995
+44800/69092	Loss: 106.108
+48000/69092	Loss: 106.068
+51200/69092	Loss: 107.085
+54400/69092	Loss: 106.714
+57600/69092	Loss: 104.995
+60800/69092	Loss: 106.151
+64000/69092	Loss: 105.687
+67200/69092	Loss: 107.965
+Training time 0:08:28.033592
+Epoch: 226 Average loss: 105.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 699)
+0/69092	Loss: 100.387
+3200/69092	Loss: 104.901
+6400/69092	Loss: 106.768
+9600/69092	Loss: 104.541
+12800/69092	Loss: 107.046
+16000/69092	Loss: 106.663
+19200/69092	Loss: 106.196
+22400/69092	Loss: 105.139
+25600/69092	Loss: 106.221
+28800/69092	Loss: 104.865
+32000/69092	Loss: 105.765
+35200/69092	Loss: 107.114
+38400/69092	Loss: 106.384
+41600/69092	Loss: 105.492
+44800/69092	Loss: 105.759
+48000/69092	Loss: 105.277
+51200/69092	Loss: 106.908
+54400/69092	Loss: 105.944
+57600/69092	Loss: 105.432
+60800/69092	Loss: 106.003
+64000/69092	Loss: 106.547
+67200/69092	Loss: 107.293
+Training time 0:08:40.540703
+Epoch: 227 Average loss: 106.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 700)
+0/69092	Loss: 101.868
+3200/69092	Loss: 106.052
+6400/69092	Loss: 105.238
+9600/69092	Loss: 107.075
+12800/69092	Loss: 107.082
+16000/69092	Loss: 106.672
+19200/69092	Loss: 107.029
+22400/69092	Loss: 106.626
+25600/69092	Loss: 106.493
+28800/69092	Loss: 106.184
+32000/69092	Loss: 105.280
+35200/69092	Loss: 105.119
+38400/69092	Loss: 106.452
+41600/69092	Loss: 105.274
+44800/69092	Loss: 106.823
+48000/69092	Loss: 105.952
+51200/69092	Loss: 104.785
+54400/69092	Loss: 105.724
+57600/69092	Loss: 106.325
+60800/69092	Loss: 106.982
+64000/69092	Loss: 104.554
+67200/69092	Loss: 104.874
+Training time 0:08:23.904157
+Epoch: 228 Average loss: 106.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 701)
+0/69092	Loss: 108.580
+3200/69092	Loss: 106.648
+6400/69092	Loss: 105.563
+9600/69092	Loss: 106.220
+12800/69092	Loss: 106.925
+16000/69092	Loss: 105.855
+19200/69092	Loss: 106.425
+22400/69092	Loss: 106.197
+25600/69092	Loss: 106.339
+28800/69092	Loss: 104.597
+32000/69092	Loss: 105.748
+35200/69092	Loss: 104.843
+38400/69092	Loss: 106.167
+41600/69092	Loss: 106.993
+44800/69092	Loss: 105.425
+48000/69092	Loss: 106.115
+51200/69092	Loss: 106.128
+54400/69092	Loss: 106.316
+57600/69092	Loss: 106.164
+60800/69092	Loss: 107.684
+64000/69092	Loss: 106.239
+67200/69092	Loss: 104.600
+Training time 0:08:17.987816
+Epoch: 229 Average loss: 106.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 702)
+0/69092	Loss: 108.705
+3200/69092	Loss: 107.761
+6400/69092	Loss: 106.302
+9600/69092	Loss: 105.635
+12800/69092	Loss: 107.141
+16000/69092	Loss: 106.381
+19200/69092	Loss: 105.783
+22400/69092	Loss: 104.906
+25600/69092	Loss: 103.312
+28800/69092	Loss: 104.815
+32000/69092	Loss: 107.540
+35200/69092	Loss: 105.228
+38400/69092	Loss: 106.573
+41600/69092	Loss: 104.637
+44800/69092	Loss: 106.452
+48000/69092	Loss: 106.110
+51200/69092	Loss: 105.273
+54400/69092	Loss: 106.972
+57600/69092	Loss: 106.033
+60800/69092	Loss: 105.135
+64000/69092	Loss: 105.952
+67200/69092	Loss: 107.134
+Training time 0:08:31.411843
+Epoch: 230 Average loss: 105.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 703)
+0/69092	Loss: 109.997
+3200/69092	Loss: 106.701
+6400/69092	Loss: 105.239
+9600/69092	Loss: 105.972
+12800/69092	Loss: 104.693
+16000/69092	Loss: 105.919
+19200/69092	Loss: 106.498
+22400/69092	Loss: 104.994
+25600/69092	Loss: 107.073
+28800/69092	Loss: 105.371
+32000/69092	Loss: 105.324
+35200/69092	Loss: 105.175
+38400/69092	Loss: 106.722
+41600/69092	Loss: 106.970
+44800/69092	Loss: 107.746
+48000/69092	Loss: 106.094
+51200/69092	Loss: 105.963
+54400/69092	Loss: 104.855
+57600/69092	Loss: 104.864
+60800/69092	Loss: 104.479
+64000/69092	Loss: 106.113
+67200/69092	Loss: 107.003
+Training time 0:08:35.640257
+Epoch: 231 Average loss: 105.96
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 704)
+0/69092	Loss: 99.023
+3200/69092	Loss: 106.133
+6400/69092	Loss: 103.953
+9600/69092	Loss: 106.588
+12800/69092	Loss: 103.748
+16000/69092	Loss: 106.819
+19200/69092	Loss: 106.795
+22400/69092	Loss: 106.438
+25600/69092	Loss: 106.336
+28800/69092	Loss: 104.452
+32000/69092	Loss: 107.474
+35200/69092	Loss: 105.620
+38400/69092	Loss: 107.181
+41600/69092	Loss: 106.219
+44800/69092	Loss: 105.854
+48000/69092	Loss: 106.273
+51200/69092	Loss: 105.586
+54400/69092	Loss: 105.656
+57600/69092	Loss: 105.932
+60800/69092	Loss: 106.884
+64000/69092	Loss: 106.188
+67200/69092	Loss: 106.109
+Training time 0:08:30.378238
+Epoch: 232 Average loss: 106.07
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 705)
+0/69092	Loss: 115.092
+3200/69092	Loss: 105.291
+6400/69092	Loss: 105.150
+9600/69092	Loss: 106.622
+12800/69092	Loss: 106.600
+16000/69092	Loss: 105.654
+19200/69092	Loss: 106.292
+22400/69092	Loss: 105.552
+25600/69092	Loss: 106.306
+28800/69092	Loss: 107.029
+32000/69092	Loss: 106.689
+35200/69092	Loss: 105.538
+38400/69092	Loss: 105.183
+41600/69092	Loss: 106.011
+44800/69092	Loss: 105.852
+48000/69092	Loss: 106.408
+51200/69092	Loss: 104.927
+54400/69092	Loss: 105.282
+57600/69092	Loss: 106.056
+60800/69092	Loss: 106.608
+64000/69092	Loss: 105.861
+67200/69092	Loss: 106.496
+Training time 0:08:17.459356
+Epoch: 233 Average loss: 105.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 706)
+0/69092	Loss: 99.244
+3200/69092	Loss: 106.592
+6400/69092	Loss: 104.928
+9600/69092	Loss: 104.254
+12800/69092	Loss: 105.963
+16000/69092	Loss: 105.462
+19200/69092	Loss: 105.197
+22400/69092	Loss: 107.355
+25600/69092	Loss: 105.591
+28800/69092	Loss: 106.583
+32000/69092	Loss: 105.067
+35200/69092	Loss: 105.076
+38400/69092	Loss: 106.832
+41600/69092	Loss: 106.872
+44800/69092	Loss: 104.939
+48000/69092	Loss: 106.403
+51200/69092	Loss: 106.669
+54400/69092	Loss: 105.488
+57600/69092	Loss: 107.464
+60800/69092	Loss: 106.547
+64000/69092	Loss: 106.263
+67200/69092	Loss: 106.731
+Training time 0:08:23.984451
+Epoch: 234 Average loss: 105.99
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 707)
+0/69092	Loss: 94.664
+3200/69092	Loss: 105.063
+6400/69092	Loss: 106.149
+9600/69092	Loss: 105.586
+12800/69092	Loss: 106.044
+16000/69092	Loss: 104.878
+19200/69092	Loss: 106.973
+22400/69092	Loss: 106.625
+25600/69092	Loss: 105.751
+28800/69092	Loss: 106.421
+32000/69092	Loss: 105.418
+35200/69092	Loss: 107.047
+38400/69092	Loss: 107.914
+41600/69092	Loss: 105.580
+44800/69092	Loss: 107.075
+48000/69092	Loss: 105.620
+51200/69092	Loss: 104.796
+54400/69092	Loss: 104.523
+57600/69092	Loss: 106.971
+60800/69092	Loss: 105.472
+64000/69092	Loss: 104.828
+67200/69092	Loss: 106.680
+Training time 0:08:37.702991
+Epoch: 235 Average loss: 105.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 708)
+0/69092	Loss: 102.050
+3200/69092	Loss: 106.772
+6400/69092	Loss: 105.498
+9600/69092	Loss: 105.883
+12800/69092	Loss: 105.258
+16000/69092	Loss: 105.395
+19200/69092	Loss: 104.918
+22400/69092	Loss: 104.934
+25600/69092	Loss: 105.175
+28800/69092	Loss: 107.500
+32000/69092	Loss: 105.482
+35200/69092	Loss: 107.276
+38400/69092	Loss: 106.788
+41600/69092	Loss: 105.661
+44800/69092	Loss: 106.466
+48000/69092	Loss: 107.183
+51200/69092	Loss: 105.646
+54400/69092	Loss: 108.238
+57600/69092	Loss: 107.752
+60800/69092	Loss: 104.743
+64000/69092	Loss: 105.404
+67200/69092	Loss: 106.303
+Training time 0:08:12.504065
+Epoch: 236 Average loss: 106.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 709)
+0/69092	Loss: 112.111
+3200/69092	Loss: 105.964
+6400/69092	Loss: 106.936
+9600/69092	Loss: 105.225
+12800/69092	Loss: 105.616
+16000/69092	Loss: 104.757
+19200/69092	Loss: 107.250
+22400/69092	Loss: 107.147
+25600/69092	Loss: 105.469
+28800/69092	Loss: 107.893
+32000/69092	Loss: 105.358
+35200/69092	Loss: 106.049
+38400/69092	Loss: 105.214
+41600/69092	Loss: 106.115
+44800/69092	Loss: 104.732
+48000/69092	Loss: 104.093
+51200/69092	Loss: 107.386
+54400/69092	Loss: 106.116
+57600/69092	Loss: 105.922
+60800/69092	Loss: 106.185
+64000/69092	Loss: 106.136
+67200/69092	Loss: 105.205
+Training time 0:08:17.323460
+Epoch: 237 Average loss: 105.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 710)
+0/69092	Loss: 106.526
+3200/69092	Loss: 105.133
+6400/69092	Loss: 105.928
+9600/69092	Loss: 105.475
+12800/69092	Loss: 106.872
+16000/69092	Loss: 106.153
+19200/69092	Loss: 107.106
+22400/69092	Loss: 104.479
+25600/69092	Loss: 106.941
+28800/69092	Loss: 107.342
+32000/69092	Loss: 105.962
+35200/69092	Loss: 106.511
+38400/69092	Loss: 105.141
+41600/69092	Loss: 106.129
+44800/69092	Loss: 105.984
+48000/69092	Loss: 105.370
+51200/69092	Loss: 106.415
+54400/69092	Loss: 106.724
+57600/69092	Loss: 105.808
+60800/69092	Loss: 105.475
+64000/69092	Loss: 106.056
+67200/69092	Loss: 106.246
+Training time 0:08:36.748830
+Epoch: 238 Average loss: 106.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 711)
+0/69092	Loss: 109.824
+3200/69092	Loss: 106.311
+6400/69092	Loss: 106.422
+9600/69092	Loss: 105.782
+12800/69092	Loss: 106.680
+16000/69092	Loss: 105.592
+19200/69092	Loss: 105.995
+22400/69092	Loss: 106.168
+25600/69092	Loss: 105.457
+28800/69092	Loss: 105.181
+32000/69092	Loss: 105.599
+35200/69092	Loss: 104.978
+38400/69092	Loss: 106.107
+41600/69092	Loss: 104.844
+44800/69092	Loss: 107.404
+48000/69092	Loss: 105.763
+51200/69092	Loss: 105.989
+54400/69092	Loss: 105.759
+57600/69092	Loss: 105.787
+60800/69092	Loss: 107.621
+64000/69092	Loss: 104.274
+67200/69092	Loss: 105.418
+Training time 0:08:41.468139
+Epoch: 239 Average loss: 105.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 712)
+0/69092	Loss: 117.618
+3200/69092	Loss: 106.658
+6400/69092	Loss: 105.108
+9600/69092	Loss: 105.125
+12800/69092	Loss: 106.253
+16000/69092	Loss: 105.664
+19200/69092	Loss: 108.187
+22400/69092	Loss: 105.142
+25600/69092	Loss: 107.355
+28800/69092	Loss: 106.615
+32000/69092	Loss: 103.693
+35200/69092	Loss: 104.701
+38400/69092	Loss: 106.595
+41600/69092	Loss: 106.280
+44800/69092	Loss: 105.403
+48000/69092	Loss: 105.811
+51200/69092	Loss: 105.775
+54400/69092	Loss: 106.689
+57600/69092	Loss: 104.890
+60800/69092	Loss: 104.813
+64000/69092	Loss: 105.744
+67200/69092	Loss: 106.803
+Training time 0:08:24.811712
+Epoch: 240 Average loss: 105.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 713)
+0/69092	Loss: 111.961
+3200/69092	Loss: 106.898
+6400/69092	Loss: 104.486
+9600/69092	Loss: 105.924
+12800/69092	Loss: 107.881
+16000/69092	Loss: 107.144
+19200/69092	Loss: 106.493
+22400/69092	Loss: 104.537
+25600/69092	Loss: 105.667
+28800/69092	Loss: 107.266
+32000/69092	Loss: 107.049
+35200/69092	Loss: 106.144
+38400/69092	Loss: 106.358
+41600/69092	Loss: 104.714
+44800/69092	Loss: 105.439
+48000/69092	Loss: 105.080
+51200/69092	Loss: 104.798
+54400/69092	Loss: 106.280
+57600/69092	Loss: 106.550
+60800/69092	Loss: 107.426
+64000/69092	Loss: 104.789
+67200/69092	Loss: 107.697
+Training time 0:08:22.312542
+Epoch: 241 Average loss: 106.14
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 714)
+0/69092	Loss: 115.787
+3200/69092	Loss: 105.476
+6400/69092	Loss: 106.647
+9600/69092	Loss: 106.777
+12800/69092	Loss: 106.181
+16000/69092	Loss: 106.485
+19200/69092	Loss: 106.136
+22400/69092	Loss: 105.154
+25600/69092	Loss: 105.693
+28800/69092	Loss: 105.028
+32000/69092	Loss: 106.173
+35200/69092	Loss: 106.209
+38400/69092	Loss: 104.776
+41600/69092	Loss: 105.121
+44800/69092	Loss: 106.748
+48000/69092	Loss: 106.765
+51200/69092	Loss: 105.166
+54400/69092	Loss: 105.996
+57600/69092	Loss: 106.933
+60800/69092	Loss: 106.083
+64000/69092	Loss: 106.132
+67200/69092	Loss: 105.403
+Training time 0:08:41.926897
+Epoch: 242 Average loss: 106.03
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 715)
+0/69092	Loss: 97.564
+3200/69092	Loss: 105.789
+6400/69092	Loss: 106.007
+9600/69092	Loss: 106.522
+12800/69092	Loss: 104.991
+16000/69092	Loss: 105.909
+19200/69092	Loss: 106.388
+22400/69092	Loss: 105.948
+25600/69092	Loss: 106.587
+28800/69092	Loss: 106.199
+32000/69092	Loss: 107.374
+35200/69092	Loss: 105.877
+38400/69092	Loss: 107.074
+41600/69092	Loss: 107.478
+44800/69092	Loss: 104.823
+48000/69092	Loss: 105.414
+51200/69092	Loss: 106.102
+54400/69092	Loss: 105.929
+57600/69092	Loss: 104.754
+60800/69092	Loss: 107.117
+64000/69092	Loss: 105.599
+67200/69092	Loss: 105.732
+Training time 0:08:48.720795
+Epoch: 243 Average loss: 106.05
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 716)
+0/69092	Loss: 109.048
+3200/69092	Loss: 106.029
+6400/69092	Loss: 105.295
+9600/69092	Loss: 106.397
+12800/69092	Loss: 107.872
+16000/69092	Loss: 107.499
+19200/69092	Loss: 107.751
+22400/69092	Loss: 106.750
+25600/69092	Loss: 104.753
+28800/69092	Loss: 105.554
+32000/69092	Loss: 106.064
+35200/69092	Loss: 105.767
+38400/69092	Loss: 104.742
+41600/69092	Loss: 106.285
+44800/69092	Loss: 105.775
+48000/69092	Loss: 106.229
+51200/69092	Loss: 105.762
+54400/69092	Loss: 105.718
+57600/69092	Loss: 107.042
+60800/69092	Loss: 105.385
+64000/69092	Loss: 105.649
+67200/69092	Loss: 106.809
+Training time 0:08:30.647251
+Epoch: 244 Average loss: 106.16
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 717)
+0/69092	Loss: 112.271
+3200/69092	Loss: 104.326
+6400/69092	Loss: 105.636
+9600/69092	Loss: 104.428
+12800/69092	Loss: 106.516
+16000/69092	Loss: 104.981
+19200/69092	Loss: 106.446
+22400/69092	Loss: 105.799
+25600/69092	Loss: 104.672
+28800/69092	Loss: 107.131
+32000/69092	Loss: 106.154
+35200/69092	Loss: 108.167
+38400/69092	Loss: 105.297
+41600/69092	Loss: 105.765
+44800/69092	Loss: 106.471
+48000/69092	Loss: 106.358
+51200/69092	Loss: 105.708
+54400/69092	Loss: 105.474
+57600/69092	Loss: 106.157
+60800/69092	Loss: 105.280
+64000/69092	Loss: 107.981
+67200/69092	Loss: 107.499
+Training time 0:08:11.488859
+Epoch: 245 Average loss: 106.04
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 718)
+0/69092	Loss: 108.181
+3200/69092	Loss: 105.217
+6400/69092	Loss: 106.833
+9600/69092	Loss: 106.450
+12800/69092	Loss: 105.236
+16000/69092	Loss: 105.384
+19200/69092	Loss: 107.086
+22400/69092	Loss: 105.650
+25600/69092	Loss: 106.508
+28800/69092	Loss: 106.218
+32000/69092	Loss: 105.979
+35200/69092	Loss: 106.361
+38400/69092	Loss: 104.955
+41600/69092	Loss: 105.171
+44800/69092	Loss: 105.209
+48000/69092	Loss: 106.335
+51200/69092	Loss: 106.114
+54400/69092	Loss: 106.314
+57600/69092	Loss: 104.810
+60800/69092	Loss: 105.536
+64000/69092	Loss: 106.613
+67200/69092	Loss: 105.100
+Training time 0:08:25.901428
+Epoch: 246 Average loss: 105.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 719)
+0/69092	Loss: 103.823
+3200/69092	Loss: 106.529
+6400/69092	Loss: 106.308
+9600/69092	Loss: 105.826
+12800/69092	Loss: 105.317
+16000/69092	Loss: 104.787
+19200/69092	Loss: 105.674
+22400/69092	Loss: 104.455
+25600/69092	Loss: 105.914
+28800/69092	Loss: 106.134
+32000/69092	Loss: 106.457
+35200/69092	Loss: 106.203
+38400/69092	Loss: 107.015
+41600/69092	Loss: 106.284
+44800/69092	Loss: 106.906
+48000/69092	Loss: 105.291
+51200/69092	Loss: 106.273
+54400/69092	Loss: 104.065
+57600/69092	Loss: 105.542
+60800/69092	Loss: 105.603
+64000/69092	Loss: 106.896
+67200/69092	Loss: 107.500
+Training time 0:08:34.102430
+Epoch: 247 Average loss: 106.04
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 720)
+0/69092	Loss: 105.551
+3200/69092	Loss: 106.278
+6400/69092	Loss: 106.267
+9600/69092	Loss: 103.908
+12800/69092	Loss: 105.448
+16000/69092	Loss: 107.270
+19200/69092	Loss: 106.824
+22400/69092	Loss: 106.254
+25600/69092	Loss: 105.909
+28800/69092	Loss: 106.071
+32000/69092	Loss: 106.194
+35200/69092	Loss: 106.014
+38400/69092	Loss: 105.115
+41600/69092	Loss: 105.699
+44800/69092	Loss: 106.218
+48000/69092	Loss: 104.804
+51200/69092	Loss: 106.152
+54400/69092	Loss: 105.435
+57600/69092	Loss: 106.421
+60800/69092	Loss: 107.068
+64000/69092	Loss: 105.994
+67200/69092	Loss: 107.665
+Training time 0:08:21.557660
+Epoch: 248 Average loss: 106.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 721)
+0/69092	Loss: 102.823
+3200/69092	Loss: 106.464
+6400/69092	Loss: 104.554
+9600/69092	Loss: 106.965
+12800/69092	Loss: 107.599
+16000/69092	Loss: 105.131
+19200/69092	Loss: 105.597
+22400/69092	Loss: 105.915
+25600/69092	Loss: 106.484
+28800/69092	Loss: 106.209
+32000/69092	Loss: 106.675
+35200/69092	Loss: 105.960
+38400/69092	Loss: 106.167
+41600/69092	Loss: 105.320
+44800/69092	Loss: 106.533
+48000/69092	Loss: 105.939
+51200/69092	Loss: 104.978
+54400/69092	Loss: 105.978
+57600/69092	Loss: 104.624
+60800/69092	Loss: 104.004
+64000/69092	Loss: 105.365
+67200/69092	Loss: 106.634
+Training time 0:08:13.500072
+Epoch: 249 Average loss: 105.90
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 722)
+0/69092	Loss: 113.857
+3200/69092	Loss: 106.954
+6400/69092	Loss: 106.274
+9600/69092	Loss: 105.330
+12800/69092	Loss: 106.696
+16000/69092	Loss: 105.045
+19200/69092	Loss: 107.232
+22400/69092	Loss: 105.712
+25600/69092	Loss: 106.354
+28800/69092	Loss: 105.585
+32000/69092	Loss: 107.838
+35200/69092	Loss: 105.021
+38400/69092	Loss: 103.672
+41600/69092	Loss: 106.374
+44800/69092	Loss: 107.960
+48000/69092	Loss: 105.363
+51200/69092	Loss: 105.238
+54400/69092	Loss: 104.889
+57600/69092	Loss: 106.180
+60800/69092	Loss: 106.520
+64000/69092	Loss: 107.406
+67200/69092	Loss: 105.601
+Training time 0:08:42.971794
+Epoch: 250 Average loss: 106.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 723)
+0/69092	Loss: 107.065
+3200/69092	Loss: 106.763
+6400/69092	Loss: 105.972
+9600/69092	Loss: 106.074
+12800/69092	Loss: 105.116
+16000/69092	Loss: 108.422
+19200/69092	Loss: 104.927
+22400/69092	Loss: 106.067
+25600/69092	Loss: 105.028
+28800/69092	Loss: 105.010
+32000/69092	Loss: 106.012
+35200/69092	Loss: 105.863
+38400/69092	Loss: 105.880
+41600/69092	Loss: 106.257
+44800/69092	Loss: 105.749
+48000/69092	Loss: 106.995
+51200/69092	Loss: 105.467
+54400/69092	Loss: 105.615
+57600/69092	Loss: 104.733
+60800/69092	Loss: 106.303
+64000/69092	Loss: 107.540
+67200/69092	Loss: 107.218
+Training time 0:08:42.142851
+Epoch: 251 Average loss: 106.03
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 724)
+0/69092	Loss: 100.747
+3200/69092	Loss: 104.877
+6400/69092	Loss: 107.138
+9600/69092	Loss: 107.771
+12800/69092	Loss: 105.197
+16000/69092	Loss: 107.821
+19200/69092	Loss: 105.907
+22400/69092	Loss: 105.692
+25600/69092	Loss: 106.355
+28800/69092	Loss: 105.775
+32000/69092	Loss: 106.124
+35200/69092	Loss: 105.739
+38400/69092	Loss: 106.951
+41600/69092	Loss: 106.438
+44800/69092	Loss: 105.543
+48000/69092	Loss: 105.639
+51200/69092	Loss: 105.965
+54400/69092	Loss: 107.903
+57600/69092	Loss: 104.385
+60800/69092	Loss: 104.783
+64000/69092	Loss: 107.015
+67200/69092	Loss: 105.066
+Training time 0:08:19.916936
+Epoch: 252 Average loss: 106.11
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 725)
+0/69092	Loss: 100.595
+3200/69092	Loss: 105.333
+6400/69092	Loss: 107.414
+9600/69092	Loss: 106.450
+12800/69092	Loss: 106.517
+16000/69092	Loss: 106.880
+19200/69092	Loss: 105.812
+22400/69092	Loss: 105.439
+25600/69092	Loss: 105.031
+28800/69092	Loss: 106.756
+32000/69092	Loss: 106.972
+35200/69092	Loss: 105.400
+38400/69092	Loss: 106.506
+41600/69092	Loss: 105.780
+44800/69092	Loss: 105.578
+48000/69092	Loss: 105.758
+51200/69092	Loss: 103.878
+54400/69092	Loss: 106.517
+57600/69092	Loss: 106.700
+60800/69092	Loss: 106.032
+64000/69092	Loss: 107.413
+67200/69092	Loss: 104.789
+Training time 0:08:23.023540
+Epoch: 253 Average loss: 106.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 726)
+0/69092	Loss: 115.182
+3200/69092	Loss: 104.397
+6400/69092	Loss: 104.478
+9600/69092	Loss: 107.875
+12800/69092	Loss: 105.375
+16000/69092	Loss: 106.107
+19200/69092	Loss: 104.554
+22400/69092	Loss: 105.063
+25600/69092	Loss: 106.507
+28800/69092	Loss: 105.718
+32000/69092	Loss: 105.850
+35200/69092	Loss: 105.924
+38400/69092	Loss: 105.916
+41600/69092	Loss: 106.853
+44800/69092	Loss: 105.433
+48000/69092	Loss: 106.754
+51200/69092	Loss: 105.738
+54400/69092	Loss: 106.870
+57600/69092	Loss: 104.963
+60800/69092	Loss: 106.767
+64000/69092	Loss: 106.422
+67200/69092	Loss: 107.077
+Training time 0:08:41.310186
+Epoch: 254 Average loss: 105.91
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 727)
+0/69092	Loss: 111.221
+3200/69092	Loss: 104.693
+6400/69092	Loss: 105.202
+9600/69092	Loss: 104.663
+12800/69092	Loss: 104.696
+16000/69092	Loss: 105.940
+19200/69092	Loss: 106.168
+22400/69092	Loss: 107.183
+25600/69092	Loss: 106.230
+28800/69092	Loss: 105.337
+32000/69092	Loss: 104.817
+35200/69092	Loss: 105.210
+38400/69092	Loss: 106.820
+41600/69092	Loss: 105.840
+44800/69092	Loss: 106.921
+48000/69092	Loss: 104.942
+51200/69092	Loss: 104.887
+54400/69092	Loss: 107.172
+57600/69092	Loss: 106.473
+60800/69092	Loss: 105.358
+64000/69092	Loss: 107.162
+67200/69092	Loss: 106.235
+Training time 0:08:50.651075
+Epoch: 255 Average loss: 105.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last' (iter 728)
+0/69092	Loss: 104.860
+3200/69092	Loss: 105.419
+6400/69092	Loss: 104.990
+9600/69092	Loss: 105.173
+12800/69092	Loss: 105.489
+16000/69092	Loss: 107.144
+19200/69092	Loss: 106.267
+22400/69092	Loss: 107.215
+25600/69092	Loss: 107.026
+28800/69092	Loss: 106.891
+32000/69092	Loss: 105.282
+35200/69092	Loss: 105.275
+38400/69092	Loss: 105.454
+41600/69092	Loss: 106.023
+44800/69092	Loss: 106.265
+48000/69092	Loss: 104.114
+51200/69092	Loss: 106.275
diff --git a/OAR.2073654.stderr b/OAR.2073654.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..92461377c1305714c42156039c92dd32bb540f67
--- /dev/null
+++ b/OAR.2073654.stderr
@@ -0,0 +1,3 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+## OAR [2020-07-06 15:43:57] Job 2073654 KILLED ##
diff --git a/OAR.2073654.stdout b/OAR.2073654.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..ba6233289b23e4d6f55b8c3d7441f650889634ff
--- /dev/null
+++ b/OAR.2073654.stdout
@@ -0,0 +1,1516 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64_ls_20', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=20, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+Tesla K40c
+Tesla K80
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=40, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=20, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 773035
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last (iter 306)'
+0/69092	Loss: 103.436
+3200/69092	Loss: 101.891
+6400/69092	Loss: 101.232
+9600/69092	Loss: 100.114
+12800/69092	Loss: 100.473
+16000/69092	Loss: 100.469
+19200/69092	Loss: 101.966
+22400/69092	Loss: 100.943
+25600/69092	Loss: 100.959
+28800/69092	Loss: 100.555
+32000/69092	Loss: 101.914
+35200/69092	Loss: 101.552
+38400/69092	Loss: 100.987
+41600/69092	Loss: 100.993
+44800/69092	Loss: 101.747
+48000/69092	Loss: 100.503
+51200/69092	Loss: 101.382
+54400/69092	Loss: 101.060
+57600/69092	Loss: 101.328
+60800/69092	Loss: 101.804
+64000/69092	Loss: 99.939
+67200/69092	Loss: 101.055
+Training time 0:14:41.787025
+Epoch: 1 Average loss: 101.09
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 307)
+0/69092	Loss: 107.130
+3200/69092	Loss: 101.321
+6400/69092	Loss: 100.395
+9600/69092	Loss: 100.241
+12800/69092	Loss: 100.907
+16000/69092	Loss: 101.341
+19200/69092	Loss: 99.843
+22400/69092	Loss: 100.946
+25600/69092	Loss: 100.380
+28800/69092	Loss: 101.629
+32000/69092	Loss: 102.444
+35200/69092	Loss: 101.570
+38400/69092	Loss: 101.353
+41600/69092	Loss: 101.364
+44800/69092	Loss: 101.641
+48000/69092	Loss: 100.585
+51200/69092	Loss: 100.068
+54400/69092	Loss: 101.052
+57600/69092	Loss: 100.505
+60800/69092	Loss: 101.015
+64000/69092	Loss: 101.804
+67200/69092	Loss: 101.833
+Training time 0:13:48.986240
+Epoch: 2 Average loss: 101.10
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 308)
+0/69092	Loss: 97.897
+3200/69092	Loss: 99.790
+6400/69092	Loss: 100.779
+9600/69092	Loss: 101.454
+12800/69092	Loss: 101.456
+16000/69092	Loss: 100.413
+19200/69092	Loss: 101.386
+22400/69092	Loss: 100.628
+25600/69092	Loss: 102.060
+28800/69092	Loss: 101.975
+32000/69092	Loss: 100.300
+35200/69092	Loss: 100.916
+38400/69092	Loss: 101.092
+41600/69092	Loss: 100.152
+44800/69092	Loss: 100.723
+48000/69092	Loss: 100.422
+51200/69092	Loss: 102.224
+54400/69092	Loss: 101.234
+57600/69092	Loss: 101.301
+60800/69092	Loss: 100.431
+64000/69092	Loss: 100.798
+67200/69092	Loss: 100.829
+Training time 0:13:40.429280
+Epoch: 3 Average loss: 100.97
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 309)
+0/69092	Loss: 104.405
+3200/69092	Loss: 102.697
+6400/69092	Loss: 102.042
+9600/69092	Loss: 99.874
+12800/69092	Loss: 101.562
+16000/69092	Loss: 101.218
+19200/69092	Loss: 99.150
+22400/69092	Loss: 100.849
+25600/69092	Loss: 99.347
+28800/69092	Loss: 102.045
+32000/69092	Loss: 101.202
+35200/69092	Loss: 100.960
+38400/69092	Loss: 100.857
+41600/69092	Loss: 100.561
+44800/69092	Loss: 100.716
+48000/69092	Loss: 101.735
+51200/69092	Loss: 101.473
+54400/69092	Loss: 101.561
+57600/69092	Loss: 101.530
+60800/69092	Loss: 101.593
+64000/69092	Loss: 100.781
+67200/69092	Loss: 102.120
+Training time 0:13:49.228027
+Epoch: 4 Average loss: 101.16
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 310)
+0/69092	Loss: 100.612
+3200/69092	Loss: 100.087
+6400/69092	Loss: 101.472
+9600/69092	Loss: 101.564
+12800/69092	Loss: 102.014
+16000/69092	Loss: 101.146
+19200/69092	Loss: 100.999
+22400/69092	Loss: 99.694
+25600/69092	Loss: 100.075
+28800/69092	Loss: 100.433
+32000/69092	Loss: 101.577
+35200/69092	Loss: 101.377
+38400/69092	Loss: 101.565
+41600/69092	Loss: 101.110
+44800/69092	Loss: 101.574
+48000/69092	Loss: 102.736
+51200/69092	Loss: 101.637
+54400/69092	Loss: 100.963
+57600/69092	Loss: 100.847
+60800/69092	Loss: 100.658
+64000/69092	Loss: 100.277
+67200/69092	Loss: 101.948
+Training time 0:13:47.271542
+Epoch: 5 Average loss: 101.14
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 311)
+0/69092	Loss: 99.503
+3200/69092	Loss: 100.903
+6400/69092	Loss: 100.999
+9600/69092	Loss: 100.163
+12800/69092	Loss: 100.597
+16000/69092	Loss: 102.861
+19200/69092	Loss: 101.342
+22400/69092	Loss: 101.746
+25600/69092	Loss: 100.579
+28800/69092	Loss: 100.999
+32000/69092	Loss: 100.485
+35200/69092	Loss: 100.170
+38400/69092	Loss: 102.094
+41600/69092	Loss: 99.767
+44800/69092	Loss: 101.411
+48000/69092	Loss: 100.740
+51200/69092	Loss: 101.403
+54400/69092	Loss: 100.745
+57600/69092	Loss: 100.775
+60800/69092	Loss: 102.080
+64000/69092	Loss: 99.539
+67200/69092	Loss: 102.890
+Training time 0:13:43.537098
+Epoch: 6 Average loss: 101.04
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 312)
+0/69092	Loss: 93.034
+3200/69092	Loss: 100.929
+6400/69092	Loss: 99.783
+9600/69092	Loss: 101.700
+12800/69092	Loss: 101.977
+16000/69092	Loss: 101.483
+19200/69092	Loss: 101.781
+22400/69092	Loss: 100.891
+25600/69092	Loss: 101.834
+28800/69092	Loss: 101.288
+32000/69092	Loss: 100.274
+35200/69092	Loss: 99.955
+38400/69092	Loss: 100.806
+41600/69092	Loss: 101.287
+44800/69092	Loss: 101.291
+48000/69092	Loss: 101.328
+51200/69092	Loss: 101.429
+54400/69092	Loss: 99.736
+57600/69092	Loss: 100.624
+60800/69092	Loss: 102.407
+64000/69092	Loss: 100.510
+67200/69092	Loss: 100.911
+Training time 0:13:44.307700
+Epoch: 7 Average loss: 101.00
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 313)
+0/69092	Loss: 89.404
+3200/69092	Loss: 102.486
+6400/69092	Loss: 99.687
+9600/69092	Loss: 102.481
+12800/69092	Loss: 100.509
+16000/69092	Loss: 101.168
+19200/69092	Loss: 101.004
+22400/69092	Loss: 99.535
+25600/69092	Loss: 100.197
+28800/69092	Loss: 101.713
+32000/69092	Loss: 100.322
+35200/69092	Loss: 100.941
+38400/69092	Loss: 100.301
+41600/69092	Loss: 101.583
+44800/69092	Loss: 100.323
+48000/69092	Loss: 101.930
+51200/69092	Loss: 99.980
+54400/69092	Loss: 100.723
+57600/69092	Loss: 99.924
+60800/69092	Loss: 100.310
+64000/69092	Loss: 102.018
+67200/69092	Loss: 100.703
+Training time 0:13:46.910893
+Epoch: 8 Average loss: 100.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 314)
+0/69092	Loss: 92.930
+3200/69092	Loss: 100.759
+6400/69092	Loss: 101.740
+9600/69092	Loss: 102.505
+12800/69092	Loss: 100.584
+16000/69092	Loss: 100.649
+19200/69092	Loss: 100.761
+22400/69092	Loss: 101.945
+25600/69092	Loss: 101.388
+28800/69092	Loss: 100.734
+32000/69092	Loss: 99.510
+35200/69092	Loss: 100.671
+38400/69092	Loss: 101.366
+41600/69092	Loss: 101.232
+44800/69092	Loss: 102.137
+48000/69092	Loss: 100.523
+51200/69092	Loss: 99.612
+54400/69092	Loss: 101.236
+57600/69092	Loss: 101.923
+60800/69092	Loss: 100.240
+64000/69092	Loss: 100.809
+67200/69092	Loss: 100.129
+Training time 0:13:44.912871
+Epoch: 9 Average loss: 100.98
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 315)
+0/69092	Loss: 102.599
+3200/69092	Loss: 100.465
+6400/69092	Loss: 100.713
+9600/69092	Loss: 100.518
+12800/69092	Loss: 101.146
+16000/69092	Loss: 101.154
+19200/69092	Loss: 100.163
+22400/69092	Loss: 100.315
+25600/69092	Loss: 100.951
+28800/69092	Loss: 100.877
+32000/69092	Loss: 101.357
+35200/69092	Loss: 101.423
+38400/69092	Loss: 99.401
+41600/69092	Loss: 101.006
+44800/69092	Loss: 100.012
+48000/69092	Loss: 101.520
+51200/69092	Loss: 101.633
+54400/69092	Loss: 101.297
+57600/69092	Loss: 101.751
+60800/69092	Loss: 101.034
+64000/69092	Loss: 101.549
+67200/69092	Loss: 101.087
+Training time 0:13:44.652055
+Epoch: 10 Average loss: 100.92
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 316)
+0/69092	Loss: 92.348
+3200/69092	Loss: 102.245
+6400/69092	Loss: 101.216
+9600/69092	Loss: 99.526
+12800/69092	Loss: 99.655
+16000/69092	Loss: 99.898
+19200/69092	Loss: 101.512
+22400/69092	Loss: 100.677
+25600/69092	Loss: 101.003
+28800/69092	Loss: 101.273
+32000/69092	Loss: 101.460
+35200/69092	Loss: 102.999
+38400/69092	Loss: 101.679
+41600/69092	Loss: 101.618
+44800/69092	Loss: 101.401
+48000/69092	Loss: 102.100
+51200/69092	Loss: 101.394
+54400/69092	Loss: 101.714
+57600/69092	Loss: 99.548
+60800/69092	Loss: 98.904
+64000/69092	Loss: 100.759
+67200/69092	Loss: 101.279
+Training time 0:13:42.005208
+Epoch: 11 Average loss: 101.01
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 317)
+0/69092	Loss: 103.127
+3200/69092	Loss: 101.304
+6400/69092	Loss: 99.571
+9600/69092	Loss: 100.235
+12800/69092	Loss: 100.589
+16000/69092	Loss: 101.852
+19200/69092	Loss: 101.960
+22400/69092	Loss: 99.812
+25600/69092	Loss: 102.380
+28800/69092	Loss: 100.200
+32000/69092	Loss: 100.231
+35200/69092	Loss: 101.429
+38400/69092	Loss: 99.558
+41600/69092	Loss: 102.223
+44800/69092	Loss: 101.304
+48000/69092	Loss: 101.044
+51200/69092	Loss: 100.311
+54400/69092	Loss: 100.586
+57600/69092	Loss: 100.771
+60800/69092	Loss: 100.979
+64000/69092	Loss: 101.382
+67200/69092	Loss: 102.821
+Training time 0:13:43.604928
+Epoch: 12 Average loss: 100.95
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 318)
+0/69092	Loss: 98.660
+3200/69092	Loss: 98.855
+6400/69092	Loss: 100.068
+9600/69092	Loss: 102.204
+12800/69092	Loss: 100.711
+16000/69092	Loss: 100.779
+19200/69092	Loss: 99.195
+22400/69092	Loss: 102.301
+25600/69092	Loss: 101.048
+28800/69092	Loss: 102.352
+32000/69092	Loss: 102.131
+35200/69092	Loss: 102.798
+38400/69092	Loss: 101.116
+41600/69092	Loss: 102.418
+44800/69092	Loss: 101.405
+48000/69092	Loss: 98.969
+51200/69092	Loss: 100.470
+54400/69092	Loss: 98.923
+57600/69092	Loss: 101.077
+60800/69092	Loss: 100.787
+64000/69092	Loss: 99.927
+67200/69092	Loss: 101.746
+Training time 0:13:41.980342
+Epoch: 13 Average loss: 100.94
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 319)
+0/69092	Loss: 98.023
+3200/69092	Loss: 102.193
+6400/69092	Loss: 100.323
+9600/69092	Loss: 100.398
+12800/69092	Loss: 101.151
+16000/69092	Loss: 100.041
+19200/69092	Loss: 102.545
+22400/69092	Loss: 99.132
+25600/69092	Loss: 102.000
+28800/69092	Loss: 100.742
+32000/69092	Loss: 100.574
+35200/69092	Loss: 101.581
+38400/69092	Loss: 100.994
+41600/69092	Loss: 99.856
+44800/69092	Loss: 100.919
+48000/69092	Loss: 99.236
+51200/69092	Loss: 100.868
+54400/69092	Loss: 100.408
+57600/69092	Loss: 100.827
+60800/69092	Loss: 100.282
+64000/69092	Loss: 101.909
+67200/69092	Loss: 100.761
+Training time 0:13:38.303177
+Epoch: 14 Average loss: 100.80
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 320)
+0/69092	Loss: 109.281
+3200/69092	Loss: 100.533
+6400/69092	Loss: 99.538
+9600/69092	Loss: 100.395
+12800/69092	Loss: 100.455
+16000/69092	Loss: 100.452
+19200/69092	Loss: 100.573
+22400/69092	Loss: 101.403
+25600/69092	Loss: 101.141
+28800/69092	Loss: 100.852
+32000/69092	Loss: 100.873
+35200/69092	Loss: 100.685
+38400/69092	Loss: 100.592
+41600/69092	Loss: 100.568
+44800/69092	Loss: 101.289
+48000/69092	Loss: 101.164
+51200/69092	Loss: 101.361
+54400/69092	Loss: 100.941
+57600/69092	Loss: 101.323
+60800/69092	Loss: 100.579
+64000/69092	Loss: 100.892
+67200/69092	Loss: 100.701
+Training time 0:13:40.826917
+Epoch: 15 Average loss: 100.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 321)
+0/69092	Loss: 101.397
+3200/69092	Loss: 101.202
+6400/69092	Loss: 100.958
+9600/69092	Loss: 100.390
+12800/69092	Loss: 101.428
+16000/69092	Loss: 100.071
+19200/69092	Loss: 100.303
+22400/69092	Loss: 98.971
+25600/69092	Loss: 100.058
+28800/69092	Loss: 100.524
+32000/69092	Loss: 101.166
+35200/69092	Loss: 101.840
+38400/69092	Loss: 100.657
+41600/69092	Loss: 102.041
+44800/69092	Loss: 100.348
+48000/69092	Loss: 101.761
+51200/69092	Loss: 100.236
+54400/69092	Loss: 102.768
+57600/69092	Loss: 101.903
+60800/69092	Loss: 100.334
+64000/69092	Loss: 100.594
+67200/69092	Loss: 100.598
+Training time 0:13:42.549648
+Epoch: 16 Average loss: 100.89
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 322)
+0/69092	Loss: 101.384
+3200/69092	Loss: 100.735
+6400/69092	Loss: 102.624
+9600/69092	Loss: 101.360
+12800/69092	Loss: 100.728
+16000/69092	Loss: 99.622
+19200/69092	Loss: 101.134
+22400/69092	Loss: 100.231
+25600/69092	Loss: 102.931
+28800/69092	Loss: 100.630
+32000/69092	Loss: 101.530
+35200/69092	Loss: 99.538
+38400/69092	Loss: 100.677
+41600/69092	Loss: 100.330
+44800/69092	Loss: 100.533
+48000/69092	Loss: 100.834
+51200/69092	Loss: 101.262
+54400/69092	Loss: 101.080
+57600/69092	Loss: 99.789
+60800/69092	Loss: 103.044
+64000/69092	Loss: 101.774
+67200/69092	Loss: 101.678
+Training time 0:13:51.785993
+Epoch: 17 Average loss: 101.06
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 323)
+0/69092	Loss: 96.900
+3200/69092	Loss: 100.394
+6400/69092	Loss: 100.396
+9600/69092	Loss: 100.228
+12800/69092	Loss: 101.286
+16000/69092	Loss: 100.394
+19200/69092	Loss: 100.482
+22400/69092	Loss: 100.136
+25600/69092	Loss: 101.057
+28800/69092	Loss: 101.637
+32000/69092	Loss: 100.654
+35200/69092	Loss: 100.904
+38400/69092	Loss: 101.429
+41600/69092	Loss: 101.235
+44800/69092	Loss: 100.382
+48000/69092	Loss: 101.907
+51200/69092	Loss: 101.232
+54400/69092	Loss: 100.439
+57600/69092	Loss: 100.745
+60800/69092	Loss: 101.506
+64000/69092	Loss: 100.779
+67200/69092	Loss: 100.891
+Training time 0:13:54.479107
+Epoch: 18 Average loss: 100.81
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 324)
+0/69092	Loss: 106.432
+3200/69092	Loss: 101.905
+6400/69092	Loss: 102.005
+9600/69092	Loss: 100.527
+12800/69092	Loss: 101.517
+16000/69092	Loss: 102.610
+19200/69092	Loss: 99.099
+22400/69092	Loss: 100.048
+25600/69092	Loss: 100.255
+28800/69092	Loss: 100.488
+32000/69092	Loss: 100.228
+35200/69092	Loss: 101.847
+38400/69092	Loss: 101.005
+41600/69092	Loss: 100.958
+44800/69092	Loss: 100.345
+48000/69092	Loss: 100.847
+51200/69092	Loss: 99.665
+54400/69092	Loss: 100.755
+57600/69092	Loss: 99.048
+60800/69092	Loss: 100.771
+64000/69092	Loss: 101.709
+67200/69092	Loss: 100.025
+Training time 0:13:44.623544
+Epoch: 19 Average loss: 100.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 325)
+0/69092	Loss: 108.081
+3200/69092	Loss: 100.867
+6400/69092	Loss: 99.876
+9600/69092	Loss: 101.975
+12800/69092	Loss: 100.503
+16000/69092	Loss: 100.244
+19200/69092	Loss: 100.371
+22400/69092	Loss: 100.663
+25600/69092	Loss: 98.655
+28800/69092	Loss: 101.352
+32000/69092	Loss: 100.645
+35200/69092	Loss: 101.024
+38400/69092	Loss: 101.967
+41600/69092	Loss: 99.261
+44800/69092	Loss: 103.108
+48000/69092	Loss: 100.840
+51200/69092	Loss: 100.834
+54400/69092	Loss: 101.388
+57600/69092	Loss: 99.898
+60800/69092	Loss: 100.670
+64000/69092	Loss: 100.716
+67200/69092	Loss: 99.829
+Training time 0:13:46.285635
+Epoch: 20 Average loss: 100.74
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 326)
+0/69092	Loss: 115.593
+3200/69092	Loss: 100.072
+6400/69092	Loss: 99.461
+9600/69092	Loss: 100.909
+12800/69092	Loss: 100.815
+16000/69092	Loss: 101.452
+19200/69092	Loss: 99.734
+22400/69092	Loss: 99.116
+25600/69092	Loss: 99.806
+28800/69092	Loss: 103.116
+32000/69092	Loss: 99.992
+35200/69092	Loss: 99.445
+38400/69092	Loss: 102.130
+41600/69092	Loss: 100.887
+44800/69092	Loss: 100.788
+48000/69092	Loss: 99.998
+51200/69092	Loss: 101.494
+54400/69092	Loss: 103.332
+57600/69092	Loss: 100.992
+60800/69092	Loss: 99.393
+64000/69092	Loss: 102.040
+67200/69092	Loss: 100.811
+Training time 0:13:39.234210
+Epoch: 21 Average loss: 100.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 327)
+0/69092	Loss: 103.422
+3200/69092	Loss: 101.220
+6400/69092	Loss: 99.921
+9600/69092	Loss: 102.307
+12800/69092	Loss: 100.684
+16000/69092	Loss: 100.662
+19200/69092	Loss: 101.321
+22400/69092	Loss: 101.583
+25600/69092	Loss: 100.118
+28800/69092	Loss: 99.843
+32000/69092	Loss: 100.445
+35200/69092	Loss: 99.932
+38400/69092	Loss: 100.984
+41600/69092	Loss: 100.616
+44800/69092	Loss: 100.551
+48000/69092	Loss: 100.435
+51200/69092	Loss: 101.420
+54400/69092	Loss: 100.868
+57600/69092	Loss: 101.580
+60800/69092	Loss: 101.371
+64000/69092	Loss: 100.412
+67200/69092	Loss: 100.385
+Training time 0:13:41.420463
+Epoch: 22 Average loss: 100.82
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 328)
+0/69092	Loss: 101.117
+3200/69092	Loss: 102.322
+6400/69092	Loss: 100.668
+9600/69092	Loss: 100.493
+12800/69092	Loss: 100.947
+16000/69092	Loss: 102.199
+19200/69092	Loss: 100.582
+22400/69092	Loss: 102.171
+25600/69092	Loss: 100.547
+28800/69092	Loss: 98.796
+32000/69092	Loss: 101.258
+35200/69092	Loss: 100.227
+38400/69092	Loss: 100.362
+41600/69092	Loss: 99.823
+44800/69092	Loss: 100.352
+48000/69092	Loss: 101.622
+51200/69092	Loss: 99.726
+54400/69092	Loss: 101.785
+57600/69092	Loss: 100.515
+60800/69092	Loss: 101.281
+64000/69092	Loss: 100.352
+67200/69092	Loss: 101.289
+Training time 0:13:50.142950
+Epoch: 23 Average loss: 100.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 329)
+0/69092	Loss: 97.676
+3200/69092	Loss: 100.696
+6400/69092	Loss: 100.726
+9600/69092	Loss: 101.559
+12800/69092	Loss: 102.584
+16000/69092	Loss: 101.524
+19200/69092	Loss: 100.448
+22400/69092	Loss: 100.422
+25600/69092	Loss: 100.866
+28800/69092	Loss: 101.324
+32000/69092	Loss: 102.293
+35200/69092	Loss: 98.867
+38400/69092	Loss: 100.347
+41600/69092	Loss: 100.123
+44800/69092	Loss: 102.359
+48000/69092	Loss: 100.427
+51200/69092	Loss: 100.088
+54400/69092	Loss: 100.438
+57600/69092	Loss: 99.811
+60800/69092	Loss: 100.910
+64000/69092	Loss: 100.345
+67200/69092	Loss: 100.536
+Training time 0:13:40.610892
+Epoch: 24 Average loss: 100.77
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 330)
+0/69092	Loss: 94.685
+3200/69092	Loss: 100.876
+6400/69092	Loss: 102.026
+9600/69092	Loss: 100.950
+12800/69092	Loss: 99.815
+16000/69092	Loss: 100.259
+19200/69092	Loss: 101.200
+22400/69092	Loss: 99.880
+25600/69092	Loss: 99.571
+28800/69092	Loss: 99.784
+32000/69092	Loss: 101.550
+35200/69092	Loss: 100.886
+38400/69092	Loss: 100.867
+41600/69092	Loss: 101.638
+44800/69092	Loss: 99.415
+48000/69092	Loss: 101.404
+51200/69092	Loss: 101.102
+54400/69092	Loss: 101.780
+57600/69092	Loss: 102.143
+60800/69092	Loss: 99.996
+64000/69092	Loss: 100.388
+67200/69092	Loss: 101.842
+Training time 0:13:46.956463
+Epoch: 25 Average loss: 100.85
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 331)
+0/69092	Loss: 95.708
+3200/69092	Loss: 100.578
+6400/69092	Loss: 101.617
+9600/69092	Loss: 101.631
+12800/69092	Loss: 99.029
+16000/69092	Loss: 101.988
+19200/69092	Loss: 101.572
+22400/69092	Loss: 101.821
+25600/69092	Loss: 99.838
+28800/69092	Loss: 99.405
+32000/69092	Loss: 99.064
+35200/69092	Loss: 101.492
+38400/69092	Loss: 102.232
+41600/69092	Loss: 99.298
+44800/69092	Loss: 103.041
+48000/69092	Loss: 100.975
+51200/69092	Loss: 101.170
+54400/69092	Loss: 99.590
+57600/69092	Loss: 100.178
+60800/69092	Loss: 101.634
+64000/69092	Loss: 100.417
+67200/69092	Loss: 100.651
+Training time 0:13:48.040434
+Epoch: 26 Average loss: 100.79
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 332)
+0/69092	Loss: 103.689
+3200/69092	Loss: 101.952
+6400/69092	Loss: 99.726
+9600/69092	Loss: 99.885
+12800/69092	Loss: 100.487
+16000/69092	Loss: 100.782
+19200/69092	Loss: 102.541
+22400/69092	Loss: 99.627
+25600/69092	Loss: 101.096
+28800/69092	Loss: 102.418
+32000/69092	Loss: 101.862
+35200/69092	Loss: 100.870
+38400/69092	Loss: 102.061
+41600/69092	Loss: 100.232
+44800/69092	Loss: 99.418
+48000/69092	Loss: 100.322
+51200/69092	Loss: 100.581
+54400/69092	Loss: 99.918
+57600/69092	Loss: 100.539
+60800/69092	Loss: 99.828
+64000/69092	Loss: 100.200
+67200/69092	Loss: 99.650
+Training time 0:13:44.182382
+Epoch: 27 Average loss: 100.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 333)
+0/69092	Loss: 115.419
+3200/69092	Loss: 99.606
+6400/69092	Loss: 101.413
+9600/69092	Loss: 100.534
+12800/69092	Loss: 100.875
+16000/69092	Loss: 100.690
+19200/69092	Loss: 101.778
+22400/69092	Loss: 100.888
+25600/69092	Loss: 100.077
+28800/69092	Loss: 100.943
+32000/69092	Loss: 101.113
+35200/69092	Loss: 99.948
+38400/69092	Loss: 100.024
+41600/69092	Loss: 101.024
+44800/69092	Loss: 100.483
+48000/69092	Loss: 99.951
+51200/69092	Loss: 100.460
+54400/69092	Loss: 99.669
+57600/69092	Loss: 101.102
+60800/69092	Loss: 101.202
+64000/69092	Loss: 100.955
+67200/69092	Loss: 101.127
+Training time 0:13:55.521302
+Epoch: 28 Average loss: 100.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 334)
+0/69092	Loss: 95.009
+3200/69092	Loss: 101.236
+6400/69092	Loss: 101.021
+9600/69092	Loss: 101.044
+12800/69092	Loss: 100.359
+16000/69092	Loss: 99.065
+19200/69092	Loss: 101.529
+22400/69092	Loss: 101.653
+25600/69092	Loss: 100.111
+28800/69092	Loss: 101.576
+32000/69092	Loss: 99.921
+35200/69092	Loss: 100.603
+38400/69092	Loss: 101.467
+41600/69092	Loss: 101.212
+44800/69092	Loss: 102.408
+48000/69092	Loss: 101.539
+51200/69092	Loss: 102.248
+54400/69092	Loss: 99.994
+57600/69092	Loss: 99.332
+60800/69092	Loss: 100.135
+64000/69092	Loss: 100.359
+67200/69092	Loss: 100.526
+Training time 0:13:46.954900
+Epoch: 29 Average loss: 100.78
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 335)
+0/69092	Loss: 97.568
+3200/69092	Loss: 100.509
+6400/69092	Loss: 101.608
+9600/69092	Loss: 101.264
+12800/69092	Loss: 100.528
+16000/69092	Loss: 101.217
+19200/69092	Loss: 99.940
+22400/69092	Loss: 100.970
+25600/69092	Loss: 100.889
+28800/69092	Loss: 101.200
+32000/69092	Loss: 101.455
+35200/69092	Loss: 101.029
+38400/69092	Loss: 100.961
+41600/69092	Loss: 100.779
+44800/69092	Loss: 100.871
+48000/69092	Loss: 100.535
+51200/69092	Loss: 102.219
+54400/69092	Loss: 100.587
+57600/69092	Loss: 100.572
+60800/69092	Loss: 100.140
+64000/69092	Loss: 100.289
+67200/69092	Loss: 100.067
+Training time 0:13:45.601360
+Epoch: 30 Average loss: 100.84
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 336)
+0/69092	Loss: 102.497
+3200/69092	Loss: 99.248
+6400/69092	Loss: 100.866
+9600/69092	Loss: 100.674
+12800/69092	Loss: 101.074
+16000/69092	Loss: 100.521
+19200/69092	Loss: 99.516
+22400/69092	Loss: 99.370
+25600/69092	Loss: 100.613
+28800/69092	Loss: 101.589
+32000/69092	Loss: 100.437
+35200/69092	Loss: 100.770
+38400/69092	Loss: 100.437
+41600/69092	Loss: 99.955
+44800/69092	Loss: 100.674
+48000/69092	Loss: 102.203
+51200/69092	Loss: 102.422
+54400/69092	Loss: 102.031
+57600/69092	Loss: 100.293
+60800/69092	Loss: 99.808
+64000/69092	Loss: 101.312
+67200/69092	Loss: 98.753
+Training time 0:13:44.669288
+Epoch: 31 Average loss: 100.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 337)
+0/69092	Loss: 106.944
+3200/69092	Loss: 101.007
+6400/69092	Loss: 100.195
+9600/69092	Loss: 101.764
+12800/69092	Loss: 101.632
+16000/69092	Loss: 100.218
+19200/69092	Loss: 100.050
+22400/69092	Loss: 100.597
+25600/69092	Loss: 100.329
+28800/69092	Loss: 100.744
+32000/69092	Loss: 99.927
+35200/69092	Loss: 101.054
+38400/69092	Loss: 100.543
+41600/69092	Loss: 100.871
+44800/69092	Loss: 100.249
+48000/69092	Loss: 101.372
+51200/69092	Loss: 101.038
+54400/69092	Loss: 100.213
+57600/69092	Loss: 101.135
+60800/69092	Loss: 101.279
+64000/69092	Loss: 100.189
+67200/69092	Loss: 100.705
+Training time 0:13:48.211620
+Epoch: 32 Average loss: 100.71
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 338)
+0/69092	Loss: 105.057
+3200/69092	Loss: 101.411
+6400/69092	Loss: 101.123
+9600/69092	Loss: 101.170
+12800/69092	Loss: 100.024
+16000/69092	Loss: 100.326
+19200/69092	Loss: 99.945
+22400/69092	Loss: 98.713
+25600/69092	Loss: 99.956
+28800/69092	Loss: 100.547
+32000/69092	Loss: 101.102
+35200/69092	Loss: 100.738
+38400/69092	Loss: 100.379
+41600/69092	Loss: 99.797
+44800/69092	Loss: 101.107
+48000/69092	Loss: 101.870
+51200/69092	Loss: 100.093
+54400/69092	Loss: 102.743
+57600/69092	Loss: 100.909
+60800/69092	Loss: 100.894
+64000/69092	Loss: 101.919
+67200/69092	Loss: 99.192
+Training time 0:13:48.969388
+Epoch: 33 Average loss: 100.71
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 339)
+0/69092	Loss: 96.143
+3200/69092	Loss: 99.165
+6400/69092	Loss: 99.795
+9600/69092	Loss: 99.921
+12800/69092	Loss: 100.474
+16000/69092	Loss: 100.559
+19200/69092	Loss: 100.752
+22400/69092	Loss: 100.915
+25600/69092	Loss: 101.454
+28800/69092	Loss: 100.202
+32000/69092	Loss: 99.591
+35200/69092	Loss: 102.369
+38400/69092	Loss: 101.682
+41600/69092	Loss: 100.845
+44800/69092	Loss: 100.682
+48000/69092	Loss: 100.252
+51200/69092	Loss: 100.750
+54400/69092	Loss: 99.184
+57600/69092	Loss: 99.807
+60800/69092	Loss: 101.246
+64000/69092	Loss: 101.431
+67200/69092	Loss: 101.695
+Training time 0:13:46.804170
+Epoch: 34 Average loss: 100.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 340)
+0/69092	Loss: 102.265
+3200/69092	Loss: 99.336
+6400/69092	Loss: 100.856
+9600/69092	Loss: 100.959
+12800/69092	Loss: 99.595
+16000/69092	Loss: 101.360
+19200/69092	Loss: 99.363
+22400/69092	Loss: 100.603
+25600/69092	Loss: 99.662
+28800/69092	Loss: 100.459
+32000/69092	Loss: 100.961
+35200/69092	Loss: 102.079
+38400/69092	Loss: 102.189
+41600/69092	Loss: 100.266
+44800/69092	Loss: 100.887
+48000/69092	Loss: 100.614
+51200/69092	Loss: 99.363
+54400/69092	Loss: 102.400
+57600/69092	Loss: 99.713
+60800/69092	Loss: 100.407
+64000/69092	Loss: 99.955
+67200/69092	Loss: 101.930
+Training time 0:13:50.281189
+Epoch: 35 Average loss: 100.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 341)
+0/69092	Loss: 91.077
+3200/69092	Loss: 99.407
+6400/69092	Loss: 100.558
+9600/69092	Loss: 99.682
+12800/69092	Loss: 100.872
+16000/69092	Loss: 101.568
+19200/69092	Loss: 100.120
+22400/69092	Loss: 100.198
+25600/69092	Loss: 100.478
+28800/69092	Loss: 100.683
+32000/69092	Loss: 100.751
+35200/69092	Loss: 101.349
+38400/69092	Loss: 99.203
+41600/69092	Loss: 100.295
+44800/69092	Loss: 100.931
+48000/69092	Loss: 102.029
+51200/69092	Loss: 101.676
+54400/69092	Loss: 100.771
+57600/69092	Loss: 100.971
+60800/69092	Loss: 100.550
+64000/69092	Loss: 100.418
+67200/69092	Loss: 100.937
+Training time 0:13:46.709090
+Epoch: 36 Average loss: 100.64
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 342)
+0/69092	Loss: 100.407
+3200/69092	Loss: 101.588
+6400/69092	Loss: 99.413
+9600/69092	Loss: 99.810
+12800/69092	Loss: 100.302
+16000/69092	Loss: 99.598
+19200/69092	Loss: 99.751
+22400/69092	Loss: 101.144
+25600/69092	Loss: 101.085
+28800/69092	Loss: 99.240
+32000/69092	Loss: 99.390
+35200/69092	Loss: 99.293
+38400/69092	Loss: 102.304
+41600/69092	Loss: 101.368
+44800/69092	Loss: 101.371
+48000/69092	Loss: 102.314
+51200/69092	Loss: 102.150
+54400/69092	Loss: 101.411
+57600/69092	Loss: 98.967
+60800/69092	Loss: 100.610
+64000/69092	Loss: 101.944
+67200/69092	Loss: 100.726
+Training time 0:13:45.485489
+Epoch: 37 Average loss: 100.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 343)
+0/69092	Loss: 104.606
+3200/69092	Loss: 101.576
+6400/69092	Loss: 99.949
+9600/69092	Loss: 99.341
+12800/69092	Loss: 99.824
+16000/69092	Loss: 101.046
+19200/69092	Loss: 101.872
+22400/69092	Loss: 100.617
+25600/69092	Loss: 102.134
+28800/69092	Loss: 100.201
+32000/69092	Loss: 100.859
+35200/69092	Loss: 99.919
+38400/69092	Loss: 100.106
+41600/69092	Loss: 101.852
+44800/69092	Loss: 101.565
+48000/69092	Loss: 100.622
+51200/69092	Loss: 100.042
+54400/69092	Loss: 100.122
+57600/69092	Loss: 99.449
+60800/69092	Loss: 99.677
+64000/69092	Loss: 101.347
+67200/69092	Loss: 101.118
+Training time 0:13:42.956023
+Epoch: 38 Average loss: 100.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 344)
+0/69092	Loss: 102.286
+3200/69092	Loss: 101.637
+6400/69092	Loss: 101.905
+9600/69092	Loss: 99.692
+12800/69092	Loss: 101.770
+16000/69092	Loss: 101.143
+19200/69092	Loss: 99.607
+22400/69092	Loss: 99.366
+25600/69092	Loss: 101.293
+28800/69092	Loss: 100.114
+32000/69092	Loss: 100.635
+35200/69092	Loss: 101.462
+38400/69092	Loss: 101.717
+41600/69092	Loss: 100.653
+44800/69092	Loss: 101.033
+48000/69092	Loss: 100.163
+51200/69092	Loss: 100.070
+54400/69092	Loss: 99.830
+57600/69092	Loss: 100.736
+60800/69092	Loss: 100.665
+64000/69092	Loss: 98.934
+67200/69092	Loss: 100.187
+Training time 0:13:46.915183
+Epoch: 39 Average loss: 100.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 345)
+0/69092	Loss: 103.864
+3200/69092	Loss: 100.026
+6400/69092	Loss: 101.029
+9600/69092	Loss: 100.974
+12800/69092	Loss: 100.535
+16000/69092	Loss: 101.225
+19200/69092	Loss: 100.081
+22400/69092	Loss: 100.278
+25600/69092	Loss: 101.053
+28800/69092	Loss: 100.120
+32000/69092	Loss: 99.946
+35200/69092	Loss: 100.005
+38400/69092	Loss: 101.667
+41600/69092	Loss: 101.446
+44800/69092	Loss: 100.376
+48000/69092	Loss: 100.063
+51200/69092	Loss: 101.316
+54400/69092	Loss: 100.083
+57600/69092	Loss: 101.342
+60800/69092	Loss: 100.845
+64000/69092	Loss: 100.255
+67200/69092	Loss: 101.640
+Training time 0:13:54.693774
+Epoch: 40 Average loss: 100.66
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 346)
+0/69092	Loss: 95.797
+3200/69092	Loss: 100.685
+6400/69092	Loss: 99.963
+9600/69092	Loss: 98.557
+12800/69092	Loss: 101.479
+16000/69092	Loss: 101.028
+19200/69092	Loss: 100.734
+22400/69092	Loss: 101.016
+25600/69092	Loss: 101.209
+28800/69092	Loss: 99.807
+32000/69092	Loss: 100.774
+35200/69092	Loss: 100.273
+38400/69092	Loss: 100.478
+41600/69092	Loss: 100.282
+44800/69092	Loss: 100.459
+48000/69092	Loss: 99.303
+51200/69092	Loss: 100.207
+54400/69092	Loss: 101.014
+57600/69092	Loss: 101.858
+60800/69092	Loss: 99.894
+64000/69092	Loss: 101.244
+67200/69092	Loss: 100.885
+Training time 0:13:43.538655
+Epoch: 41 Average loss: 100.54
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 347)
+0/69092	Loss: 86.912
+3200/69092	Loss: 100.820
+6400/69092	Loss: 100.731
+9600/69092	Loss: 101.455
+12800/69092	Loss: 100.516
+16000/69092	Loss: 101.065
+19200/69092	Loss: 100.845
+22400/69092	Loss: 100.765
+25600/69092	Loss: 100.414
+28800/69092	Loss: 99.092
+32000/69092	Loss: 101.805
+35200/69092	Loss: 101.380
+38400/69092	Loss: 100.966
+41600/69092	Loss: 101.460
+44800/69092	Loss: 102.057
+48000/69092	Loss: 101.760
+51200/69092	Loss: 100.726
+54400/69092	Loss: 100.003
+57600/69092	Loss: 100.214
+60800/69092	Loss: 99.511
+64000/69092	Loss: 100.547
+67200/69092	Loss: 99.267
+Training time 0:13:43.149858
+Epoch: 42 Average loss: 100.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 348)
+0/69092	Loss: 97.847
+3200/69092	Loss: 100.792
+6400/69092	Loss: 98.761
+9600/69092	Loss: 99.049
+12800/69092	Loss: 101.049
+16000/69092	Loss: 100.065
+19200/69092	Loss: 101.160
+22400/69092	Loss: 100.325
+25600/69092	Loss: 102.291
+28800/69092	Loss: 100.398
+32000/69092	Loss: 100.803
+35200/69092	Loss: 99.658
+38400/69092	Loss: 98.757
+41600/69092	Loss: 102.815
+44800/69092	Loss: 100.821
+48000/69092	Loss: 99.938
+51200/69092	Loss: 101.464
+54400/69092	Loss: 100.865
+57600/69092	Loss: 100.684
+60800/69092	Loss: 99.620
+64000/69092	Loss: 101.463
+67200/69092	Loss: 100.893
+Training time 0:13:42.241883
+Epoch: 43 Average loss: 100.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 349)
+0/69092	Loss: 101.090
+3200/69092	Loss: 100.023
+6400/69092	Loss: 101.341
+9600/69092	Loss: 100.497
+12800/69092	Loss: 101.284
+16000/69092	Loss: 100.879
+19200/69092	Loss: 102.923
+22400/69092	Loss: 99.894
+25600/69092	Loss: 100.222
+28800/69092	Loss: 100.785
+32000/69092	Loss: 100.263
+35200/69092	Loss: 99.577
+38400/69092	Loss: 100.231
+41600/69092	Loss: 98.636
+44800/69092	Loss: 101.394
+48000/69092	Loss: 99.093
+51200/69092	Loss: 99.776
+54400/69092	Loss: 99.552
+57600/69092	Loss: 101.132
+60800/69092	Loss: 100.358
+64000/69092	Loss: 101.070
+67200/69092	Loss: 99.866
+Training time 0:13:49.832824
+Epoch: 44 Average loss: 100.45
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 350)
+0/69092	Loss: 102.602
+3200/69092	Loss: 100.804
+6400/69092	Loss: 99.065
+9600/69092	Loss: 100.865
+12800/69092	Loss: 100.152
+16000/69092	Loss: 101.009
+19200/69092	Loss: 99.823
+22400/69092	Loss: 101.312
+25600/69092	Loss: 100.640
+28800/69092	Loss: 101.284
+32000/69092	Loss: 101.579
+35200/69092	Loss: 101.127
+38400/69092	Loss: 100.654
+41600/69092	Loss: 100.400
+44800/69092	Loss: 100.680
+48000/69092	Loss: 100.607
+51200/69092	Loss: 100.626
+54400/69092	Loss: 99.207
+57600/69092	Loss: 101.036
+60800/69092	Loss: 101.112
+64000/69092	Loss: 100.693
+67200/69092	Loss: 99.929
+Training time 0:13:53.529081
+Epoch: 45 Average loss: 100.61
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 351)
+0/69092	Loss: 100.066
+3200/69092	Loss: 99.912
+6400/69092	Loss: 101.233
+9600/69092	Loss: 99.804
+12800/69092	Loss: 102.190
+16000/69092	Loss: 99.184
+19200/69092	Loss: 101.650
+22400/69092	Loss: 100.873
+25600/69092	Loss: 100.475
+28800/69092	Loss: 100.704
+32000/69092	Loss: 100.968
+35200/69092	Loss: 101.267
+38400/69092	Loss: 100.878
+41600/69092	Loss: 100.626
+44800/69092	Loss: 101.391
+48000/69092	Loss: 101.039
+51200/69092	Loss: 100.021
+54400/69092	Loss: 101.445
+57600/69092	Loss: 98.989
+60800/69092	Loss: 100.863
+64000/69092	Loss: 100.098
+67200/69092	Loss: 101.075
+Training time 0:13:41.063634
+Epoch: 46 Average loss: 100.70
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 352)
+0/69092	Loss: 107.767
+3200/69092	Loss: 100.035
+6400/69092	Loss: 100.032
+9600/69092	Loss: 100.271
+12800/69092	Loss: 99.648
+16000/69092	Loss: 100.324
+19200/69092	Loss: 100.401
+22400/69092	Loss: 99.610
+25600/69092	Loss: 100.587
+28800/69092	Loss: 101.548
+32000/69092	Loss: 100.786
+35200/69092	Loss: 101.132
+38400/69092	Loss: 100.279
+41600/69092	Loss: 102.115
+44800/69092	Loss: 101.417
+48000/69092	Loss: 99.832
+51200/69092	Loss: 100.492
+54400/69092	Loss: 99.372
+57600/69092	Loss: 101.261
+60800/69092	Loss: 99.410
+64000/69092	Loss: 100.038
+67200/69092	Loss: 100.951
+Training time 0:13:49.550724
+Epoch: 47 Average loss: 100.51
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 353)
+0/69092	Loss: 93.837
+3200/69092	Loss: 100.101
+6400/69092	Loss: 100.211
+9600/69092	Loss: 100.170
+12800/69092	Loss: 100.578
+16000/69092	Loss: 101.474
+19200/69092	Loss: 100.247
+22400/69092	Loss: 101.133
+25600/69092	Loss: 100.646
+28800/69092	Loss: 100.263
+32000/69092	Loss: 98.845
+35200/69092	Loss: 99.886
+38400/69092	Loss: 100.471
+41600/69092	Loss: 99.829
+44800/69092	Loss: 100.039
+48000/69092	Loss: 100.441
+51200/69092	Loss: 99.633
+54400/69092	Loss: 100.533
+57600/69092	Loss: 102.072
+60800/69092	Loss: 102.218
+64000/69092	Loss: 99.556
+67200/69092	Loss: 102.889
+Training time 0:13:50.161023
+Epoch: 48 Average loss: 100.56
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 354)
+0/69092	Loss: 100.686
+3200/69092	Loss: 100.585
+6400/69092	Loss: 100.088
+9600/69092	Loss: 99.718
+12800/69092	Loss: 99.970
+16000/69092	Loss: 99.199
+19200/69092	Loss: 101.050
+22400/69092	Loss: 101.403
+25600/69092	Loss: 100.966
+28800/69092	Loss: 99.846
+32000/69092	Loss: 101.012
+35200/69092	Loss: 101.104
+38400/69092	Loss: 99.477
+41600/69092	Loss: 99.318
+44800/69092	Loss: 99.971
+48000/69092	Loss: 101.069
+51200/69092	Loss: 99.977
+54400/69092	Loss: 100.429
+57600/69092	Loss: 100.081
+60800/69092	Loss: 100.556
+64000/69092	Loss: 101.308
+67200/69092	Loss: 100.124
+Training time 0:13:47.040809
+Epoch: 49 Average loss: 100.37
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 355)
+0/69092	Loss: 89.059
+3200/69092	Loss: 101.336
+6400/69092	Loss: 101.861
+9600/69092	Loss: 100.589
+12800/69092	Loss: 100.375
+16000/69092	Loss: 100.899
+19200/69092	Loss: 99.267
+22400/69092	Loss: 102.534
+25600/69092	Loss: 100.905
+28800/69092	Loss: 100.869
+32000/69092	Loss: 99.325
+35200/69092	Loss: 100.350
+38400/69092	Loss: 100.475
+41600/69092	Loss: 100.603
+44800/69092	Loss: 98.825
+48000/69092	Loss: 100.561
+51200/69092	Loss: 100.774
+54400/69092	Loss: 100.773
+57600/69092	Loss: 101.630
+60800/69092	Loss: 101.062
+64000/69092	Loss: 101.236
+67200/69092	Loss: 100.310
+Training time 0:13:43.005405
+Epoch: 50 Average loss: 100.65
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 356)
+0/69092	Loss: 91.132
+3200/69092	Loss: 99.519
+6400/69092	Loss: 100.225
+9600/69092	Loss: 101.541
+12800/69092	Loss: 101.806
+16000/69092	Loss: 99.941
+19200/69092	Loss: 101.028
+22400/69092	Loss: 100.086
+25600/69092	Loss: 101.582
+28800/69092	Loss: 100.797
+32000/69092	Loss: 100.452
+35200/69092	Loss: 99.772
+38400/69092	Loss: 99.878
+41600/69092	Loss: 100.222
+44800/69092	Loss: 100.721
+48000/69092	Loss: 100.135
+51200/69092	Loss: 100.271
+54400/69092	Loss: 100.150
+57600/69092	Loss: 99.640
+60800/69092	Loss: 99.987
+64000/69092	Loss: 100.358
+67200/69092	Loss: 100.402
+Training time 0:13:49.531916
+Epoch: 51 Average loss: 100.42
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 357)
+0/69092	Loss: 105.467
+3200/69092	Loss: 101.626
+6400/69092	Loss: 101.443
+9600/69092	Loss: 99.973
+12800/69092	Loss: 100.457
+16000/69092	Loss: 100.529
+19200/69092	Loss: 100.246
+22400/69092	Loss: 101.710
+25600/69092	Loss: 101.091
+28800/69092	Loss: 100.090
+32000/69092	Loss: 100.719
+35200/69092	Loss: 99.877
+38400/69092	Loss: 102.515
+41600/69092	Loss: 101.461
+44800/69092	Loss: 100.760
+48000/69092	Loss: 98.784
+51200/69092	Loss: 100.719
+54400/69092	Loss: 99.888
+57600/69092	Loss: 99.288
+60800/69092	Loss: 100.307
+64000/69092	Loss: 100.025
+67200/69092	Loss: 100.322
+Training time 0:13:44.136672
+Epoch: 52 Average loss: 100.58
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 358)
+0/69092	Loss: 103.413
+3200/69092	Loss: 101.116
+6400/69092	Loss: 99.892
+9600/69092	Loss: 100.741
+12800/69092	Loss: 100.848
+16000/69092	Loss: 101.090
+19200/69092	Loss: 100.641
+22400/69092	Loss: 100.172
+25600/69092	Loss: 100.832
+28800/69092	Loss: 100.282
+32000/69092	Loss: 98.993
+35200/69092	Loss: 100.923
+38400/69092	Loss: 99.936
+41600/69092	Loss: 101.969
+44800/69092	Loss: 100.839
+48000/69092	Loss: 98.820
+51200/69092	Loss: 100.309
+54400/69092	Loss: 101.948
+57600/69092	Loss: 101.291
+60800/69092	Loss: 99.798
+64000/69092	Loss: 100.224
+67200/69092	Loss: 99.963
+Training time 0:13:44.166708
+Epoch: 53 Average loss: 100.50
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 359)
+0/69092	Loss: 100.345
+3200/69092	Loss: 100.271
+6400/69092	Loss: 100.389
+9600/69092	Loss: 99.517
+12800/69092	Loss: 99.882
+16000/69092	Loss: 100.379
+19200/69092	Loss: 100.314
+22400/69092	Loss: 101.294
+25600/69092	Loss: 100.095
+28800/69092	Loss: 100.261
+32000/69092	Loss: 100.296
+35200/69092	Loss: 99.492
+38400/69092	Loss: 100.098
+41600/69092	Loss: 99.006
+44800/69092	Loss: 100.877
+48000/69092	Loss: 99.248
+51200/69092	Loss: 103.000
+54400/69092	Loss: 101.639
+57600/69092	Loss: 100.030
+60800/69092	Loss: 101.416
+64000/69092	Loss: 101.094
+67200/69092	Loss: 100.794
+Training time 0:13:50.242757
+Epoch: 54 Average loss: 100.46
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 360)
+0/69092	Loss: 98.868
+3200/69092	Loss: 99.569
+6400/69092	Loss: 99.254
+9600/69092	Loss: 101.088
+12800/69092	Loss: 100.279
+16000/69092	Loss: 100.382
+19200/69092	Loss: 100.065
+22400/69092	Loss: 100.891
+25600/69092	Loss: 100.505
+28800/69092	Loss: 101.372
+32000/69092	Loss: 100.538
+35200/69092	Loss: 100.650
+38400/69092	Loss: 100.566
+41600/69092	Loss: 100.490
+44800/69092	Loss: 100.784
+48000/69092	Loss: 99.588
+51200/69092	Loss: 99.606
+54400/69092	Loss: 100.486
+57600/69092	Loss: 100.960
+60800/69092	Loss: 100.114
+64000/69092	Loss: 101.671
+67200/69092	Loss: 100.957
+Training time 0:13:52.126694
+Epoch: 55 Average loss: 100.49
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 361)
+0/69092	Loss: 104.398
+3200/69092	Loss: 100.300
+6400/69092	Loss: 98.830
+9600/69092	Loss: 100.375
+12800/69092	Loss: 99.873
+16000/69092	Loss: 99.702
+19200/69092	Loss: 100.963
+22400/69092	Loss: 101.926
+25600/69092	Loss: 101.091
+28800/69092	Loss: 99.871
+32000/69092	Loss: 99.574
+35200/69092	Loss: 100.283
+38400/69092	Loss: 100.876
+41600/69092	Loss: 101.385
+44800/69092	Loss: 101.390
+48000/69092	Loss: 100.784
+51200/69092	Loss: 99.778
+54400/69092	Loss: 100.156
+57600/69092	Loss: 100.555
+60800/69092	Loss: 100.305
+64000/69092	Loss: 100.260
+67200/69092	Loss: 99.962
+Training time 0:13:57.916502
+Epoch: 56 Average loss: 100.43
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 362)
+0/69092	Loss: 104.034
+3200/69092	Loss: 101.533
+6400/69092	Loss: 100.483
+9600/69092	Loss: 99.607
+12800/69092	Loss: 99.642
+16000/69092	Loss: 102.000
+19200/69092	Loss: 100.447
+22400/69092	Loss: 101.309
+25600/69092	Loss: 100.319
+28800/69092	Loss: 98.204
+32000/69092	Loss: 100.233
+35200/69092	Loss: 100.042
+38400/69092	Loss: 99.224
+41600/69092	Loss: 99.368
+44800/69092	Loss: 101.921
+48000/69092	Loss: 99.659
+51200/69092	Loss: 100.453
+54400/69092	Loss: 97.972
+57600/69092	Loss: 101.011
+60800/69092	Loss: 101.066
+64000/69092	Loss: 101.635
+67200/69092	Loss: 100.867
+Training time 0:13:41.192453
+Epoch: 57 Average loss: 100.37
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 363)
+0/69092	Loss: 107.364
+3200/69092	Loss: 101.032
+6400/69092	Loss: 98.642
+9600/69092	Loss: 99.176
+12800/69092	Loss: 99.515
+16000/69092	Loss: 100.130
+19200/69092	Loss: 99.074
+22400/69092	Loss: 100.887
+25600/69092	Loss: 100.365
+28800/69092	Loss: 100.932
+32000/69092	Loss: 99.809
+35200/69092	Loss: 100.467
+38400/69092	Loss: 101.305
+41600/69092	Loss: 100.963
+44800/69092	Loss: 102.353
+48000/69092	Loss: 101.274
+51200/69092	Loss: 101.449
+54400/69092	Loss: 99.864
+57600/69092	Loss: 99.350
+60800/69092	Loss: 99.826
+64000/69092	Loss: 100.279
+67200/69092	Loss: 100.586
+Training time 0:13:43.275302
+Epoch: 58 Average loss: 100.40
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last' (iter 364)
+0/69092	Loss: 110.838
+3200/69092	Loss: 101.059
+6400/69092	Loss: 100.328
+9600/69092	Loss: 100.405
+12800/69092	Loss: 99.802
+16000/69092	Loss: 100.925
+19200/69092	Loss: 100.708
+22400/69092	Loss: 98.793
+25600/69092	Loss: 99.593
+28800/69092	Loss: 100.162
+32000/69092	Loss: 99.660
+35200/69092	Loss: 100.428
+38400/69092	Loss: 101.090
+41600/69092	Loss: 100.439
+44800/69092	Loss: 99.765
+48000/69092	Loss: 101.605
+51200/69092	Loss: 101.158
+54400/69092	Loss: 100.832
+57600/69092	Loss: 101.225
diff --git a/OAR.2073655.stderr b/OAR.2073655.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..a02fd1a3ff50d0720544966e5f0b0942dd7a795d
--- /dev/null
+++ b/OAR.2073655.stderr
@@ -0,0 +1,16 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py:26: UserWarning: 
+    There is an imbalance between your GPUs. You may want to exclude GPU 1 which
+    has less than 75% of the memory or cores of GPU 0. You can do so by setting
+    the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES
+    environment variable.
+  warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))
+Traceback (most recent call last):
+  File "main.py", line 154, in <module>
+    main(args)
+  File "main.py", line 87, in main
+    beta=args.beta)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 75, in __init__
+    self.load_checkpoint(self.ckpt_name)
+  File "/data1/data/expes/julien.dejasmin/Thesis/Pytorch_CNN_mixt_representation/utils/training.py", line 417, in load_checkpoint
+    self.mean_epoch_loss = checkpoint['loss']
+KeyError: 'loss'
diff --git a/OAR.2073655.stdout b/OAR.2073655.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..7b546397f420f76bbcc49d7999567b8941791a7e
--- /dev/null
+++ b/OAR.2073655.stdout
@@ -0,0 +1,46 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64_ls_10_lr_5e_4', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=5e-05, nb_filter_conv1=32, nb_filter_conv2=32, nb_filter_conv3=64, nb_filter_conv4=64, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+Tesla K40c
+Tesla K20m
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(64, 256, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=256, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=256, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(256, 64, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(32, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(32, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 765335
+don't use continuous capacity
diff --git a/OAR.2073656.stderr b/OAR.2073656.stderr
new file mode 100644
index 0000000000000000000000000000000000000000..227f3eb514e250ddeb2f552ffbf20957a58478c6
--- /dev/null
+++ b/OAR.2073656.stderr
@@ -0,0 +1,9 @@
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py:26: UserWarning: 
+    There is an imbalance between your GPUs. You may want to exclude GPU 1 which
+    has less than 75% of the memory or cores of GPU 0. You can do so by setting
+    the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES
+    environment variable.
+  warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))
+/data1/home/julien.dejasmin/anaconda3/envs/pytorch/lib/python3.7/site-packages/torch/nn/_reduction.py:43: UserWarning: size_average and reduce args will be deprecated, please use reduction='sum' instead.
+  warnings.warn(warning.format(ret))
+## OAR [2020-07-06 17:08:45] Job 2073656 KILLED ##
diff --git a/OAR.2073656.stdout b/OAR.2073656.stdout
new file mode 100644
index 0000000000000000000000000000000000000000..786e01aed0800b3dbe1131682bffb423862e3c81
--- /dev/null
+++ b/OAR.2073656.stdout
@@ -0,0 +1,468 @@
+Namespace(batch_size=64, beta=None, ckpt_dir='checkpoints', ckpt_name='last', cont_capacity=None, dataset='rendered_chairs', disc_capacity=None, epochs=9000, experiment_name='VAE_bs_64_conv_64_64_128_128', gpu_devices=[0, 1], is_beta_VAE=False, latent_spec_cont=10, latent_spec_disc=None, load_expe_name='', load_model_checkpoint=True, lr=1e-05, nb_filter_conv1=64, nb_filter_conv2=64, nb_filter_conv3=128, nb_filter_conv4=128, num_worker=1, print_loss_every=50, record_loss_every=50, save_model=True, save_reconstruction_image=False, save_step=1, verbose=True)
+CUDA Visible devices !
+load dataset: rendered_chairs, with: 69120 train images of shape: (3, 64, 64)
+use 2 gpu who named:
+Tesla K40c
+Tesla K20m
+DataParallel(
+  (module): VAE(
+    (img_to_last_conv): Sequential(
+      (0): Conv2d(3, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (1): ReLU()
+      (2): Conv2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): Conv2d(128, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+    )
+    (last_conv_to_continuous_features): Sequential(
+      (0): Conv2d(128, 512, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+    )
+    (features_to_hidden_continue): Sequential(
+      (0): Linear(in_features=512, out_features=20, bias=True)
+      (1): ReLU()
+    )
+    (latent_to_features): Sequential(
+      (0): Linear(in_features=10, out_features=512, bias=True)
+      (1): ReLU()
+    )
+    (features_to_img): Sequential(
+      (0): ConvTranspose2d(512, 128, kernel_size=(4, 4), stride=(1, 1))
+      (1): ReLU()
+      (2): ConvTranspose2d(128, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (3): ReLU()
+      (4): ConvTranspose2d(128, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (5): ReLU()
+      (6): ConvTranspose2d(64, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (7): ReLU()
+      (8): ConvTranspose2d(64, 3, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
+      (9): Sigmoid()
+    )
+  )
+)
+The number of parameters of model is 3037975
+don't use continuous capacity
+=> loaded checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last (iter 86)'
+0/69092	Loss: 117.694
+3200/69092	Loss: 118.432
+6400/69092	Loss: 118.501
+9600/69092	Loss: 118.489
+12800/69092	Loss: 119.350
+16000/69092	Loss: 118.195
+19200/69092	Loss: 122.088
+22400/69092	Loss: 118.524
+25600/69092	Loss: 119.645
+28800/69092	Loss: 118.861
+32000/69092	Loss: 120.393
+35200/69092	Loss: 118.982
+38400/69092	Loss: 117.442
+41600/69092	Loss: 118.423
+44800/69092	Loss: 117.580
+48000/69092	Loss: 119.497
+51200/69092	Loss: 119.496
+54400/69092	Loss: 117.932
+57600/69092	Loss: 122.195
+60800/69092	Loss: 115.537
+64000/69092	Loss: 120.373
+67200/69092	Loss: 119.428
+Training time 0:14:13.945016
+Epoch: 1 Average loss: 118.99
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 87)
+0/69092	Loss: 130.393
+3200/69092	Loss: 117.386
+6400/69092	Loss: 119.379
+9600/69092	Loss: 120.024
+12800/69092	Loss: 117.695
+16000/69092	Loss: 119.331
+19200/69092	Loss: 118.637
+22400/69092	Loss: 119.156
+25600/69092	Loss: 120.262
+28800/69092	Loss: 120.793
+32000/69092	Loss: 118.257
+35200/69092	Loss: 116.527
+38400/69092	Loss: 117.896
+41600/69092	Loss: 119.483
+44800/69092	Loss: 118.941
+48000/69092	Loss: 117.900
+51200/69092	Loss: 118.215
+54400/69092	Loss: 119.306
+57600/69092	Loss: 119.740
+60800/69092	Loss: 118.641
+64000/69092	Loss: 117.922
+67200/69092	Loss: 118.341
+Training time 0:07:31.381226
+Epoch: 2 Average loss: 118.75
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 88)
+0/69092	Loss: 119.623
+3200/69092	Loss: 120.716
+6400/69092	Loss: 118.038
+9600/69092	Loss: 119.440
+12800/69092	Loss: 119.888
+16000/69092	Loss: 116.939
+19200/69092	Loss: 118.108
+22400/69092	Loss: 118.553
+25600/69092	Loss: 118.557
+28800/69092	Loss: 119.174
+32000/69092	Loss: 119.645
+35200/69092	Loss: 118.940
+38400/69092	Loss: 117.269
+41600/69092	Loss: 121.778
+44800/69092	Loss: 120.010
+48000/69092	Loss: 117.630
+51200/69092	Loss: 119.292
+54400/69092	Loss: 119.268
+57600/69092	Loss: 118.923
+60800/69092	Loss: 119.078
+64000/69092	Loss: 118.655
+67200/69092	Loss: 119.249
+Training time 0:07:34.831308
+Epoch: 3 Average loss: 118.99
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 89)
+0/69092	Loss: 114.239
+3200/69092	Loss: 120.136
+6400/69092	Loss: 119.018
+9600/69092	Loss: 119.484
+12800/69092	Loss: 119.795
+16000/69092	Loss: 119.599
+19200/69092	Loss: 118.820
+22400/69092	Loss: 117.392
+25600/69092	Loss: 119.914
+28800/69092	Loss: 118.627
+32000/69092	Loss: 119.123
+35200/69092	Loss: 118.777
+38400/69092	Loss: 116.972
+41600/69092	Loss: 117.295
+44800/69092	Loss: 118.909
+48000/69092	Loss: 119.073
+51200/69092	Loss: 120.202
+54400/69092	Loss: 118.076
+57600/69092	Loss: 118.386
+60800/69092	Loss: 118.060
+64000/69092	Loss: 118.025
+67200/69092	Loss: 119.918
+Training time 0:07:35.087687
+Epoch: 4 Average loss: 118.86
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 90)
+0/69092	Loss: 121.327
+3200/69092	Loss: 118.618
+6400/69092	Loss: 117.247
+9600/69092	Loss: 120.337
+12800/69092	Loss: 117.886
+16000/69092	Loss: 116.250
+19200/69092	Loss: 117.602
+22400/69092	Loss: 120.076
+25600/69092	Loss: 120.992
+28800/69092	Loss: 119.478
+32000/69092	Loss: 121.168
+35200/69092	Loss: 117.906
+38400/69092	Loss: 119.290
+41600/69092	Loss: 117.479
+44800/69092	Loss: 117.553
+48000/69092	Loss: 117.566
+51200/69092	Loss: 118.227
+54400/69092	Loss: 118.682
+57600/69092	Loss: 118.498
+60800/69092	Loss: 120.303
+64000/69092	Loss: 117.960
+67200/69092	Loss: 117.698
+Training time 0:07:56.623599
+Epoch: 5 Average loss: 118.67
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 91)
+0/69092	Loss: 105.633
+3200/69092	Loss: 118.554
+6400/69092	Loss: 119.615
+9600/69092	Loss: 119.318
+12800/69092	Loss: 118.742
+16000/69092	Loss: 119.974
+19200/69092	Loss: 121.265
+22400/69092	Loss: 119.141
+25600/69092	Loss: 118.307
+28800/69092	Loss: 118.427
+32000/69092	Loss: 116.378
+35200/69092	Loss: 119.006
+38400/69092	Loss: 119.625
+41600/69092	Loss: 118.215
+44800/69092	Loss: 117.062
+48000/69092	Loss: 120.085
+51200/69092	Loss: 117.497
+54400/69092	Loss: 118.513
+57600/69092	Loss: 117.501
+60800/69092	Loss: 119.534
+64000/69092	Loss: 118.761
+67200/69092	Loss: 119.786
+Training time 0:07:49.425830
+Epoch: 6 Average loss: 118.73
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 92)
+0/69092	Loss: 128.389
+3200/69092	Loss: 117.092
+6400/69092	Loss: 119.006
+9600/69092	Loss: 119.130
+12800/69092	Loss: 116.969
+16000/69092	Loss: 118.569
+19200/69092	Loss: 119.163
+22400/69092	Loss: 116.380
+25600/69092	Loss: 117.838
+28800/69092	Loss: 119.352
+32000/69092	Loss: 118.976
+35200/69092	Loss: 118.172
+38400/69092	Loss: 118.417
+41600/69092	Loss: 119.819
+44800/69092	Loss: 117.800
+48000/69092	Loss: 119.049
+51200/69092	Loss: 121.287
+54400/69092	Loss: 120.721
+57600/69092	Loss: 118.213
+60800/69092	Loss: 117.643
+64000/69092	Loss: 119.564
+67200/69092	Loss: 118.016
+Training time 0:07:35.571668
+Epoch: 7 Average loss: 118.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 93)
+0/69092	Loss: 119.123
+3200/69092	Loss: 116.765
+6400/69092	Loss: 118.645
+9600/69092	Loss: 118.229
+12800/69092	Loss: 118.869
+16000/69092	Loss: 118.261
+19200/69092	Loss: 118.188
+22400/69092	Loss: 117.008
+25600/69092	Loss: 118.807
+28800/69092	Loss: 117.948
+32000/69092	Loss: 119.650
+35200/69092	Loss: 118.231
+38400/69092	Loss: 119.093
+41600/69092	Loss: 119.147
+44800/69092	Loss: 119.808
+48000/69092	Loss: 118.298
+51200/69092	Loss: 119.673
+54400/69092	Loss: 119.079
+57600/69092	Loss: 117.252
+60800/69092	Loss: 118.739
+64000/69092	Loss: 119.065
+67200/69092	Loss: 120.760
+Training time 0:07:32.790181
+Epoch: 8 Average loss: 118.62
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 94)
+0/69092	Loss: 101.608
+3200/69092	Loss: 119.196
+6400/69092	Loss: 119.704
+9600/69092	Loss: 119.780
+12800/69092	Loss: 118.972
+16000/69092	Loss: 117.676
+19200/69092	Loss: 120.463
+22400/69092	Loss: 118.339
+25600/69092	Loss: 118.546
+28800/69092	Loss: 118.832
+32000/69092	Loss: 119.358
+35200/69092	Loss: 119.058
+38400/69092	Loss: 117.461
+41600/69092	Loss: 116.151
+44800/69092	Loss: 119.484
+48000/69092	Loss: 117.108
+51200/69092	Loss: 120.395
+54400/69092	Loss: 118.880
+57600/69092	Loss: 118.098
+60800/69092	Loss: 118.353
+64000/69092	Loss: 118.227
+67200/69092	Loss: 118.784
+Training time 0:07:29.947963
+Epoch: 9 Average loss: 118.63
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 95)
+0/69092	Loss: 126.880
+3200/69092	Loss: 119.853
+6400/69092	Loss: 118.711
+9600/69092	Loss: 118.999
+12800/69092	Loss: 117.955
+16000/69092	Loss: 119.300
+19200/69092	Loss: 117.833
+22400/69092	Loss: 117.864
+25600/69092	Loss: 118.584
+28800/69092	Loss: 118.970
+32000/69092	Loss: 117.937
+35200/69092	Loss: 118.265
+38400/69092	Loss: 118.579
+41600/69092	Loss: 119.163
+44800/69092	Loss: 117.567
+48000/69092	Loss: 119.146
+51200/69092	Loss: 117.409
+54400/69092	Loss: 119.171
+57600/69092	Loss: 119.717
+60800/69092	Loss: 120.156
+64000/69092	Loss: 117.829
+67200/69092	Loss: 118.871
+Training time 0:07:29.316301
+Epoch: 10 Average loss: 118.68
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 96)
+0/69092	Loss: 115.064
+3200/69092	Loss: 119.530
+6400/69092	Loss: 117.345
+9600/69092	Loss: 119.148
+12800/69092	Loss: 119.863
+16000/69092	Loss: 118.319
+19200/69092	Loss: 118.111
+22400/69092	Loss: 116.091
+25600/69092	Loss: 118.846
+28800/69092	Loss: 119.157
+32000/69092	Loss: 117.030
+35200/69092	Loss: 118.431
+38400/69092	Loss: 120.034
+41600/69092	Loss: 118.253
+44800/69092	Loss: 118.826
+48000/69092	Loss: 118.417
+51200/69092	Loss: 119.849
+54400/69092	Loss: 118.038
+57600/69092	Loss: 118.830
+60800/69092	Loss: 120.045
+64000/69092	Loss: 116.852
+67200/69092	Loss: 116.874
+Training time 0:07:35.170053
+Epoch: 11 Average loss: 118.48
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 97)
+0/69092	Loss: 131.390
+3200/69092	Loss: 119.872
+6400/69092	Loss: 119.467
+9600/69092	Loss: 119.365
+12800/69092	Loss: 121.863
+16000/69092	Loss: 118.354
+19200/69092	Loss: 117.457
+22400/69092	Loss: 120.095
+25600/69092	Loss: 118.251
+28800/69092	Loss: 118.245
+32000/69092	Loss: 119.155
+35200/69092	Loss: 119.537
+38400/69092	Loss: 116.894
+41600/69092	Loss: 118.937
+44800/69092	Loss: 117.073
+48000/69092	Loss: 117.284
+51200/69092	Loss: 119.048
+54400/69092	Loss: 119.683
+57600/69092	Loss: 116.164
+60800/69092	Loss: 117.780
+64000/69092	Loss: 119.660
+67200/69092	Loss: 116.056
+Training time 0:07:34.422163
+Epoch: 12 Average loss: 118.60
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 98)
+0/69092	Loss: 122.095
+3200/69092	Loss: 117.016
+6400/69092	Loss: 116.512
+9600/69092	Loss: 120.309
+12800/69092	Loss: 118.080
+16000/69092	Loss: 116.443
+19200/69092	Loss: 119.067
+22400/69092	Loss: 117.616
+25600/69092	Loss: 120.111
+28800/69092	Loss: 118.229
+32000/69092	Loss: 118.735
+35200/69092	Loss: 115.753
+38400/69092	Loss: 117.180
+41600/69092	Loss: 117.769
+44800/69092	Loss: 118.198
+48000/69092	Loss: 118.902
+51200/69092	Loss: 117.921
+54400/69092	Loss: 120.463
+57600/69092	Loss: 117.913
+60800/69092	Loss: 118.975
+64000/69092	Loss: 119.985
+67200/69092	Loss: 120.136
+Training time 0:07:31.623966
+Epoch: 13 Average loss: 118.39
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 99)
+0/69092	Loss: 111.591
+3200/69092	Loss: 116.552
+6400/69092	Loss: 117.541
+9600/69092	Loss: 119.470
+12800/69092	Loss: 118.757
+16000/69092	Loss: 117.719
+19200/69092	Loss: 117.224
+22400/69092	Loss: 119.372
+25600/69092	Loss: 120.709
+28800/69092	Loss: 117.695
+32000/69092	Loss: 116.136
+35200/69092	Loss: 120.033
+38400/69092	Loss: 120.406
+41600/69092	Loss: 117.325
+44800/69092	Loss: 117.913
+48000/69092	Loss: 117.831
+51200/69092	Loss: 119.979
+54400/69092	Loss: 118.512
+57600/69092	Loss: 118.619
+60800/69092	Loss: 117.288
+64000/69092	Loss: 117.566
+67200/69092	Loss: 120.574
+Training time 0:07:30.207680
+Epoch: 14 Average loss: 118.44
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 100)
+0/69092	Loss: 123.426
+3200/69092	Loss: 118.659
+6400/69092	Loss: 118.713
+9600/69092	Loss: 117.724
+12800/69092	Loss: 118.388
+16000/69092	Loss: 117.357
+19200/69092	Loss: 117.287
+22400/69092	Loss: 118.643
+25600/69092	Loss: 117.376
+28800/69092	Loss: 117.028
+32000/69092	Loss: 120.223
+35200/69092	Loss: 119.158
+38400/69092	Loss: 119.948
+41600/69092	Loss: 118.666
+44800/69092	Loss: 119.500
+48000/69092	Loss: 121.176
+51200/69092	Loss: 119.840
+54400/69092	Loss: 117.195
+57600/69092	Loss: 116.212
+60800/69092	Loss: 117.903
+64000/69092	Loss: 117.594
+67200/69092	Loss: 117.326
+Training time 0:07:31.308007
+Epoch: 15 Average loss: 118.38
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 101)
+0/69092	Loss: 120.264
+3200/69092	Loss: 119.231
+6400/69092	Loss: 115.626
+9600/69092	Loss: 117.766
+12800/69092	Loss: 118.371
+16000/69092	Loss: 118.611
+19200/69092	Loss: 118.427
+22400/69092	Loss: 118.136
+25600/69092	Loss: 117.239
+28800/69092	Loss: 119.401
+32000/69092	Loss: 118.719
+35200/69092	Loss: 119.317
+38400/69092	Loss: 118.726
+41600/69092	Loss: 119.508
+44800/69092	Loss: 119.788
+48000/69092	Loss: 120.357
+51200/69092	Loss: 118.214
+54400/69092	Loss: 119.092
+57600/69092	Loss: 118.792
+60800/69092	Loss: 118.131
+64000/69092	Loss: 119.248
+67200/69092	Loss: 117.364
+Training time 0:07:30.172670
+Epoch: 16 Average loss: 118.54
+=> saved checkpoint 'trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last' (iter 102)
+0/69092	Loss: 109.716
+3200/69092	Loss: 119.807
+6400/69092	Loss: 117.220
+9600/69092	Loss: 119.324
+12800/69092	Loss: 118.453
+16000/69092	Loss: 119.029
+19200/69092	Loss: 119.127
+22400/69092	Loss: 118.859
+25600/69092	Loss: 116.423
+28800/69092	Loss: 115.011
+32000/69092	Loss: 117.166
+35200/69092	Loss: 121.352
+38400/69092	Loss: 119.396
+41600/69092	Loss: 118.837
+44800/69092	Loss: 116.260
+48000/69092	Loss: 119.507
+51200/69092	Loss: 119.166
+54400/69092	Loss: 118.681
+57600/69092	Loss: 117.348
+60800/69092	Loss: 118.259
+64000/69092	Loss: 119.696
diff --git a/VAE_model/__pycache__/binary_activation.cpython-37.pyc b/VAE_model/__pycache__/binary_activation.cpython-37.pyc
index d4b4a88d3e50b5c5615c90e6ec2c0fd299771617..0281594dac1b6f9cba314cb9974d58e1c8e33ad1 100644
Binary files a/VAE_model/__pycache__/binary_activation.cpython-37.pyc and b/VAE_model/__pycache__/binary_activation.cpython-37.pyc differ
diff --git a/VAE_model/__pycache__/models.cpython-37.pyc b/VAE_model/__pycache__/models.cpython-37.pyc
index b66bcc937eda9bc236e86b5150c4dc419043967c..bf2ae15b9d331cf50d65f2a667f3b1785270638c 100644
Binary files a/VAE_model/__pycache__/models.cpython-37.pyc and b/VAE_model/__pycache__/models.cpython-37.pyc differ
diff --git a/VAE_model/distributions/__pycache__/__init__.cpython-37.pyc b/VAE_model/distributions/__pycache__/__init__.cpython-37.pyc
index 72a5b85b5727f69d19573a1052bfd8ebbca2c8de..94edce05a5895e317dff0c018bb6f210c52d3915 100644
Binary files a/VAE_model/distributions/__pycache__/__init__.cpython-37.pyc and b/VAE_model/distributions/__pycache__/__init__.cpython-37.pyc differ
diff --git a/VAE_model/distributions/__pycache__/bernoulli.cpython-37.pyc b/VAE_model/distributions/__pycache__/bernoulli.cpython-37.pyc
index 47be158845f776013a384db81149c1095ced3eb3..ddbbaec450a4334cc2daba949638d85529c2fb41 100644
Binary files a/VAE_model/distributions/__pycache__/bernoulli.cpython-37.pyc and b/VAE_model/distributions/__pycache__/bernoulli.cpython-37.pyc differ
diff --git a/VAE_model/distributions/__pycache__/distribution.cpython-37.pyc b/VAE_model/distributions/__pycache__/distribution.cpython-37.pyc
index 4bff73c8305628f75a7aaf69ffb08b10987c6a58..b1598f6251526ea47104023f2a996a5910f69212 100644
Binary files a/VAE_model/distributions/__pycache__/distribution.cpython-37.pyc and b/VAE_model/distributions/__pycache__/distribution.cpython-37.pyc differ
diff --git a/VAE_model/distributions/__pycache__/functions.cpython-37.pyc b/VAE_model/distributions/__pycache__/functions.cpython-37.pyc
index be06f59cb370dd0bafe5b4029ff299bf2e4ad5fd..74e856fa9448f6aa01cb77e06bbe3b45e6ca8b13 100644
Binary files a/VAE_model/distributions/__pycache__/functions.cpython-37.pyc and b/VAE_model/distributions/__pycache__/functions.cpython-37.pyc differ
diff --git a/VAE_model/distributions/__pycache__/round.cpython-37.pyc b/VAE_model/distributions/__pycache__/round.cpython-37.pyc
index 81af15d65ca5bdbd66a177b08c055a2e4a41c844..348f4315817320f11336421e9e3a8702525d94d7 100644
Binary files a/VAE_model/distributions/__pycache__/round.cpython-37.pyc and b/VAE_model/distributions/__pycache__/round.cpython-37.pyc differ
diff --git a/VAE_model/distributions/__pycache__/utils.cpython-37.pyc b/VAE_model/distributions/__pycache__/utils.cpython-37.pyc
index 8741c7cc8419e5da9760ce0727b4567db821b9f4..52799f7aa66a3bc43cc8ece1f337d7a6b7f13f12 100644
Binary files a/VAE_model/distributions/__pycache__/utils.cpython-37.pyc and b/VAE_model/distributions/__pycache__/utils.cpython-37.pyc differ
diff --git a/dataloader/__pycache__/dataloaders.cpython-37.pyc b/dataloader/__pycache__/dataloaders.cpython-37.pyc
index e19bec02c0871905e3f2f2ad557bb23db1635a83..bb56e963ff7cbe7b5deb67de148f28f33c4cf21d 100644
Binary files a/dataloader/__pycache__/dataloaders.cpython-37.pyc and b/dataloader/__pycache__/dataloaders.cpython-37.pyc differ
diff --git a/parameters_combinations/param_combinations_chairs.txt b/parameters_combinations/param_combinations_chairs.txt
index 0c6fe84ca55d9a216805065748e00df160533f50..07861d8d7a88b40309242721dcec205134a2de12 100644
--- a/parameters_combinations/param_combinations_chairs.txt
+++ b/parameters_combinations/param_combinations_chairs.txt
@@ -1,15 +1,15 @@
---batch-size=64 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=30 --lr=1e-5 --experiment-name=VAE_bs_64_ls_30 --gpu-devices 0 1 --load-model-checkpoint=True
---batch-size=64 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=40 --lr=1e-5 --experiment-name=VAE_bs_64_ls_40 --gpu-devices 0 1 --load-model-checkpoint=True
---batch-size=64 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=50 --lr=1e-5 --experiment-name=VAE_bs_64_ls_50 --gpu-devices 0 1 --load-model-checkpoint=True
---batch-size=256 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=10 --is-beta-VAE=True --beta=4 --lr=1e-5 --experiment-name=beta_VAE_bs_256 --gpu-devices 0 1 --load-model-checkpoint=True
---batch-size=64 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=10 --is-beta-VAE=True --beta=4 --lr=1e-5 --experiment-name=beta_VAE_bs_64 --gpu-devices 0 1 --load-model-checkpoint=True
---batch-size=256 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=10 --lr=1e-5 --experiment-name=VAE_bs_256 --gpu-devices 0 1 --load-model-checkpoint=True
---batch-size=64 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=10 --lr=1e-5 --experiment-name=VAE_bs_64 --gpu-devices 0 1 --load-model-checkpoint=True
---batch-size=64 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=15 --is-beta-VAE=True --beta=4 --lr=1e-5 --gpu-devices 0 1 --experiment-name=beta_VAE_bs_64_ls_15 --load-model-checkpoint=True
---batch-size=64 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=20 --is-beta-VAE=True --beta=4 --lr=1e-5 --gpu-devices 0 1 --experiment-name=beta_VAE_bs_64_ls_20 --load-model-checkpoint=True
---batch-size=64 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=5 --is-beta-VAE=True --beta=4 --lr=1e-5 --gpu-devices 0 1 --experiment-name=beta_VAE_bs_64_ls_5 --load-model-checkpoint=True
---batch-size=64 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=5 --lr=1e-5 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_5 --load-model-checkpoint=True
---batch-size=64 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=15 --lr=1e-5 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_15 --load-model-checkpoint=True
---batch-size=64 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=20 --lr=1e-5 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_20 --load-model-checkpoint=True
---batch-size=64 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=10 --lr=5e-5 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_10_lr_5e_4 --load-model-checkpoint=True
---batch-size=64 --dataset=rendered_chairs --epochs=400 --latent_spec_cont=10 --lr=1e-5 --experiment-name=VAE_bs_64_conv_64_64_128_128 --gpu-devices 0 1 --nb-filter-conv1=64 --nb-filter-conv2=64 --nb-filter-conv3=128 --nb-filter-conv4=128 --load-model-checkpoint=True
\ No newline at end of file
+--batch-size=64 --dataset=rendered_chairs --epochs=90000 --latent_spec_cont=30 --lr=1e-5 --experiment-name=VAE_bs_64_ls_30 --gpu-devices 0 1 --load-model-checkpoint=True
+--batch-size=64 --dataset=rendered_chairs --epochs=9000 --latent_spec_cont=40 --lr=1e-5 --experiment-name=VAE_bs_64_ls_40 --gpu-devices 0 1 --load-model-checkpoint=True
+--batch-size=64 --dataset=rendered_chairs --epochs=9000 --latent_spec_cont=50 --lr=1e-5 --experiment-name=VAE_bs_64_ls_50 --gpu-devices 0 1 --load-model-checkpoint=True
+--batch-size=256 --dataset=rendered_chairs --epochs=9000 --latent_spec_cont=10 --is-beta-VAE=True --beta=4 --lr=1e-5 --experiment-name=beta_VAE_bs_256 --gpu-devices 0 1 --load-model-checkpoint=True
+--batch-size=64 --dataset=rendered_chairs --epochs=9000 --latent_spec_cont=10 --is-beta-VAE=True --beta=4 --lr=1e-5 --experiment-name=beta_VAE_bs_64 --gpu-devices 0 1 --load-model-checkpoint=True
+--batch-size=256 --dataset=rendered_chairs --epochs=9000 --latent_spec_cont=10 --lr=1e-5 --experiment-name=VAE_bs_256 --gpu-devices 0 1 --load-model-checkpoint=True
+--batch-size=64 --dataset=rendered_chairs --epochs=9000 --latent_spec_cont=10 --lr=1e-5 --experiment-name=VAE_bs_64 --gpu-devices 0 1 --load-model-checkpoint=True
+--batch-size=64 --dataset=rendered_chairs --epochs=9000 --latent_spec_cont=15 --is-beta-VAE=True --beta=4 --lr=1e-5 --gpu-devices 0 1 --experiment-name=beta_VAE_bs_64_ls_15 --load-model-checkpoint=True
+--batch-size=64 --dataset=rendered_chairs --epochs=9000 --latent_spec_cont=20 --is-beta-VAE=True --beta=4 --lr=1e-5 --gpu-devices 0 1 --experiment-name=beta_VAE_bs_64_ls_20 --load-model-checkpoint=True
+--batch-size=64 --dataset=rendered_chairs --epochs=9000 --latent_spec_cont=5 --is-beta-VAE=True --beta=4 --lr=1e-5 --gpu-devices 0 1 --experiment-name=beta_VAE_bs_64_ls_5 --load-model-checkpoint=True
+--batch-size=64 --dataset=rendered_chairs --epochs=9000 --latent_spec_cont=5 --lr=1e-5 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_5 --load-model-checkpoint=True
+--batch-size=64 --dataset=rendered_chairs --epochs=9000 --latent_spec_cont=15 --lr=1e-5 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_15 --load-model-checkpoint=True
+--batch-size=64 --dataset=rendered_chairs --epochs=9000 --latent_spec_cont=20 --lr=1e-5 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_20 --load-model-checkpoint=True
+--batch-size=64 --dataset=rendered_chairs --epochs=9000 --latent_spec_cont=10 --lr=5e-5 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_10_lr_5e_4 --load-model-checkpoint=True
+--batch-size=64 --dataset=rendered_chairs --epochs=9000 --latent_spec_cont=10 --lr=1e-5 --experiment-name=VAE_bs_64_conv_64_64_128_128 --gpu-devices 0 1 --nb-filter-conv1=64 --nb-filter-conv2=64 --nb-filter-conv3=128 --nb-filter-conv4=128 --load-model-checkpoint=True
diff --git a/parameters_combinations/param_combinations_fashion_mnist.txt b/parameters_combinations/param_combinations_fashion_mnist.txt
index a3ed0197e42fb35d5ffe5650248a12cfcd723dee..0d72c21533077471c19196abf213b83898410785 100644
--- a/parameters_combinations/param_combinations_fashion_mnist.txt
+++ b/parameters_combinations/param_combinations_fashion_mnist.txt
@@ -1,13 +1,13 @@
---batch-size=64 --dataset=fashion_data --epochs=400 --latent_spec_cont=30 --lr=1e-4 --experiment-name=VAE_bs_64_ls_30 --gpu-devices 0 1
---batch-size=64 --dataset=fashion_data --epochs=400 --latent_spec_cont=40 --lr=1e-4 --experiment-name=VAE_bs_64_ls_40 --gpu-devices 0 1
---batch-size=64 --dataset=fashion_data --epochs=400 --latent_spec_cont=50 --lr=1e-4 --experiment-name=VAE_bs_64_ls_50 --gpu-devices 0 1
---batch-size=64 --dataset=fashion_data --epochs=400 --latent_spec_cont=10 --is-beta-VAE=True --beta=4 --lr=1e-4 --experiment-name=beta_VAE_bs_64 --gpu-devices 0 1
---batch-size=64 --dataset=fashion_data --epochs=400 --latent_spec_cont=10 --lr=1e-4 --experiment-name=VAE_bs_64 --gpu-devices 0 1
---batch-size=64 --dataset=fashion_data --epochs=400 --latent_spec_cont=15 --is-beta-VAE=True --beta=4 --lr=1e-4 --gpu-devices 0 1 --experiment-name=beta_VAE_bs_64_ls_15
---batch-size=64 --dataset=fashion_data --epochs=400 --latent_spec_cont=20 --is-beta-VAE=True --beta=4 --lr=1e-4 --gpu-devices 0 1 --experiment-name=beta_VAE_bs_64_ls_20
---batch-size=64 --dataset=fashion_data --epochs=400 --latent_spec_cont=5 --is-beta-VAE=True --beta=4 --lr=1e-4 --gpu-devices 0 1 --experiment-name=beta_VAE_bs_64_ls_5
---batch-size=64 --dataset=fashion_data --epochs=400 --latent_spec_cont=5 --lr=1e-4 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_5
---batch-size=64 --dataset=fashion_data --epochs=400 --latent_spec_cont=15 --lr=1e-4 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_15
---batch-size=64 --dataset=fashion_data --epochs=400 --latent_spec_cont=20 --lr=1e-4 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_20
---batch-size=64 --dataset=fashion_data --epochs=400 --latent_spec_cont=10 --lr=5e-4 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_10_lr_5e_4
---batch-size=64 --dataset=fashion_data --epochs=400 --latent_spec_cont=10 --lr=1e-4 --experiment-name=VAE_bs_64_conv_64_64_128_128 --gpu-devices 0 1 --nb-filter-conv1=64 --nb-filter-conv2=64 --nb-filter-conv3=128 --nb-filter-conv4=128
\ No newline at end of file
+--batch-size=64 --dataset=fashion_data --epochs=9000000 --latent_spec_cont=30 --lr=1e-4 --experiment-name=VAE_bs_64_ls_30 --gpu-devices 0 1
+--batch-size=64 --dataset=fashion_data --epochs=9000000 --latent_spec_cont=40 --lr=1e-4 --experiment-name=VAE_bs_64_ls_40 --gpu-devices 0 1
+--batch-size=64 --dataset=fashion_data --epochs=9000000 --latent_spec_cont=50 --lr=1e-4 --experiment-name=VAE_bs_64_ls_50 --gpu-devices 0 1
+--batch-size=64 --dataset=fashion_data --epochs=9000000 --latent_spec_cont=10 --is-beta-VAE=True --beta=4 --lr=1e-4 --experiment-name=beta_VAE_bs_64 --gpu-devices 0 1
+--batch-size=64 --dataset=fashion_data --epochs=9000000 --latent_spec_cont=10 --lr=1e-4 --experiment-name=VAE_bs_64 --gpu-devices 0 1
+--batch-size=64 --dataset=fashion_data --epochs=9000000 --latent_spec_cont=15 --is-beta-VAE=True --beta=4 --lr=1e-4 --gpu-devices 0 1 --experiment-name=beta_VAE_bs_64_ls_15
+--batch-size=64 --dataset=fashion_data --epochs=9000000 --latent_spec_cont=20 --is-beta-VAE=True --beta=4 --lr=1e-4 --gpu-devices 0 1 --experiment-name=beta_VAE_bs_64_ls_20
+--batch-size=64 --dataset=fashion_data --epochs=9000000 --latent_spec_cont=5 --is-beta-VAE=True --beta=4 --lr=1e-4 --gpu-devices 0 1 --experiment-name=beta_VAE_bs_64_ls_5
+--batch-size=64 --dataset=fashion_data --epochs=9000000 --latent_spec_cont=5 --lr=1e-4 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_5
+--batch-size=64 --dataset=fashion_data --epochs=9000000 --latent_spec_cont=15 --lr=1e-4 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_15
+--batch-size=64 --dataset=fashion_data --epochs=9000000 --latent_spec_cont=20 --lr=1e-4 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_20
+--batch-size=64 --dataset=fashion_data --epochs=9000000 --latent_spec_cont=10 --lr=5e-4 --gpu-devices 0 1 --experiment-name=VAE_bs_64_ls_10_lr_5e_4
+--batch-size=64 --dataset=fashion_data --epochs=9000000 --latent_spec_cont=10 --lr=1e-4 --experiment-name=VAE_bs_64_conv_64_64_128_128 --gpu-devices 0 1 --nb-filter-conv1=64 --nb-filter-conv2=64 --nb-filter-conv3=128 --nb-filter-conv4=128
diff --git a/trained_models/fashion_data/VAE_bs_64/specs.json b/trained_models/fashion_data/VAE_bs_64/specs.json
index 8827ec8ee8d7eacbabfc2256fa0102a8e0a0d15c..0b1d4c2329cabcd7e166e3bfd4bdfd8f0ca58195 100644
--- a/trained_models/fashion_data/VAE_bs_64/specs.json
+++ b/trained_models/fashion_data/VAE_bs_64/specs.json
@@ -1 +1 @@
-{"dataset": "fashion_data", "epochs": 400, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 10, "experiment_name": "VAE_bs_64", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
+{"dataset": "fashion_data", "epochs": 9000000, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 10, "experiment_name": "VAE_bs_64", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
diff --git a/trained_models/fashion_data/VAE_bs_64_conv_64_64_128_128/specs.json b/trained_models/fashion_data/VAE_bs_64_conv_64_64_128_128/specs.json
index ffc5e2aba171d4b4dc140f49816b3025afe02795..fec300f1dea74c04fb2ad4157dd01bda4c53b9ea 100644
--- a/trained_models/fashion_data/VAE_bs_64_conv_64_64_128_128/specs.json
+++ b/trained_models/fashion_data/VAE_bs_64_conv_64_64_128_128/specs.json
@@ -1 +1 @@
-{"dataset": "fashion_data", "epochs": 400, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 10, "experiment_name": "VAE_bs_64_conv_64_64_128_128", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
+{"dataset": "fashion_data", "epochs": 9000000, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 10, "experiment_name": "VAE_bs_64_conv_64_64_128_128", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
diff --git a/trained_models/fashion_data/VAE_bs_64_ls_10_lr_5e_4/specs.json b/trained_models/fashion_data/VAE_bs_64_ls_10_lr_5e_4/specs.json
new file mode 100644
index 0000000000000000000000000000000000000000..b7db6ccc3d83186bbc6ade3cc8c24ca92c70e567
--- /dev/null
+++ b/trained_models/fashion_data/VAE_bs_64_ls_10_lr_5e_4/specs.json
@@ -0,0 +1 @@
+{"dataset": "fashion_data", "epochs": 9000000, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 10, "experiment_name": "VAE_bs_64_ls_10_lr_5e_4", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
diff --git a/trained_models/fashion_data/VAE_bs_64_ls_15/specs.json b/trained_models/fashion_data/VAE_bs_64_ls_15/specs.json
index 8dd2aa76bcf40d9aac98485c7cc5f94b296db0bc..356fd0e70e5451f10faef558e51782dd1eed5b49 100644
--- a/trained_models/fashion_data/VAE_bs_64_ls_15/specs.json
+++ b/trained_models/fashion_data/VAE_bs_64_ls_15/specs.json
@@ -1 +1 @@
-{"dataset": "fashion_data", "epochs": 400, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 15, "experiment_name": "VAE_bs_64_ls_15", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
+{"dataset": "fashion_data", "epochs": 9000000, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 15, "experiment_name": "VAE_bs_64_ls_15", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
diff --git a/trained_models/fashion_data/VAE_bs_64_ls_20/specs.json b/trained_models/fashion_data/VAE_bs_64_ls_20/specs.json
index 742a1ec14c37e60e19cd5dfe11421ac7a900fc73..f714b4321f9b7dd4ebfb9c48e8e74300c0e5f20e 100644
--- a/trained_models/fashion_data/VAE_bs_64_ls_20/specs.json
+++ b/trained_models/fashion_data/VAE_bs_64_ls_20/specs.json
@@ -1 +1 @@
-{"dataset": "fashion_data", "epochs": 400, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 20, "experiment_name": "VAE_bs_64_ls_20", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
+{"dataset": "fashion_data", "epochs": 9000000, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 20, "experiment_name": "VAE_bs_64_ls_20", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
diff --git a/trained_models/fashion_data/VAE_bs_64_ls_30/specs.json b/trained_models/fashion_data/VAE_bs_64_ls_30/specs.json
index ebd44573c2bfa66cc6e370419fb11254bc39c63e..3b531b00a37198c1efbdc8b4c52637f2e7646f04 100644
--- a/trained_models/fashion_data/VAE_bs_64_ls_30/specs.json
+++ b/trained_models/fashion_data/VAE_bs_64_ls_30/specs.json
@@ -1 +1 @@
-{"dataset": "fashion_data", "epochs": 400, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 30, "experiment_name": "VAE_bs_64_ls_30", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
+{"dataset": "fashion_data", "epochs": 9000000, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 30, "experiment_name": "VAE_bs_64_ls_30", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
diff --git a/trained_models/fashion_data/VAE_bs_64_ls_40/specs.json b/trained_models/fashion_data/VAE_bs_64_ls_40/specs.json
index 6deb250aad790d8ad37a7b627e6d3178149f2217..9074cd4f299cbf8534fc0b0908022dcf52a1a911 100644
--- a/trained_models/fashion_data/VAE_bs_64_ls_40/specs.json
+++ b/trained_models/fashion_data/VAE_bs_64_ls_40/specs.json
@@ -1 +1 @@
-{"dataset": "fashion_data", "epochs": 400, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 40, "experiment_name": "VAE_bs_64_ls_40", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
+{"dataset": "fashion_data", "epochs": 9000000, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 40, "experiment_name": "VAE_bs_64_ls_40", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
diff --git a/trained_models/fashion_data/VAE_bs_64_ls_5/specs.json b/trained_models/fashion_data/VAE_bs_64_ls_5/specs.json
index 75fb6db3940a910ae1ad3c0fe0a5fd39fdfb5354..02e347ff7f436400446ba679e80f69819c11217f 100644
--- a/trained_models/fashion_data/VAE_bs_64_ls_5/specs.json
+++ b/trained_models/fashion_data/VAE_bs_64_ls_5/specs.json
@@ -1 +1 @@
-{"dataset": "fashion_data", "epochs": 400, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 5, "experiment_name": "VAE_bs_64_ls_5", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
+{"dataset": "fashion_data", "epochs": 9000000, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 5, "experiment_name": "VAE_bs_64_ls_5", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
diff --git a/trained_models/fashion_data/VAE_bs_64_ls_50/specs.json b/trained_models/fashion_data/VAE_bs_64_ls_50/specs.json
index fc059be70e7c5268521354258dd8aba2933ee94e..eb12256d5d8080a75e0c0696f6eb2797ab71ccf8 100644
--- a/trained_models/fashion_data/VAE_bs_64_ls_50/specs.json
+++ b/trained_models/fashion_data/VAE_bs_64_ls_50/specs.json
@@ -1 +1 @@
-{"dataset": "fashion_data", "epochs": 400, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 50, "experiment_name": "VAE_bs_64_ls_50", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
+{"dataset": "fashion_data", "epochs": 9000000, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 50, "experiment_name": "VAE_bs_64_ls_50", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
diff --git a/trained_models/fashion_data/beta_VAE_bs_64/specs.json b/trained_models/fashion_data/beta_VAE_bs_64/specs.json
index 6070399134d9b84261d45a84d1b4626f5fd7f64f..d9b29d20d520bd81ba341f54b3a58b708f1a07f4 100644
--- a/trained_models/fashion_data/beta_VAE_bs_64/specs.json
+++ b/trained_models/fashion_data/beta_VAE_bs_64/specs.json
@@ -1 +1 @@
-{"dataset": "fashion_data", "epochs": 400, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 10, "experiment_name": "beta_VAE_bs_64", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
+{"dataset": "fashion_data", "epochs": 9000000, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 10, "experiment_name": "beta_VAE_bs_64", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
diff --git a/trained_models/fashion_data/beta_VAE_bs_64_ls_15/specs.json b/trained_models/fashion_data/beta_VAE_bs_64_ls_15/specs.json
index 2d5c0042568f8e9d274763e49ac51ec0f7392df9..fc6e32ef196478cebfcbb356fcd31c5d4edd676d 100644
--- a/trained_models/fashion_data/beta_VAE_bs_64_ls_15/specs.json
+++ b/trained_models/fashion_data/beta_VAE_bs_64_ls_15/specs.json
@@ -1 +1 @@
-{"dataset": "fashion_data", "epochs": 400, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 15, "experiment_name": "beta_VAE_bs_64_ls_15", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
+{"dataset": "fashion_data", "epochs": 9000000, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 15, "experiment_name": "beta_VAE_bs_64_ls_15", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
diff --git a/trained_models/fashion_data/beta_VAE_bs_64_ls_20/specs.json b/trained_models/fashion_data/beta_VAE_bs_64_ls_20/specs.json
index 30ae5379003d5e6199983749a50fdd6652fa41ef..fb6d45018286e6a3535d2ef12a0a94580419e785 100644
--- a/trained_models/fashion_data/beta_VAE_bs_64_ls_20/specs.json
+++ b/trained_models/fashion_data/beta_VAE_bs_64_ls_20/specs.json
@@ -1 +1 @@
-{"dataset": "fashion_data", "epochs": 400, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 20, "experiment_name": "beta_VAE_bs_64_ls_20", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
+{"dataset": "fashion_data", "epochs": 9000000, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 20, "experiment_name": "beta_VAE_bs_64_ls_20", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
diff --git a/trained_models/fashion_data/beta_VAE_bs_64_ls_5/specs.json b/trained_models/fashion_data/beta_VAE_bs_64_ls_5/specs.json
index 06042458f797ab61cacc57962a6c0dcf81ab98a7..e9bf876749bd87b9b5e4cb8ca404992345c3e93d 100644
--- a/trained_models/fashion_data/beta_VAE_bs_64_ls_5/specs.json
+++ b/trained_models/fashion_data/beta_VAE_bs_64_ls_5/specs.json
@@ -1 +1 @@
-{"dataset": "fashion_data", "epochs": 400, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 5, "experiment_name": "beta_VAE_bs_64_ls_5", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
+{"dataset": "fashion_data", "epochs": 9000000, "cont_capacity": null, "disc_capacity": null, "record_loss_every": 50, "batch_size": 64, "latent_spec_cont": 5, "experiment_name": "beta_VAE_bs_64_ls_5", "print_loss_every": 50, "latent_spec_disc": null, "nb_classes": 10}
\ No newline at end of file
diff --git a/trained_models/rendered_chairs/VAE_bs_256/checkpoints/last b/trained_models/rendered_chairs/VAE_bs_256/checkpoints/last
index cb177b2a09cbbb5ec3855f67263df44ec114a168..3a1ca47b346c4cc743827e69eb6468b02f5a4f8c 100644
Binary files a/trained_models/rendered_chairs/VAE_bs_256/checkpoints/last and b/trained_models/rendered_chairs/VAE_bs_256/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/VAE_bs_64/checkpoints/last b/trained_models/rendered_chairs/VAE_bs_64/checkpoints/last
index 4f2642ad341e29f5407b4424c4b4e2123c640da4..39717da547fa0b64bef48fa5c49cb503c7de1f67 100644
Binary files a/trained_models/rendered_chairs/VAE_bs_64/checkpoints/last and b/trained_models/rendered_chairs/VAE_bs_64/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last b/trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last
index bea1d7c106bb084bf229132e559a4d7a7b15ec75..d5c7e714d0f090fe8c448adc742ea3c78312eda3 100644
Binary files a/trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last and b/trained_models/rendered_chairs/VAE_bs_64_conv_64_64_128_128/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last b/trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last
index 7221155bdbbe2c7363eef33d85eface626b67d18..29ae868df0107585dba17f70297c779e05a3e28f 100644
Binary files a/trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last and b/trained_models/rendered_chairs/VAE_bs_64_ls_15/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last b/trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last
index 38197bbadf0b585f9d8609dd769acd38caffbf6b..ce6a799c271b4812f1afb6911568d6a7d341124d 100644
Binary files a/trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last and b/trained_models/rendered_chairs/VAE_bs_64_ls_20/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last b/trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last
index 72b2573a48d08d3e56c5496b1c132eabd5434fd4..1c7f1bc6a64f196c0760a4ff77c40f98fc67abbb 100644
Binary files a/trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last and b/trained_models/rendered_chairs/VAE_bs_64_ls_30/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last b/trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last
index ec60f6afe1e8e7f9ad62860e82424b6b1328e366..5eaaee5c35ee332c8c30b362f90442885392d920 100644
Binary files a/trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last and b/trained_models/rendered_chairs/VAE_bs_64_ls_40/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last b/trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last
index 6b228a26f653b8f9c577bf8d972789248386c44e..a9d9859a9330dd80d76baa9c6fd0c4c6e4c71b25 100644
Binary files a/trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last and b/trained_models/rendered_chairs/VAE_bs_64_ls_5/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last b/trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last
index 2b42d43dc2fecf682658e2bb42014de3bb47d9a5..7adf854108060734ac527343fd89106af42fec2b 100644
Binary files a/trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last and b/trained_models/rendered_chairs/VAE_bs_64_ls_50/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last b/trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last
index bd97a1596ce25bc80b9d7219543de89c95eb8da9..53410edf8474e996d6380e785b83a79f05936c90 100644
Binary files a/trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last and b/trained_models/rendered_chairs/beta_VAE_bs_64/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last b/trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last
index 754683cd89ef435818991bf29b93f403a60bbb1c..74229b050f36d53c6813858e4a54717c836ed969 100644
Binary files a/trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last and b/trained_models/rendered_chairs/beta_VAE_bs_64_ls_15/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/beta_VAE_bs_64_ls_20/checkpoints/last b/trained_models/rendered_chairs/beta_VAE_bs_64_ls_20/checkpoints/last
index 370e0479e6ef0e85a003c540bc44f2dc321e294c..eba082061469e7ed53eafa01bfcbb42052fecf4c 100644
Binary files a/trained_models/rendered_chairs/beta_VAE_bs_64_ls_20/checkpoints/last and b/trained_models/rendered_chairs/beta_VAE_bs_64_ls_20/checkpoints/last differ
diff --git a/trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last b/trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last
index 93f578b0f0b6f984624e70129a2298d6a17eaffa..db9be3928fe1deb94a215d98e62b01698f799643 100644
Binary files a/trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last and b/trained_models/rendered_chairs/beta_VAE_bs_64_ls_5/checkpoints/last differ
diff --git a/utils/__pycache__/training.cpython-37.pyc b/utils/__pycache__/training.cpython-37.pyc
index 284f1ae2db0b5e771f0b0b31ca3eb4de98376665..59954b810d7f6d786f331fc4b908486334ba7c1e 100644
Binary files a/utils/__pycache__/training.cpython-37.pyc and b/utils/__pycache__/training.cpython-37.pyc differ
diff --git a/utils/training.py b/utils/training.py
index 3b7c7ef1885e3de90a6bde1eb0d1f76772043e3d..6dbfc53da7db804a84e9f1a051e45ef6c55ba049 100644
--- a/utils/training.py
+++ b/utils/training.py
@@ -222,10 +222,10 @@ class Trainer:
         self.optimizer.step()
 
         train_loss = loss.item()
-        recon_loss_iter = recon_loss.item()
-        kl_loss_iter = kl_loss.item()
-        pred_loss_iter = pred_loss.item()
-        pred_random_loss_iter = pred_random_loss.item()
+        recon_loss_iter = recon_loss
+        kl_loss_iter = kl_loss
+        pred_loss_iter = pred_loss
+        pred_random_loss_iter = pred_random_loss
         
         return train_loss, recon_loss_iter, kl_loss_iter, pred_loss_iter, pred_random_loss_iter
 
diff --git a/viz/__pycache__/latent_traversals.cpython-37.pyc b/viz/__pycache__/latent_traversals.cpython-37.pyc
index edaee6f3a96f9f8af4206ac3de633dae53c234cb..7091d2bc17aa2f5bc68ecbad33d61fd09bf4f755 100644
Binary files a/viz/__pycache__/latent_traversals.cpython-37.pyc and b/viz/__pycache__/latent_traversals.cpython-37.pyc differ
diff --git a/viz/__pycache__/visualize.cpython-37.pyc b/viz/__pycache__/visualize.cpython-37.pyc
index 04ae3f7f39922c4320c30d9e0f44464bcb742118..2b3b8a388de1a10817c8f255e67ff77db11000e3 100644
Binary files a/viz/__pycache__/visualize.cpython-37.pyc and b/viz/__pycache__/visualize.cpython-37.pyc differ