Global seed set to 42
GPU available: True, used: True
TPU available: False, using: 0 TPU cores
Namespace(batch_size=1024, device='0', dropout=0.1, epochs=1, evaluate=False, hidden_channels=2048, in_memory=False, model='rgat', sizes=[1000, 1000])
#Params 27259229
Converting adjacency matrix... Done! [0.00s]
Merging adjacency matrices... Done! [1.76s]
Generating full feature matrix...
Done! [4.15s]
Reading dataset... LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]
Set SLURM handle signals.

  | Name  | Type       | Params
-------------------------------------
0 | convs | ModuleList | 17.9 M
1 | norms | ModuleList | 8.2 K 
2 | skips | ModuleList | 4.5 M 
3 | mlp   | Sequential | 4.9 M 
4 | acc   | Accuracy   | 0     
-------------------------------------
27.3 M    Trainable params
0         Non-trainable params
27.3 M    Total params
109.037   Total estimated model params size (MB)
Done! [0.88s]

Validation sanity check: 0it [00:00, ?it/s]
Validation sanity check:   0%|          | 0/2 [00:00<?, ?it/s]
Validation sanity check:  50%|█████     | 1/2 [00:06<00:06,  6.83s/it]
Validation sanity check: 100%|██████████| 2/2 [00:06<00:00,  2.89s/it]
                                                                      /home/kfountou/berserker/lib/python3.7/site-packages/pytorch_lightning/core/step_result.py:115: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
  value = torch.tensor(value, device=device, dtype=torch.float)
Global seed set to 42


Training: 0it [00:00, ?it/s]
Training:   0%|          | 0/679 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/679 [00:00<?, ?it/s] 
Epoch 0:   0%|          | 1/679 [00:04<53:17,  4.72s/it]
Epoch 0:   0%|          | 1/679 [00:04<53:18,  4.72s/it, loss=5.97, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   0%|          | 2/679 [00:04<27:22,  2.43s/it, loss=5.97, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   0%|          | 2/679 [00:04<27:22,  2.43s/it, loss=7.4, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:   0%|          | 3/679 [00:04<18:44,  1.66s/it, loss=7.4, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   0%|          | 3/679 [00:04<18:44,  1.66s/it, loss=8.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   1%|          | 4/679 [00:05<14:24,  1.28s/it, loss=8.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   1%|          | 4/679 [00:05<14:24,  1.28s/it, loss=9.43, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   1%|          | 5/679 [00:05<11:48,  1.05s/it, loss=9.43, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   1%|          | 5/679 [00:05<11:48,  1.05s/it, loss=9.79, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   1%|          | 6/679 [00:05<10:07,  1.11it/s, loss=9.79, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   1%|          | 6/679 [00:05<10:07,  1.11it/s, loss=9.82, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   1%|          | 7/679 [00:05<08:53,  1.26it/s, loss=9.82, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   1%|          | 7/679 [00:05<08:53,  1.26it/s, loss=9.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   1%|          | 8/679 [00:05<07:56,  1.41it/s, loss=9.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   1%|          | 8/679 [00:05<07:56,  1.41it/s, loss=9.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   1%|▏         | 9/679 [00:05<07:14,  1.54it/s, loss=9.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   1%|▏         | 9/679 [00:05<07:14,  1.54it/s, loss=9.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   1%|▏         | 10/679 [00:05<06:39,  1.67it/s, loss=9.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   1%|▏         | 10/679 [00:05<06:39,  1.67it/s, loss=9.37, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   2%|▏         | 11/679 [00:06<06:10,  1.80it/s, loss=9.37, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   2%|▏         | 11/679 [00:06<06:10,  1.80it/s, loss=9.17, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   2%|▏         | 12/679 [00:06<05:46,  1.92it/s, loss=9.17, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   2%|▏         | 12/679 [00:06<05:46,  1.92it/s, loss=8.95, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   2%|▏         | 13/679 [00:06<05:27,  2.04it/s, loss=8.95, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   2%|▏         | 13/679 [00:06<05:27,  2.04it/s, loss=8.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   2%|▏         | 14/679 [00:06<05:09,  2.15it/s, loss=8.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   2%|▏         | 14/679 [00:06<05:09,  2.15it/s, loss=8.67, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   2%|▏         | 15/679 [00:06<04:54,  2.26it/s, loss=8.67, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   2%|▏         | 15/679 [00:06<04:54,  2.26it/s, loss=8.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   2%|▏         | 16/679 [00:06<04:41,  2.35it/s, loss=8.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   2%|▏         | 16/679 [00:06<04:41,  2.35it/s, loss=8.36, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   3%|▎         | 17/679 [00:06<04:30,  2.45it/s, loss=8.36, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   3%|▎         | 17/679 [00:06<04:30,  2.45it/s, loss=8.21, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   3%|▎         | 18/679 [00:07<04:19,  2.54it/s, loss=8.21, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   3%|▎         | 18/679 [00:07<04:19,  2.54it/s, loss=8.06, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   3%|▎         | 19/679 [00:07<04:10,  2.64it/s, loss=8.06, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   3%|▎         | 19/679 [00:07<04:10,  2.64it/s, loss=7.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   3%|▎         | 20/679 [00:07<04:01,  2.73it/s, loss=7.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   3%|▎         | 20/679 [00:07<04:01,  2.73it/s, loss=7.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   3%|▎         | 21/679 [00:07<03:54,  2.80it/s, loss=7.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   3%|▎         | 21/679 [00:07<03:54,  2.80it/s, loss=7.72, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   3%|▎         | 22/679 [00:07<03:47,  2.89it/s, loss=7.72, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   3%|▎         | 22/679 [00:07<03:47,  2.89it/s, loss=7.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   3%|▎         | 23/679 [00:07<03:41,  2.97it/s, loss=7.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   3%|▎         | 23/679 [00:07<03:41,  2.97it/s, loss=7.24, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   4%|▎         | 24/679 [00:07<03:35,  3.04it/s, loss=7.24, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   4%|▎         | 24/679 [00:07<03:35,  3.04it/s, loss=6.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   4%|▎         | 25/679 [00:08<03:30,  3.11it/s, loss=6.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   4%|▎         | 25/679 [00:08<03:30,  3.11it/s, loss=6.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   4%|▍         | 26/679 [00:08<03:24,  3.19it/s, loss=6.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   4%|▍         | 26/679 [00:08<03:24,  3.19it/s, loss=6.36, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   4%|▍         | 27/679 [00:08<03:20,  3.26it/s, loss=6.36, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   4%|▍         | 27/679 [00:08<03:20,  3.26it/s, loss=6.14, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   4%|▍         | 28/679 [00:08<03:15,  3.33it/s, loss=6.14, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   4%|▍         | 28/679 [00:08<03:15,  3.33it/s, loss=5.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   4%|▍         | 29/679 [00:08<03:12,  3.38it/s, loss=5.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   4%|▍         | 29/679 [00:08<03:12,  3.38it/s, loss=5.8, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:   4%|▍         | 30/679 [00:08<03:08,  3.45it/s, loss=5.8, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   4%|▍         | 30/679 [00:08<03:08,  3.45it/s, loss=5.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   5%|▍         | 31/679 [00:08<03:04,  3.51it/s, loss=5.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   5%|▍         | 31/679 [00:08<03:04,  3.51it/s, loss=5.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   5%|▍         | 32/679 [00:08<03:01,  3.57it/s, loss=5.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   5%|▍         | 32/679 [00:08<03:01,  3.57it/s, loss=5.42, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   5%|▍         | 33/679 [00:09<02:58,  3.63it/s, loss=5.42, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   5%|▍         | 33/679 [00:09<02:58,  3.63it/s, loss=5.33, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   5%|▌         | 34/679 [00:09<02:57,  3.64it/s, loss=5.33, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   5%|▌         | 34/679 [00:09<02:57,  3.64it/s, loss=5.2, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:   5%|▌         | 35/679 [00:09<02:55,  3.67it/s, loss=5.2, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   5%|▌         | 35/679 [00:09<02:55,  3.67it/s, loss=5.12, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   5%|▌         | 36/679 [00:09<02:52,  3.73it/s, loss=5.12, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   5%|▌         | 36/679 [00:09<02:52,  3.73it/s, loss=5.04, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   5%|▌         | 37/679 [00:09<02:49,  3.78it/s, loss=5.04, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   5%|▌         | 37/679 [00:09<02:49,  3.78it/s, loss=4.96, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   6%|▌         | 38/679 [00:09<02:47,  3.83it/s, loss=4.96, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   6%|▌         | 38/679 [00:09<02:47,  3.83it/s, loss=4.89, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   6%|▌         | 39/679 [00:10<02:45,  3.88it/s, loss=4.89, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   6%|▌         | 39/679 [00:10<02:45,  3.88it/s, loss=4.85, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   6%|▌         | 40/679 [00:10<02:42,  3.93it/s, loss=4.85, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   6%|▌         | 40/679 [00:10<02:42,  3.93it/s, loss=4.8, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:   6%|▌         | 41/679 [00:10<02:42,  3.94it/s, loss=4.8, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   6%|▌         | 41/679 [00:10<02:42,  3.94it/s, loss=4.75, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   6%|▌         | 42/679 [00:10<02:39,  3.98it/s, loss=4.75, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   6%|▌         | 42/679 [00:10<02:39,  3.98it/s, loss=4.68, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   6%|▋         | 43/679 [00:10<02:37,  4.03it/s, loss=4.68, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   6%|▋         | 43/679 [00:10<02:37,  4.03it/s, loss=4.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   6%|▋         | 44/679 [00:10<02:35,  4.07it/s, loss=4.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   6%|▋         | 44/679 [00:10<02:36,  4.07it/s, loss=4.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   7%|▋         | 45/679 [00:10<02:34,  4.11it/s, loss=4.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   7%|▋         | 45/679 [00:10<02:34,  4.11it/s, loss=4.49, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   7%|▋         | 46/679 [00:11<02:32,  4.15it/s, loss=4.49, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   7%|▋         | 46/679 [00:11<02:32,  4.15it/s, loss=4.45, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   7%|▋         | 47/679 [00:11<02:30,  4.19it/s, loss=4.45, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   7%|▋         | 47/679 [00:11<02:30,  4.19it/s, loss=4.38, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   7%|▋         | 48/679 [00:11<02:29,  4.23it/s, loss=4.38, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   7%|▋         | 48/679 [00:11<02:29,  4.23it/s, loss=4.28, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   7%|▋         | 49/679 [00:11<02:27,  4.26it/s, loss=4.28, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   7%|▋         | 49/679 [00:11<02:27,  4.26it/s, loss=4.23, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   7%|▋         | 50/679 [00:11<02:26,  4.30it/s, loss=4.23, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   7%|▋         | 50/679 [00:11<02:26,  4.30it/s, loss=4.2, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:   8%|▊         | 51/679 [00:11<02:24,  4.34it/s, loss=4.2, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   8%|▊         | 51/679 [00:11<02:24,  4.34it/s, loss=4.16, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   8%|▊         | 52/679 [00:11<02:23,  4.38it/s, loss=4.16, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   8%|▊         | 52/679 [00:11<02:23,  4.38it/s, loss=4.1, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:   8%|▊         | 53/679 [00:12<02:22,  4.41it/s, loss=4.1, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   8%|▊         | 53/679 [00:12<02:22,  4.41it/s, loss=4.04, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   8%|▊         | 54/679 [00:12<02:20,  4.44it/s, loss=4.04, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   8%|▊         | 54/679 [00:12<02:20,  4.44it/s, loss=4, v_num=1.94e+7, val_acc=0.000]   
Epoch 0:   8%|▊         | 55/679 [00:12<02:19,  4.48it/s, loss=4, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   8%|▊         | 55/679 [00:12<02:19,  4.48it/s, loss=3.95, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   8%|▊         | 56/679 [00:12<02:18,  4.51it/s, loss=3.95, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   8%|▊         | 56/679 [00:12<02:18,  4.51it/s, loss=3.91, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   8%|▊         | 57/679 [00:12<02:16,  4.54it/s, loss=3.91, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   8%|▊         | 57/679 [00:12<02:16,  4.54it/s, loss=3.87, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   9%|▊         | 58/679 [00:12<02:15,  4.58it/s, loss=3.87, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   9%|▊         | 58/679 [00:12<02:15,  4.58it/s, loss=3.84, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   9%|▊         | 59/679 [00:12<02:14,  4.61it/s, loss=3.84, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   9%|▊         | 59/679 [00:12<02:14,  4.61it/s, loss=3.8, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:   9%|▉         | 60/679 [00:12<02:13,  4.64it/s, loss=3.8, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   9%|▉         | 60/679 [00:12<02:13,  4.64it/s, loss=3.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   9%|▉         | 61/679 [00:13<02:12,  4.66it/s, loss=3.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   9%|▉         | 61/679 [00:13<02:12,  4.66it/s, loss=3.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   9%|▉         | 62/679 [00:13<02:11,  4.69it/s, loss=3.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   9%|▉         | 62/679 [00:13<02:11,  4.69it/s, loss=3.73, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   9%|▉         | 63/679 [00:13<02:10,  4.72it/s, loss=3.73, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   9%|▉         | 63/679 [00:13<02:10,  4.72it/s, loss=3.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   9%|▉         | 64/679 [00:13<02:09,  4.75it/s, loss=3.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:   9%|▉         | 64/679 [00:13<02:09,  4.75it/s, loss=3.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  10%|▉         | 65/679 [00:13<02:08,  4.77it/s, loss=3.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  10%|▉         | 65/679 [00:13<02:08,  4.77it/s, loss=3.67, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  10%|▉         | 66/679 [00:13<02:07,  4.80it/s, loss=3.67, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  10%|▉         | 66/679 [00:13<02:07,  4.80it/s, loss=3.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  10%|▉         | 67/679 [00:13<02:06,  4.82it/s, loss=3.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  10%|▉         | 67/679 [00:13<02:06,  4.82it/s, loss=3.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  10%|█         | 68/679 [00:14<02:05,  4.85it/s, loss=3.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  10%|█         | 68/679 [00:14<02:05,  4.85it/s, loss=3.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  10%|█         | 69/679 [00:14<02:05,  4.88it/s, loss=3.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  10%|█         | 69/679 [00:14<02:05,  4.88it/s, loss=3.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  10%|█         | 70/679 [00:14<02:04,  4.90it/s, loss=3.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  10%|█         | 70/679 [00:14<02:04,  4.90it/s, loss=3.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  10%|█         | 71/679 [00:14<02:03,  4.93it/s, loss=3.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  10%|█         | 71/679 [00:14<02:03,  4.93it/s, loss=3.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  11%|█         | 72/679 [00:14<02:02,  4.95it/s, loss=3.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  11%|█         | 72/679 [00:14<02:02,  4.95it/s, loss=3.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  11%|█         | 73/679 [00:14<02:01,  4.98it/s, loss=3.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  11%|█         | 73/679 [00:14<02:01,  4.98it/s, loss=3.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  11%|█         | 74/679 [00:14<02:00,  5.00it/s, loss=3.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  11%|█         | 74/679 [00:14<02:00,  5.00it/s, loss=3.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  11%|█         | 75/679 [00:14<02:00,  5.02it/s, loss=3.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  11%|█         | 75/679 [00:14<02:00,  5.02it/s, loss=3.5, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  11%|█         | 76/679 [00:15<01:59,  5.04it/s, loss=3.5, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  11%|█         | 76/679 [00:15<01:59,  5.04it/s, loss=3.48, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  11%|█▏        | 77/679 [00:15<01:58,  5.06it/s, loss=3.48, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  11%|█▏        | 77/679 [00:15<01:58,  5.06it/s, loss=3.47, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  11%|█▏        | 78/679 [00:15<01:58,  5.09it/s, loss=3.47, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  11%|█▏        | 78/679 [00:15<01:58,  5.09it/s, loss=3.46, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  12%|█▏        | 79/679 [00:15<01:57,  5.11it/s, loss=3.46, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  12%|█▏        | 79/679 [00:15<01:57,  5.11it/s, loss=3.44, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  12%|█▏        | 80/679 [00:15<01:56,  5.13it/s, loss=3.44, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  12%|█▏        | 80/679 [00:15<01:56,  5.13it/s, loss=3.42, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  12%|█▏        | 81/679 [00:15<01:56,  5.15it/s, loss=3.42, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  12%|█▏        | 81/679 [00:15<01:56,  5.15it/s, loss=3.42, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  12%|█▏        | 82/679 [00:15<01:55,  5.17it/s, loss=3.42, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  12%|█▏        | 82/679 [00:15<01:55,  5.17it/s, loss=3.4, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  12%|█▏        | 83/679 [00:16<01:54,  5.19it/s, loss=3.4, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  12%|█▏        | 83/679 [00:16<01:54,  5.19it/s, loss=3.39, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  12%|█▏        | 84/679 [00:16<01:54,  5.21it/s, loss=3.39, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  12%|█▏        | 84/679 [00:16<01:54,  5.21it/s, loss=3.37, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  13%|█▎        | 85/679 [00:16<01:53,  5.22it/s, loss=3.37, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  13%|█▎        | 85/679 [00:16<01:53,  5.22it/s, loss=3.37, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  13%|█▎        | 86/679 [00:16<01:53,  5.24it/s, loss=3.37, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  13%|█▎        | 86/679 [00:16<01:53,  5.24it/s, loss=3.36, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  13%|█▎        | 87/679 [00:16<01:52,  5.25it/s, loss=3.36, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  13%|█▎        | 87/679 [00:16<01:52,  5.25it/s, loss=3.35, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  13%|█▎        | 88/679 [00:16<01:52,  5.27it/s, loss=3.35, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  13%|█▎        | 88/679 [00:16<01:52,  5.27it/s, loss=3.33, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  13%|█▎        | 89/679 [00:16<01:51,  5.29it/s, loss=3.33, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  13%|█▎        | 89/679 [00:16<01:51,  5.29it/s, loss=3.32, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  13%|█▎        | 90/679 [00:16<01:51,  5.30it/s, loss=3.32, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  13%|█▎        | 90/679 [00:16<01:51,  5.30it/s, loss=3.31, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  13%|█▎        | 91/679 [00:17<01:50,  5.32it/s, loss=3.31, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  13%|█▎        | 91/679 [00:17<01:50,  5.32it/s, loss=3.3, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  14%|█▎        | 92/679 [00:17<01:50,  5.33it/s, loss=3.3, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  14%|█▎        | 92/679 [00:17<01:50,  5.33it/s, loss=3.29, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  14%|█▎        | 93/679 [00:17<01:49,  5.35it/s, loss=3.29, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  14%|█▎        | 93/679 [00:17<01:49,  5.35it/s, loss=3.29, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  14%|█▍        | 94/679 [00:17<01:48,  5.37it/s, loss=3.29, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  14%|█▍        | 94/679 [00:17<01:48,  5.37it/s, loss=3.28, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  14%|█▍        | 95/679 [00:17<01:48,  5.39it/s, loss=3.28, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  14%|█▍        | 95/679 [00:17<01:48,  5.39it/s, loss=3.27, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  14%|█▍        | 96/679 [00:17<01:47,  5.41it/s, loss=3.27, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  14%|█▍        | 96/679 [00:17<01:47,  5.41it/s, loss=3.27, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  14%|█▍        | 97/679 [00:17<01:47,  5.42it/s, loss=3.27, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  14%|█▍        | 97/679 [00:17<01:47,  5.42it/s, loss=3.25, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  14%|█▍        | 98/679 [00:18<01:46,  5.44it/s, loss=3.25, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  14%|█▍        | 98/679 [00:18<01:46,  5.44it/s, loss=3.24, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  15%|█▍        | 99/679 [00:18<01:46,  5.45it/s, loss=3.24, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  15%|█▍        | 99/679 [00:18<01:46,  5.45it/s, loss=3.24, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  15%|█▍        | 100/679 [00:18<01:45,  5.47it/s, loss=3.24, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  15%|█▍        | 100/679 [00:18<01:45,  5.47it/s, loss=3.24, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  15%|█▍        | 101/679 [00:18<01:45,  5.48it/s, loss=3.24, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  15%|█▍        | 101/679 [00:18<01:45,  5.48it/s, loss=3.23, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  15%|█▌        | 102/679 [00:18<01:44,  5.50it/s, loss=3.23, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  15%|█▌        | 102/679 [00:18<01:44,  5.50it/s, loss=3.22, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  15%|█▌        | 103/679 [00:18<01:44,  5.51it/s, loss=3.22, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  15%|█▌        | 103/679 [00:18<01:44,  5.51it/s, loss=3.22, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  15%|█▌        | 104/679 [00:18<01:44,  5.53it/s, loss=3.22, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  15%|█▌        | 104/679 [00:18<01:44,  5.53it/s, loss=3.21, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  15%|█▌        | 105/679 [00:18<01:43,  5.54it/s, loss=3.21, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  15%|█▌        | 105/679 [00:18<01:43,  5.54it/s, loss=3.21, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  16%|█▌        | 106/679 [00:19<01:43,  5.56it/s, loss=3.21, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  16%|█▌        | 106/679 [00:19<01:43,  5.56it/s, loss=3.2, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  16%|█▌        | 107/679 [00:19<01:42,  5.57it/s, loss=3.2, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  16%|█▌        | 107/679 [00:19<01:42,  5.57it/s, loss=3.2, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  16%|█▌        | 108/679 [00:19<01:42,  5.58it/s, loss=3.2, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  16%|█▌        | 108/679 [00:19<01:42,  5.58it/s, loss=3.19, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  16%|█▌        | 109/679 [00:19<01:41,  5.59it/s, loss=3.19, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  16%|█▌        | 109/679 [00:19<01:41,  5.59it/s, loss=3.19, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  16%|█▌        | 110/679 [00:19<01:41,  5.61it/s, loss=3.19, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  16%|█▌        | 110/679 [00:19<01:41,  5.61it/s, loss=3.18, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  16%|█▋        | 111/679 [00:19<01:41,  5.62it/s, loss=3.18, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  16%|█▋        | 111/679 [00:19<01:41,  5.62it/s, loss=3.18, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  16%|█▋        | 112/679 [00:19<01:40,  5.64it/s, loss=3.18, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  16%|█▋        | 112/679 [00:19<01:40,  5.64it/s, loss=3.17, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  17%|█▋        | 113/679 [00:20<01:40,  5.65it/s, loss=3.17, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  17%|█▋        | 113/679 [00:20<01:40,  5.65it/s, loss=3.16, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  17%|█▋        | 114/679 [00:20<01:39,  5.66it/s, loss=3.16, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  17%|█▋        | 114/679 [00:20<01:39,  5.66it/s, loss=3.15, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  17%|█▋        | 115/679 [00:20<01:39,  5.67it/s, loss=3.15, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  17%|█▋        | 115/679 [00:20<01:39,  5.67it/s, loss=3.14, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  17%|█▋        | 116/679 [00:20<01:39,  5.68it/s, loss=3.14, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  17%|█▋        | 116/679 [00:20<01:39,  5.68it/s, loss=3.14, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  17%|█▋        | 117/679 [00:20<01:38,  5.70it/s, loss=3.14, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  17%|█▋        | 117/679 [00:20<01:38,  5.70it/s, loss=3.13, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  17%|█▋        | 118/679 [00:20<01:38,  5.71it/s, loss=3.13, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  17%|█▋        | 118/679 [00:20<01:38,  5.71it/s, loss=3.13, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  18%|█▊        | 119/679 [00:20<01:37,  5.72it/s, loss=3.13, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  18%|█▊        | 119/679 [00:20<01:37,  5.72it/s, loss=3.13, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  18%|█▊        | 120/679 [00:20<01:37,  5.73it/s, loss=3.13, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  18%|█▊        | 120/679 [00:20<01:37,  5.73it/s, loss=3.12, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  18%|█▊        | 121/679 [00:21<01:37,  5.74it/s, loss=3.12, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  18%|█▊        | 121/679 [00:21<01:37,  5.74it/s, loss=3.11, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  18%|█▊        | 122/679 [00:21<01:36,  5.75it/s, loss=3.11, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  18%|█▊        | 122/679 [00:21<01:36,  5.75it/s, loss=3.11, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  18%|█▊        | 123/679 [00:21<01:36,  5.76it/s, loss=3.11, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  18%|█▊        | 123/679 [00:21<01:36,  5.76it/s, loss=3.1, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  18%|█▊        | 124/679 [00:21<01:36,  5.77it/s, loss=3.1, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  18%|█▊        | 124/679 [00:21<01:36,  5.77it/s, loss=3.09, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  18%|█▊        | 125/679 [00:21<01:35,  5.78it/s, loss=3.09, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  18%|█▊        | 125/679 [00:21<01:35,  5.78it/s, loss=3.08, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  19%|█▊        | 126/679 [00:21<01:35,  5.79it/s, loss=3.08, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  19%|█▊        | 126/679 [00:21<01:35,  5.79it/s, loss=3.07, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  19%|█▊        | 127/679 [00:21<01:35,  5.80it/s, loss=3.07, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  19%|█▊        | 127/679 [00:21<01:35,  5.80it/s, loss=3.07, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  19%|█▉        | 128/679 [00:22<01:34,  5.81it/s, loss=3.07, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  19%|█▉        | 128/679 [00:22<01:34,  5.81it/s, loss=3.05, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  19%|█▉        | 129/679 [00:22<01:34,  5.82it/s, loss=3.05, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  19%|█▉        | 129/679 [00:22<01:34,  5.82it/s, loss=3.04, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  19%|█▉        | 130/679 [00:22<01:34,  5.83it/s, loss=3.04, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  19%|█▉        | 130/679 [00:22<01:34,  5.83it/s, loss=3.04, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  19%|█▉        | 131/679 [00:22<01:33,  5.84it/s, loss=3.04, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  19%|█▉        | 131/679 [00:22<01:33,  5.84it/s, loss=3.03, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  19%|█▉        | 132/679 [00:22<01:33,  5.85it/s, loss=3.03, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  19%|█▉        | 132/679 [00:22<01:33,  5.85it/s, loss=3.03, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  20%|█▉        | 133/679 [00:22<01:33,  5.86it/s, loss=3.03, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  20%|█▉        | 133/679 [00:22<01:33,  5.86it/s, loss=3.03, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  20%|█▉        | 134/679 [00:22<01:32,  5.87it/s, loss=3.03, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  20%|█▉        | 134/679 [00:22<01:32,  5.87it/s, loss=3.02, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  20%|█▉        | 135/679 [00:22<01:32,  5.88it/s, loss=3.02, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  20%|█▉        | 135/679 [00:22<01:32,  5.88it/s, loss=3.02, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  20%|██        | 136/679 [00:23<01:32,  5.89it/s, loss=3.02, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  20%|██        | 136/679 [00:23<01:32,  5.89it/s, loss=3.01, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  20%|██        | 137/679 [00:23<01:31,  5.90it/s, loss=3.01, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  20%|██        | 137/679 [00:23<01:31,  5.90it/s, loss=3.01, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  20%|██        | 138/679 [00:23<01:31,  5.91it/s, loss=3.01, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  20%|██        | 138/679 [00:23<01:31,  5.91it/s, loss=3, v_num=1.94e+7, val_acc=0.000]   
Epoch 0:  20%|██        | 139/679 [00:23<01:31,  5.91it/s, loss=3, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  20%|██        | 139/679 [00:23<01:31,  5.91it/s, loss=3, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  21%|██        | 140/679 [00:23<01:31,  5.92it/s, loss=3, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  21%|██        | 140/679 [00:23<01:31,  5.92it/s, loss=2.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  21%|██        | 141/679 [00:23<01:30,  5.93it/s, loss=2.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  21%|██        | 141/679 [00:23<01:30,  5.93it/s, loss=2.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  21%|██        | 142/679 [00:23<01:30,  5.94it/s, loss=2.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  21%|██        | 142/679 [00:23<01:30,  5.94it/s, loss=2.98, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  21%|██        | 143/679 [00:24<01:30,  5.95it/s, loss=2.98, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  21%|██        | 143/679 [00:24<01:30,  5.95it/s, loss=2.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  21%|██        | 144/679 [00:24<01:29,  5.95it/s, loss=2.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  21%|██        | 144/679 [00:24<01:29,  5.95it/s, loss=2.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  21%|██▏       | 145/679 [00:24<01:29,  5.96it/s, loss=2.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  21%|██▏       | 145/679 [00:24<01:29,  5.96it/s, loss=2.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  22%|██▏       | 146/679 [00:24<01:29,  5.97it/s, loss=2.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  22%|██▏       | 146/679 [00:24<01:29,  5.97it/s, loss=2.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  22%|██▏       | 147/679 [00:24<01:28,  5.98it/s, loss=2.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  22%|██▏       | 147/679 [00:24<01:28,  5.98it/s, loss=2.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  22%|██▏       | 148/679 [00:24<01:28,  5.99it/s, loss=2.99, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  22%|██▏       | 148/679 [00:24<01:28,  5.99it/s, loss=2.98, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  22%|██▏       | 149/679 [00:24<01:28,  5.99it/s, loss=2.98, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  22%|██▏       | 149/679 [00:24<01:28,  5.99it/s, loss=2.98, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  22%|██▏       | 150/679 [00:24<01:28,  6.00it/s, loss=2.98, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  22%|██▏       | 150/679 [00:24<01:28,  6.00it/s, loss=2.98, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  22%|██▏       | 151/679 [00:25<01:27,  6.01it/s, loss=2.98, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  22%|██▏       | 151/679 [00:25<01:27,  6.01it/s, loss=2.98, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  22%|██▏       | 152/679 [00:25<01:27,  6.01it/s, loss=2.98, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  22%|██▏       | 152/679 [00:25<01:27,  6.01it/s, loss=2.97, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  23%|██▎       | 153/679 [00:25<01:27,  6.02it/s, loss=2.97, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  23%|██▎       | 153/679 [00:25<01:27,  6.02it/s, loss=2.96, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  23%|██▎       | 154/679 [00:25<01:27,  6.03it/s, loss=2.96, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  23%|██▎       | 154/679 [00:25<01:27,  6.03it/s, loss=2.97, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  23%|██▎       | 155/679 [00:25<01:26,  6.03it/s, loss=2.97, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  23%|██▎       | 155/679 [00:25<01:26,  6.03it/s, loss=2.95, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  23%|██▎       | 156/679 [00:25<01:26,  6.04it/s, loss=2.95, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  23%|██▎       | 156/679 [00:25<01:26,  6.04it/s, loss=2.95, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  23%|██▎       | 157/679 [00:25<01:26,  6.05it/s, loss=2.95, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  23%|██▎       | 157/679 [00:25<01:26,  6.05it/s, loss=2.94, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  23%|██▎       | 158/679 [00:26<01:26,  6.06it/s, loss=2.94, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  23%|██▎       | 158/679 [00:26<01:26,  6.06it/s, loss=2.94, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  23%|██▎       | 159/679 [00:26<01:25,  6.06it/s, loss=2.94, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  23%|██▎       | 159/679 [00:26<01:25,  6.06it/s, loss=2.94, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  24%|██▎       | 160/679 [00:26<01:25,  6.07it/s, loss=2.94, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  24%|██▎       | 160/679 [00:26<01:25,  6.07it/s, loss=2.94, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  24%|██▎       | 161/679 [00:26<01:25,  6.07it/s, loss=2.94, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  24%|██▎       | 161/679 [00:26<01:25,  6.07it/s, loss=2.94, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  24%|██▍       | 162/679 [00:26<01:24,  6.08it/s, loss=2.94, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  24%|██▍       | 162/679 [00:26<01:24,  6.08it/s, loss=2.94, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  24%|██▍       | 163/679 [00:26<01:24,  6.09it/s, loss=2.94, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  24%|██▍       | 163/679 [00:26<01:24,  6.09it/s, loss=2.93, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  24%|██▍       | 164/679 [00:26<01:24,  6.10it/s, loss=2.93, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  24%|██▍       | 164/679 [00:26<01:24,  6.10it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  24%|██▍       | 165/679 [00:27<01:24,  6.10it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  24%|██▍       | 165/679 [00:27<01:24,  6.10it/s, loss=2.93, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  24%|██▍       | 166/679 [00:27<01:23,  6.11it/s, loss=2.93, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  24%|██▍       | 166/679 [00:27<01:23,  6.11it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  25%|██▍       | 167/679 [00:27<01:23,  6.12it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  25%|██▍       | 167/679 [00:27<01:23,  6.12it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  25%|██▍       | 168/679 [00:27<01:23,  6.12it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  25%|██▍       | 168/679 [00:27<01:23,  6.12it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  25%|██▍       | 169/679 [00:27<01:23,  6.13it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  25%|██▍       | 169/679 [00:27<01:23,  6.13it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  25%|██▌       | 170/679 [00:27<01:22,  6.14it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  25%|██▌       | 170/679 [00:27<01:22,  6.14it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  25%|██▌       | 171/679 [00:27<01:22,  6.14it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  25%|██▌       | 171/679 [00:27<01:22,  6.14it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  25%|██▌       | 172/679 [00:27<01:22,  6.15it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  25%|██▌       | 172/679 [00:27<01:22,  6.15it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  25%|██▌       | 173/679 [00:28<01:22,  6.16it/s, loss=2.92, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  25%|██▌       | 173/679 [00:28<01:22,  6.16it/s, loss=2.91, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  26%|██▌       | 174/679 [00:28<01:21,  6.16it/s, loss=2.91, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  26%|██▌       | 174/679 [00:28<01:21,  6.16it/s, loss=2.91, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  26%|██▌       | 175/679 [00:28<01:21,  6.17it/s, loss=2.91, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  26%|██▌       | 175/679 [00:28<01:21,  6.17it/s, loss=2.91, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  26%|██▌       | 176/679 [00:28<01:21,  6.18it/s, loss=2.91, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  26%|██▌       | 176/679 [00:28<01:21,  6.18it/s, loss=2.91, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  26%|██▌       | 177/679 [00:28<01:21,  6.18it/s, loss=2.91, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  26%|██▌       | 177/679 [00:28<01:21,  6.18it/s, loss=2.91, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  26%|██▌       | 178/679 [00:28<01:21,  6.18it/s, loss=2.91, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  26%|██▌       | 178/679 [00:28<01:21,  6.18it/s, loss=2.9, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  26%|██▋       | 179/679 [00:28<01:20,  6.19it/s, loss=2.9, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  26%|██▋       | 179/679 [00:28<01:20,  6.19it/s, loss=2.9, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  27%|██▋       | 180/679 [00:29<01:20,  6.20it/s, loss=2.9, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  27%|██▋       | 180/679 [00:29<01:20,  6.20it/s, loss=2.9, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  27%|██▋       | 181/679 [00:29<01:20,  6.20it/s, loss=2.9, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  27%|██▋       | 181/679 [00:29<01:20,  6.20it/s, loss=2.9, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  27%|██▋       | 182/679 [00:29<01:20,  6.21it/s, loss=2.9, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  27%|██▋       | 182/679 [00:29<01:20,  6.21it/s, loss=2.89, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  27%|██▋       | 183/679 [00:29<01:19,  6.21it/s, loss=2.89, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  27%|██▋       | 183/679 [00:29<01:19,  6.21it/s, loss=2.89, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  27%|██▋       | 184/679 [00:29<01:19,  6.22it/s, loss=2.89, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  27%|██▋       | 184/679 [00:29<01:19,  6.22it/s, loss=2.89, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  27%|██▋       | 185/679 [00:29<01:19,  6.22it/s, loss=2.89, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  27%|██▋       | 185/679 [00:29<01:19,  6.22it/s, loss=2.87, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  27%|██▋       | 186/679 [00:29<01:19,  6.23it/s, loss=2.87, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  27%|██▋       | 186/679 [00:29<01:19,  6.23it/s, loss=2.87, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  28%|██▊       | 187/679 [00:30<01:18,  6.23it/s, loss=2.87, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  28%|██▊       | 187/679 [00:30<01:18,  6.23it/s, loss=2.88, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  28%|██▊       | 188/679 [00:30<01:18,  6.24it/s, loss=2.88, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  28%|██▊       | 188/679 [00:30<01:18,  6.24it/s, loss=2.88, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  28%|██▊       | 189/679 [00:30<01:18,  6.24it/s, loss=2.88, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  28%|██▊       | 189/679 [00:30<01:18,  6.24it/s, loss=2.88, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  28%|██▊       | 190/679 [00:30<01:18,  6.25it/s, loss=2.88, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  28%|██▊       | 190/679 [00:30<01:18,  6.25it/s, loss=2.87, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  28%|██▊       | 191/679 [00:30<01:18,  6.25it/s, loss=2.87, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  28%|██▊       | 191/679 [00:30<01:18,  6.25it/s, loss=2.87, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  28%|██▊       | 192/679 [00:30<01:17,  6.26it/s, loss=2.87, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  28%|██▊       | 192/679 [00:30<01:17,  6.26it/s, loss=2.87, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  28%|██▊       | 193/679 [00:30<01:17,  6.26it/s, loss=2.87, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  28%|██▊       | 193/679 [00:30<01:17,  6.26it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  29%|██▊       | 194/679 [00:30<01:17,  6.27it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  29%|██▊       | 194/679 [00:30<01:17,  6.27it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  29%|██▊       | 195/679 [00:31<01:17,  6.27it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  29%|██▊       | 195/679 [00:31<01:17,  6.27it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  29%|██▉       | 196/679 [00:31<01:16,  6.28it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  29%|██▉       | 196/679 [00:31<01:16,  6.28it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  29%|██▉       | 197/679 [00:31<01:16,  6.28it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  29%|██▉       | 197/679 [00:31<01:16,  6.28it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  29%|██▉       | 198/679 [00:31<01:16,  6.29it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  29%|██▉       | 198/679 [00:31<01:16,  6.29it/s, loss=2.87, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  29%|██▉       | 199/679 [00:31<01:16,  6.29it/s, loss=2.87, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  29%|██▉       | 199/679 [00:31<01:16,  6.29it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  29%|██▉       | 200/679 [00:31<01:16,  6.30it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  29%|██▉       | 200/679 [00:31<01:16,  6.30it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  30%|██▉       | 201/679 [00:31<01:15,  6.30it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  30%|██▉       | 201/679 [00:31<01:15,  6.30it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  30%|██▉       | 202/679 [00:32<01:15,  6.31it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  30%|██▉       | 202/679 [00:32<01:15,  6.31it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  30%|██▉       | 203/679 [00:32<01:15,  6.31it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  30%|██▉       | 203/679 [00:32<01:15,  6.31it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  30%|███       | 204/679 [00:32<01:15,  6.32it/s, loss=2.86, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  30%|███       | 204/679 [00:32<01:15,  6.32it/s, loss=2.85, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  30%|███       | 205/679 [00:32<01:15,  6.32it/s, loss=2.85, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  30%|███       | 205/679 [00:32<01:15,  6.32it/s, loss=2.85, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  30%|███       | 206/679 [00:32<01:14,  6.32it/s, loss=2.85, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  30%|███       | 206/679 [00:32<01:14,  6.32it/s, loss=2.85, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  30%|███       | 207/679 [00:32<01:14,  6.33it/s, loss=2.85, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  30%|███       | 207/679 [00:32<01:14,  6.33it/s, loss=2.84, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  31%|███       | 208/679 [00:32<01:14,  6.33it/s, loss=2.84, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  31%|███       | 208/679 [00:32<01:14,  6.33it/s, loss=2.84, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  31%|███       | 209/679 [00:32<01:14,  6.34it/s, loss=2.84, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  31%|███       | 209/679 [00:32<01:14,  6.34it/s, loss=2.83, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  31%|███       | 210/679 [00:33<01:13,  6.34it/s, loss=2.83, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  31%|███       | 210/679 [00:33<01:13,  6.34it/s, loss=2.83, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  31%|███       | 211/679 [00:33<01:13,  6.34it/s, loss=2.83, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  31%|███       | 211/679 [00:33<01:13,  6.34it/s, loss=2.83, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  31%|███       | 212/679 [00:33<01:13,  6.35it/s, loss=2.83, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  31%|███       | 212/679 [00:33<01:13,  6.35it/s, loss=2.83, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  31%|███▏      | 213/679 [00:33<01:13,  6.35it/s, loss=2.83, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  31%|███▏      | 213/679 [00:33<01:13,  6.35it/s, loss=2.83, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  32%|███▏      | 214/679 [00:33<01:13,  6.36it/s, loss=2.83, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  32%|███▏      | 214/679 [00:33<01:13,  6.36it/s, loss=2.82, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  32%|███▏      | 215/679 [00:33<01:12,  6.37it/s, loss=2.82, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  32%|███▏      | 215/679 [00:33<01:12,  6.37it/s, loss=2.82, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  32%|███▏      | 216/679 [00:33<01:12,  6.37it/s, loss=2.82, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  32%|███▏      | 216/679 [00:33<01:12,  6.37it/s, loss=2.82, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  32%|███▏      | 217/679 [00:34<01:12,  6.37it/s, loss=2.82, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  32%|███▏      | 217/679 [00:34<01:12,  6.37it/s, loss=2.81, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  32%|███▏      | 218/679 [00:34<01:12,  6.38it/s, loss=2.81, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  32%|███▏      | 218/679 [00:34<01:12,  6.38it/s, loss=2.8, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  32%|███▏      | 219/679 [00:34<01:12,  6.38it/s, loss=2.8, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  32%|███▏      | 219/679 [00:34<01:12,  6.38it/s, loss=2.8, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  32%|███▏      | 220/679 [00:34<01:11,  6.38it/s, loss=2.8, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  32%|███▏      | 220/679 [00:34<01:11,  6.38it/s, loss=2.8, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  33%|███▎      | 221/679 [00:34<01:11,  6.39it/s, loss=2.8, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  33%|███▎      | 221/679 [00:34<01:11,  6.39it/s, loss=2.79, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  33%|███▎      | 222/679 [00:34<01:11,  6.39it/s, loss=2.79, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  33%|███▎      | 222/679 [00:34<01:11,  6.39it/s, loss=2.79, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  33%|███▎      | 223/679 [00:34<01:11,  6.40it/s, loss=2.79, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  33%|███▎      | 223/679 [00:34<01:11,  6.40it/s, loss=2.79, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  33%|███▎      | 224/679 [00:35<01:11,  6.40it/s, loss=2.79, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  33%|███▎      | 224/679 [00:35<01:11,  6.40it/s, loss=2.79, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  33%|███▎      | 225/679 [00:35<01:10,  6.40it/s, loss=2.79, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  33%|███▎      | 225/679 [00:35<01:10,  6.40it/s, loss=2.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  33%|███▎      | 226/679 [00:35<01:10,  6.40it/s, loss=2.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  33%|███▎      | 226/679 [00:35<01:10,  6.40it/s, loss=2.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  33%|███▎      | 227/679 [00:35<01:10,  6.41it/s, loss=2.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  33%|███▎      | 227/679 [00:35<01:10,  6.41it/s, loss=2.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  34%|███▎      | 228/679 [00:35<01:10,  6.41it/s, loss=2.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  34%|███▎      | 228/679 [00:35<01:10,  6.41it/s, loss=2.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  34%|███▎      | 229/679 [00:35<01:10,  6.42it/s, loss=2.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  34%|███▎      | 229/679 [00:35<01:10,  6.42it/s, loss=2.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  34%|███▍      | 230/679 [00:35<01:09,  6.42it/s, loss=2.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  34%|███▍      | 230/679 [00:35<01:09,  6.42it/s, loss=2.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  34%|███▍      | 231/679 [00:35<01:09,  6.42it/s, loss=2.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  34%|███▍      | 231/679 [00:35<01:09,  6.42it/s, loss=2.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  34%|███▍      | 232/679 [00:36<01:09,  6.43it/s, loss=2.78, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  34%|███▍      | 232/679 [00:36<01:09,  6.43it/s, loss=2.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  34%|███▍      | 233/679 [00:36<01:09,  6.43it/s, loss=2.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  34%|███▍      | 233/679 [00:36<01:09,  6.43it/s, loss=2.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  34%|███▍      | 234/679 [00:36<01:09,  6.44it/s, loss=2.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  34%|███▍      | 234/679 [00:36<01:09,  6.44it/s, loss=2.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  35%|███▍      | 235/679 [00:36<01:08,  6.44it/s, loss=2.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  35%|███▍      | 235/679 [00:36<01:08,  6.44it/s, loss=2.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  35%|███▍      | 236/679 [00:36<01:08,  6.44it/s, loss=2.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  35%|███▍      | 236/679 [00:36<01:08,  6.44it/s, loss=2.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  35%|███▍      | 237/679 [00:36<01:08,  6.44it/s, loss=2.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  35%|███▍      | 237/679 [00:36<01:08,  6.44it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  35%|███▌      | 238/679 [00:36<01:08,  6.45it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  35%|███▌      | 238/679 [00:36<01:08,  6.45it/s, loss=2.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  35%|███▌      | 239/679 [00:37<01:08,  6.45it/s, loss=2.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  35%|███▌      | 239/679 [00:37<01:08,  6.45it/s, loss=2.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  35%|███▌      | 240/679 [00:37<01:08,  6.45it/s, loss=2.77, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  35%|███▌      | 240/679 [00:37<01:08,  6.45it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  35%|███▌      | 241/679 [00:37<01:07,  6.46it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  35%|███▌      | 241/679 [00:37<01:07,  6.46it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  36%|███▌      | 242/679 [00:37<01:07,  6.46it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  36%|███▌      | 242/679 [00:37<01:07,  6.46it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  36%|███▌      | 243/679 [00:37<01:07,  6.46it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  36%|███▌      | 243/679 [00:37<01:07,  6.46it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  36%|███▌      | 244/679 [00:37<01:07,  6.47it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  36%|███▌      | 244/679 [00:37<01:07,  6.47it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  36%|███▌      | 245/679 [00:37<01:07,  6.47it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  36%|███▌      | 245/679 [00:37<01:07,  6.47it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  36%|███▌      | 246/679 [00:37<01:06,  6.48it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  36%|███▌      | 246/679 [00:37<01:06,  6.48it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  36%|███▋      | 247/679 [00:38<01:06,  6.48it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  36%|███▋      | 247/679 [00:38<01:06,  6.48it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  37%|███▋      | 248/679 [00:38<01:06,  6.48it/s, loss=2.76, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  37%|███▋      | 248/679 [00:38<01:06,  6.48it/s, loss=2.75, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  37%|███▋      | 249/679 [00:38<01:06,  6.49it/s, loss=2.75, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  37%|███▋      | 249/679 [00:38<01:06,  6.49it/s, loss=2.75, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  37%|███▋      | 250/679 [00:38<01:06,  6.49it/s, loss=2.75, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  37%|███▋      | 250/679 [00:38<01:06,  6.49it/s, loss=2.75, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  37%|███▋      | 251/679 [00:38<01:05,  6.49it/s, loss=2.75, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  37%|███▋      | 251/679 [00:38<01:05,  6.49it/s, loss=2.75, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  37%|███▋      | 252/679 [00:38<01:05,  6.50it/s, loss=2.75, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  37%|███▋      | 252/679 [00:38<01:05,  6.50it/s, loss=2.75, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  37%|███▋      | 253/679 [00:38<01:05,  6.50it/s, loss=2.75, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  37%|███▋      | 253/679 [00:38<01:05,  6.50it/s, loss=2.75, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  37%|███▋      | 254/679 [00:39<01:05,  6.50it/s, loss=2.75, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  37%|███▋      | 254/679 [00:39<01:05,  6.50it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  38%|███▊      | 255/679 [00:39<01:05,  6.50it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  38%|███▊      | 255/679 [00:39<01:05,  6.50it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  38%|███▊      | 256/679 [00:39<01:05,  6.51it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  38%|███▊      | 256/679 [00:39<01:05,  6.51it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  38%|███▊      | 257/679 [00:39<01:04,  6.51it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  38%|███▊      | 257/679 [00:39<01:04,  6.51it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  38%|███▊      | 258/679 [00:39<01:04,  6.51it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  38%|███▊      | 258/679 [00:39<01:04,  6.51it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  38%|███▊      | 259/679 [00:39<01:04,  6.52it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  38%|███▊      | 259/679 [00:39<01:04,  6.52it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  38%|███▊      | 260/679 [00:39<01:04,  6.52it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  38%|███▊      | 260/679 [00:39<01:04,  6.52it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  38%|███▊      | 261/679 [00:40<01:04,  6.52it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  38%|███▊      | 261/679 [00:40<01:04,  6.52it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  39%|███▊      | 262/679 [00:40<01:03,  6.53it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  39%|███▊      | 262/679 [00:40<01:03,  6.53it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  39%|███▊      | 263/679 [00:40<01:03,  6.53it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  39%|███▊      | 263/679 [00:40<01:03,  6.53it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  39%|███▉      | 264/679 [00:40<01:03,  6.53it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  39%|███▉      | 264/679 [00:40<01:03,  6.53it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  39%|███▉      | 265/679 [00:40<01:03,  6.53it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  39%|███▉      | 265/679 [00:40<01:03,  6.53it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  39%|███▉      | 266/679 [00:40<01:03,  6.54it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  39%|███▉      | 266/679 [00:40<01:03,  6.54it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  39%|███▉      | 267/679 [00:40<01:02,  6.54it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  39%|███▉      | 267/679 [00:40<01:02,  6.54it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  39%|███▉      | 268/679 [00:40<01:02,  6.54it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  39%|███▉      | 268/679 [00:40<01:02,  6.54it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  40%|███▉      | 269/679 [00:41<01:02,  6.55it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  40%|███▉      | 269/679 [00:41<01:02,  6.55it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  40%|███▉      | 270/679 [00:41<01:02,  6.55it/s, loss=2.74, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  40%|███▉      | 270/679 [00:41<01:02,  6.55it/s, loss=2.73, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  40%|███▉      | 271/679 [00:41<01:02,  6.55it/s, loss=2.73, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  40%|███▉      | 271/679 [00:41<01:02,  6.55it/s, loss=2.73, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  40%|████      | 272/679 [00:41<01:02,  6.56it/s, loss=2.73, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  40%|████      | 272/679 [00:41<01:02,  6.56it/s, loss=2.72, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  40%|████      | 273/679 [00:41<01:01,  6.56it/s, loss=2.72, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  40%|████      | 273/679 [00:41<01:01,  6.56it/s, loss=2.72, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  40%|████      | 274/679 [00:41<01:01,  6.56it/s, loss=2.72, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  40%|████      | 274/679 [00:41<01:01,  6.56it/s, loss=2.72, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  41%|████      | 275/679 [00:41<01:01,  6.56it/s, loss=2.72, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  41%|████      | 275/679 [00:41<01:01,  6.56it/s, loss=2.72, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  41%|████      | 276/679 [00:42<01:01,  6.57it/s, loss=2.72, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  41%|████      | 276/679 [00:42<01:01,  6.57it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  41%|████      | 277/679 [00:42<01:01,  6.57it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  41%|████      | 277/679 [00:42<01:01,  6.57it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  41%|████      | 278/679 [00:42<01:01,  6.57it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  41%|████      | 278/679 [00:42<01:01,  6.57it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  41%|████      | 279/679 [00:42<01:00,  6.57it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  41%|████      | 279/679 [00:42<01:00,  6.57it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  41%|████      | 280/679 [00:42<01:00,  6.58it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  41%|████      | 280/679 [00:42<01:00,  6.58it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  41%|████▏     | 281/679 [00:42<01:00,  6.58it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  41%|████▏     | 281/679 [00:42<01:00,  6.58it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  42%|████▏     | 282/679 [00:42<01:00,  6.58it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  42%|████▏     | 282/679 [00:42<01:00,  6.58it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  42%|████▏     | 283/679 [00:42<01:00,  6.58it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  42%|████▏     | 283/679 [00:42<01:00,  6.58it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  42%|████▏     | 284/679 [00:43<00:59,  6.59it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  42%|████▏     | 284/679 [00:43<00:59,  6.59it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  42%|████▏     | 285/679 [00:43<00:59,  6.59it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  42%|████▏     | 285/679 [00:43<00:59,  6.59it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  42%|████▏     | 286/679 [00:43<00:59,  6.59it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  42%|████▏     | 286/679 [00:43<00:59,  6.59it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  42%|████▏     | 287/679 [00:43<00:59,  6.59it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  42%|████▏     | 287/679 [00:43<00:59,  6.59it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  42%|████▏     | 288/679 [00:43<00:59,  6.60it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  42%|████▏     | 288/679 [00:43<00:59,  6.60it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  43%|████▎     | 289/679 [00:43<00:59,  6.60it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  43%|████▎     | 289/679 [00:43<00:59,  6.60it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  43%|████▎     | 290/679 [00:43<00:58,  6.60it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  43%|████▎     | 290/679 [00:43<00:58,  6.60it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  43%|████▎     | 291/679 [00:44<00:58,  6.60it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  43%|████▎     | 291/679 [00:44<00:58,  6.60it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  43%|████▎     | 292/679 [00:44<00:58,  6.60it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  43%|████▎     | 292/679 [00:44<00:58,  6.60it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  43%|████▎     | 293/679 [00:44<00:58,  6.61it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  43%|████▎     | 293/679 [00:44<00:58,  6.61it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  43%|████▎     | 294/679 [00:44<00:58,  6.61it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  43%|████▎     | 294/679 [00:44<00:58,  6.61it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  43%|████▎     | 295/679 [00:44<00:58,  6.61it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  43%|████▎     | 295/679 [00:44<00:58,  6.61it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  44%|████▎     | 296/679 [00:44<00:57,  6.61it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  44%|████▎     | 296/679 [00:44<00:57,  6.61it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  44%|████▎     | 297/679 [00:44<00:57,  6.62it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  44%|████▎     | 297/679 [00:44<00:57,  6.62it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  44%|████▍     | 298/679 [00:45<00:57,  6.62it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  44%|████▍     | 298/679 [00:45<00:57,  6.62it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  44%|████▍     | 299/679 [00:45<00:57,  6.62it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  44%|████▍     | 299/679 [00:45<00:57,  6.62it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  44%|████▍     | 300/679 [00:45<00:57,  6.62it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  44%|████▍     | 300/679 [00:45<00:57,  6.62it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  44%|████▍     | 301/679 [00:45<00:57,  6.63it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  44%|████▍     | 301/679 [00:45<00:57,  6.63it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  44%|████▍     | 302/679 [00:45<00:56,  6.63it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  44%|████▍     | 302/679 [00:45<00:56,  6.63it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  45%|████▍     | 303/679 [00:45<00:56,  6.63it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  45%|████▍     | 303/679 [00:45<00:56,  6.63it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  45%|████▍     | 304/679 [00:45<00:56,  6.63it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  45%|████▍     | 304/679 [00:45<00:56,  6.63it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  45%|████▍     | 305/679 [00:45<00:56,  6.64it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  45%|████▍     | 305/679 [00:45<00:56,  6.64it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  45%|████▌     | 306/679 [00:46<00:56,  6.64it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  45%|████▌     | 306/679 [00:46<00:56,  6.64it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  45%|████▌     | 307/679 [00:46<00:56,  6.64it/s, loss=2.71, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  45%|████▌     | 307/679 [00:46<00:56,  6.64it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  45%|████▌     | 308/679 [00:46<00:55,  6.64it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  45%|████▌     | 308/679 [00:46<00:55,  6.64it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  46%|████▌     | 309/679 [00:46<00:55,  6.64it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  46%|████▌     | 309/679 [00:46<00:55,  6.64it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  46%|████▌     | 310/679 [00:46<00:55,  6.65it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  46%|████▌     | 310/679 [00:46<00:55,  6.65it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  46%|████▌     | 311/679 [00:46<00:55,  6.65it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  46%|████▌     | 311/679 [00:46<00:55,  6.65it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  46%|████▌     | 312/679 [00:46<00:55,  6.65it/s, loss=2.7, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  46%|████▌     | 312/679 [00:46<00:55,  6.65it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  46%|████▌     | 313/679 [00:47<00:55,  6.65it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  46%|████▌     | 313/679 [00:47<00:55,  6.65it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  46%|████▌     | 314/679 [00:47<00:54,  6.65it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  46%|████▌     | 314/679 [00:47<00:54,  6.65it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  46%|████▋     | 315/679 [00:47<00:54,  6.66it/s, loss=2.69, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  46%|████▋     | 315/679 [00:47<00:54,  6.66it/s, loss=2.68, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  47%|████▋     | 316/679 [00:47<00:54,  6.66it/s, loss=2.68, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  47%|████▋     | 316/679 [00:47<00:54,  6.66it/s, loss=2.67, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  47%|████▋     | 317/679 [00:47<00:54,  6.66it/s, loss=2.67, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  47%|████▋     | 317/679 [00:47<00:54,  6.66it/s, loss=2.67, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  47%|████▋     | 318/679 [00:47<00:54,  6.66it/s, loss=2.67, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  47%|████▋     | 318/679 [00:47<00:54,  6.66it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  47%|████▋     | 319/679 [00:47<00:54,  6.67it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  47%|████▋     | 319/679 [00:47<00:54,  6.67it/s, loss=2.67, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  47%|████▋     | 320/679 [00:47<00:53,  6.67it/s, loss=2.67, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  47%|████▋     | 320/679 [00:47<00:53,  6.67it/s, loss=2.67, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  47%|████▋     | 321/679 [00:48<00:53,  6.67it/s, loss=2.67, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  47%|████▋     | 321/679 [00:48<00:53,  6.67it/s, loss=2.67, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  47%|████▋     | 322/679 [00:48<00:53,  6.67it/s, loss=2.67, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  47%|████▋     | 322/679 [00:48<00:53,  6.67it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  48%|████▊     | 323/679 [00:48<00:53,  6.67it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  48%|████▊     | 323/679 [00:48<00:53,  6.67it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  48%|████▊     | 324/679 [00:48<00:53,  6.68it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  48%|████▊     | 324/679 [00:48<00:53,  6.68it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  48%|████▊     | 325/679 [00:48<00:52,  6.68it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  48%|████▊     | 325/679 [00:48<00:52,  6.68it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  48%|████▊     | 326/679 [00:48<00:52,  6.68it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  48%|████▊     | 326/679 [00:48<00:52,  6.68it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  48%|████▊     | 327/679 [00:48<00:52,  6.68it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  48%|████▊     | 327/679 [00:48<00:52,  6.68it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  48%|████▊     | 328/679 [00:49<00:52,  6.69it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  48%|████▊     | 328/679 [00:49<00:52,  6.69it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  48%|████▊     | 329/679 [00:49<00:52,  6.69it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  48%|████▊     | 329/679 [00:49<00:52,  6.69it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  49%|████▊     | 330/679 [00:49<00:52,  6.69it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  49%|████▊     | 330/679 [00:49<00:52,  6.69it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  49%|████▊     | 331/679 [00:49<00:51,  6.69it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  49%|████▊     | 331/679 [00:49<00:51,  6.69it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  49%|████▉     | 332/679 [00:49<00:51,  6.70it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  49%|████▉     | 332/679 [00:49<00:51,  6.69it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  49%|████▉     | 333/679 [00:49<00:51,  6.70it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  49%|████▉     | 333/679 [00:49<00:51,  6.70it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  49%|████▉     | 334/679 [00:49<00:51,  6.70it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  49%|████▉     | 334/679 [00:49<00:51,  6.70it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  49%|████▉     | 335/679 [00:49<00:51,  6.70it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  49%|████▉     | 335/679 [00:49<00:51,  6.70it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  49%|████▉     | 336/679 [00:50<00:51,  6.70it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  49%|████▉     | 336/679 [00:50<00:51,  6.70it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  50%|████▉     | 337/679 [00:50<00:51,  6.71it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  50%|████▉     | 337/679 [00:50<00:51,  6.71it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  50%|████▉     | 338/679 [00:50<00:50,  6.71it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  50%|████▉     | 338/679 [00:50<00:50,  6.71it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  50%|████▉     | 339/679 [00:50<00:50,  6.71it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  50%|████▉     | 339/679 [00:50<00:50,  6.71it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  50%|█████     | 340/679 [00:50<00:50,  6.71it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  50%|█████     | 340/679 [00:50<00:50,  6.71it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  50%|█████     | 341/679 [00:50<00:50,  6.71it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  50%|█████     | 341/679 [00:50<00:50,  6.71it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  50%|█████     | 342/679 [00:50<00:50,  6.71it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  50%|█████     | 342/679 [00:50<00:50,  6.71it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  51%|█████     | 343/679 [00:51<00:50,  6.71it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  51%|█████     | 343/679 [00:51<00:50,  6.71it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  51%|█████     | 344/679 [00:51<00:49,  6.72it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  51%|█████     | 344/679 [00:51<00:49,  6.72it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  51%|█████     | 345/679 [00:51<00:49,  6.72it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  51%|█████     | 345/679 [00:51<00:49,  6.72it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  51%|█████     | 346/679 [00:51<00:49,  6.72it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  51%|█████     | 346/679 [00:51<00:49,  6.72it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  51%|█████     | 347/679 [00:51<00:49,  6.72it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  51%|█████     | 347/679 [00:51<00:49,  6.72it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  51%|█████▏    | 348/679 [00:51<00:49,  6.72it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  51%|█████▏    | 348/679 [00:51<00:49,  6.72it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  51%|█████▏    | 349/679 [00:51<00:49,  6.72it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  51%|█████▏    | 349/679 [00:51<00:49,  6.72it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  52%|█████▏    | 350/679 [00:52<00:48,  6.73it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  52%|█████▏    | 350/679 [00:52<00:48,  6.73it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  52%|█████▏    | 351/679 [00:52<00:48,  6.73it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  52%|█████▏    | 351/679 [00:52<00:48,  6.73it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  52%|█████▏    | 352/679 [00:52<00:48,  6.73it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  52%|█████▏    | 352/679 [00:52<00:48,  6.73it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  52%|█████▏    | 353/679 [00:52<00:48,  6.73it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  52%|█████▏    | 353/679 [00:52<00:48,  6.73it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  52%|█████▏    | 354/679 [00:52<00:48,  6.73it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  52%|█████▏    | 354/679 [00:52<00:48,  6.73it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  52%|█████▏    | 355/679 [00:52<00:48,  6.73it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  52%|█████▏    | 355/679 [00:52<00:48,  6.73it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  52%|█████▏    | 356/679 [00:52<00:47,  6.74it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  52%|█████▏    | 356/679 [00:52<00:47,  6.74it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  53%|█████▎    | 357/679 [00:52<00:47,  6.74it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  53%|█████▎    | 357/679 [00:52<00:47,  6.74it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  53%|█████▎    | 358/679 [00:53<00:47,  6.74it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  53%|█████▎    | 358/679 [00:53<00:47,  6.74it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  53%|█████▎    | 359/679 [00:53<00:47,  6.74it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  53%|█████▎    | 359/679 [00:53<00:47,  6.74it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  53%|█████▎    | 360/679 [00:53<00:47,  6.75it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  53%|█████▎    | 360/679 [00:53<00:47,  6.75it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  53%|█████▎    | 361/679 [00:53<00:47,  6.75it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  53%|█████▎    | 361/679 [00:53<00:47,  6.75it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  53%|█████▎    | 362/679 [00:53<00:46,  6.75it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  53%|█████▎    | 362/679 [00:53<00:46,  6.75it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  53%|█████▎    | 363/679 [00:53<00:46,  6.75it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  53%|█████▎    | 363/679 [00:53<00:46,  6.75it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  54%|█████▎    | 364/679 [00:53<00:46,  6.75it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  54%|█████▎    | 364/679 [00:53<00:46,  6.75it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  54%|█████▍    | 365/679 [00:54<00:46,  6.75it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  54%|█████▍    | 365/679 [00:54<00:46,  6.75it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  54%|█████▍    | 366/679 [00:54<00:46,  6.76it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  54%|█████▍    | 366/679 [00:54<00:46,  6.76it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  54%|█████▍    | 367/679 [00:54<00:46,  6.76it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  54%|█████▍    | 367/679 [00:54<00:46,  6.76it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  54%|█████▍    | 368/679 [00:54<00:45,  6.76it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  54%|█████▍    | 368/679 [00:54<00:45,  6.76it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  54%|█████▍    | 369/679 [00:54<00:45,  6.76it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  54%|█████▍    | 369/679 [00:54<00:45,  6.76it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  54%|█████▍    | 370/679 [00:54<00:45,  6.76it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  54%|█████▍    | 370/679 [00:54<00:45,  6.76it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  55%|█████▍    | 371/679 [00:54<00:45,  6.76it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  55%|█████▍    | 371/679 [00:54<00:45,  6.76it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  55%|█████▍    | 372/679 [00:54<00:45,  6.77it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  55%|█████▍    | 372/679 [00:54<00:45,  6.77it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  55%|█████▍    | 373/679 [00:55<00:45,  6.77it/s, loss=2.66, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  55%|█████▍    | 373/679 [00:55<00:45,  6.77it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  55%|█████▌    | 374/679 [00:55<00:45,  6.77it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  55%|█████▌    | 374/679 [00:55<00:45,  6.77it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  55%|█████▌    | 375/679 [00:55<00:44,  6.77it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  55%|█████▌    | 375/679 [00:55<00:44,  6.77it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  55%|█████▌    | 376/679 [00:55<00:44,  6.77it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  55%|█████▌    | 376/679 [00:55<00:44,  6.77it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  56%|█████▌    | 377/679 [00:55<00:44,  6.77it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  56%|█████▌    | 377/679 [00:55<00:44,  6.77it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  56%|█████▌    | 378/679 [00:55<00:44,  6.78it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  56%|█████▌    | 378/679 [00:55<00:44,  6.78it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  56%|█████▌    | 379/679 [00:55<00:44,  6.78it/s, loss=2.65, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  56%|█████▌    | 379/679 [00:55<00:44,  6.78it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  56%|█████▌    | 380/679 [00:56<00:44,  6.78it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  56%|█████▌    | 380/679 [00:56<00:44,  6.78it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  56%|█████▌    | 381/679 [00:56<00:43,  6.78it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  56%|█████▌    | 381/679 [00:56<00:43,  6.78it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  56%|█████▋    | 382/679 [00:56<00:43,  6.78it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  56%|█████▋    | 382/679 [00:56<00:43,  6.78it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  56%|█████▋    | 383/679 [00:56<00:43,  6.78it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  56%|█████▋    | 383/679 [00:56<00:43,  6.78it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  57%|█████▋    | 384/679 [00:56<00:43,  6.78it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  57%|█████▋    | 384/679 [00:56<00:43,  6.78it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  57%|█████▋    | 385/679 [00:56<00:43,  6.78it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  57%|█████▋    | 385/679 [00:56<00:43,  6.78it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  57%|█████▋    | 386/679 [00:56<00:43,  6.79it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  57%|█████▋    | 386/679 [00:56<00:43,  6.79it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  57%|█████▋    | 387/679 [00:57<00:43,  6.79it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  57%|█████▋    | 387/679 [00:57<00:43,  6.79it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  57%|█████▋    | 388/679 [00:57<00:42,  6.79it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  57%|█████▋    | 388/679 [00:57<00:42,  6.79it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  57%|█████▋    | 389/679 [00:57<00:42,  6.79it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  57%|█████▋    | 389/679 [00:57<00:42,  6.79it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  57%|█████▋    | 390/679 [00:57<00:42,  6.79it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  57%|█████▋    | 390/679 [00:57<00:42,  6.79it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  58%|█████▊    | 391/679 [00:57<00:42,  6.79it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  58%|█████▊    | 391/679 [00:57<00:42,  6.79it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  58%|█████▊    | 392/679 [00:57<00:42,  6.79it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  58%|█████▊    | 392/679 [00:57<00:42,  6.79it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  58%|█████▊    | 393/679 [00:57<00:42,  6.79it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  58%|█████▊    | 393/679 [00:57<00:42,  6.79it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  58%|█████▊    | 394/679 [00:57<00:41,  6.80it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  58%|█████▊    | 394/679 [00:57<00:41,  6.79it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  58%|█████▊    | 395/679 [00:58<00:41,  6.79it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  58%|█████▊    | 395/679 [00:58<00:41,  6.79it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  58%|█████▊    | 396/679 [00:58<00:41,  6.80it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  58%|█████▊    | 396/679 [00:58<00:41,  6.80it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  58%|█████▊    | 397/679 [00:58<00:41,  6.80it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  58%|█████▊    | 397/679 [00:58<00:41,  6.80it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  59%|█████▊    | 398/679 [00:58<00:41,  6.80it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  59%|█████▊    | 398/679 [00:58<00:41,  6.80it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  59%|█████▉    | 399/679 [00:58<00:41,  6.80it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  59%|█████▉    | 399/679 [00:58<00:41,  6.80it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  59%|█████▉    | 400/679 [00:58<00:41,  6.80it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  59%|█████▉    | 400/679 [00:58<00:41,  6.80it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  59%|█████▉    | 401/679 [00:58<00:40,  6.80it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  59%|█████▉    | 401/679 [00:58<00:40,  6.80it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  59%|█████▉    | 402/679 [00:59<00:40,  6.81it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  59%|█████▉    | 402/679 [00:59<00:40,  6.81it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  59%|█████▉    | 403/679 [00:59<00:40,  6.81it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  59%|█████▉    | 403/679 [00:59<00:40,  6.81it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  59%|█████▉    | 404/679 [00:59<00:40,  6.81it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  59%|█████▉    | 404/679 [00:59<00:40,  6.81it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  60%|█████▉    | 405/679 [00:59<00:40,  6.81it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  60%|█████▉    | 405/679 [00:59<00:40,  6.81it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  60%|█████▉    | 406/679 [00:59<00:40,  6.81it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  60%|█████▉    | 406/679 [00:59<00:40,  6.81it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  60%|█████▉    | 407/679 [00:59<00:39,  6.81it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  60%|█████▉    | 407/679 [00:59<00:39,  6.81it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  60%|██████    | 408/679 [00:59<00:39,  6.81it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  60%|██████    | 408/679 [00:59<00:39,  6.81it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  60%|██████    | 409/679 [01:00<00:39,  6.81it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  60%|██████    | 409/679 [01:00<00:39,  6.81it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  60%|██████    | 410/679 [01:00<00:39,  6.82it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  60%|██████    | 410/679 [01:00<00:39,  6.82it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  61%|██████    | 411/679 [01:00<00:39,  6.82it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  61%|██████    | 411/679 [01:00<00:39,  6.82it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  61%|██████    | 412/679 [01:00<00:39,  6.82it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  61%|██████    | 412/679 [01:00<00:39,  6.82it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  61%|██████    | 413/679 [01:00<00:39,  6.82it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  61%|██████    | 413/679 [01:00<00:39,  6.82it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  61%|██████    | 414/679 [01:00<00:38,  6.82it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  61%|██████    | 414/679 [01:00<00:38,  6.82it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  61%|██████    | 415/679 [01:00<00:38,  6.82it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  61%|██████    | 415/679 [01:00<00:38,  6.82it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  61%|██████▏   | 416/679 [01:00<00:38,  6.82it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  61%|██████▏   | 416/679 [01:00<00:38,  6.82it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  61%|██████▏   | 417/679 [01:01<00:38,  6.82it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  61%|██████▏   | 417/679 [01:01<00:38,  6.82it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  62%|██████▏   | 418/679 [01:01<00:38,  6.83it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  62%|██████▏   | 418/679 [01:01<00:38,  6.83it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  62%|██████▏   | 419/679 [01:01<00:38,  6.83it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  62%|██████▏   | 419/679 [01:01<00:38,  6.83it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  62%|██████▏   | 420/679 [01:01<00:37,  6.83it/s, loss=2.64, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  62%|██████▏   | 420/679 [01:01<00:37,  6.83it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  62%|██████▏   | 421/679 [01:01<00:37,  6.83it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  62%|██████▏   | 421/679 [01:01<00:37,  6.83it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  62%|██████▏   | 422/679 [01:01<00:37,  6.83it/s, loss=2.63, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  62%|██████▏   | 422/679 [01:01<00:37,  6.83it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  62%|██████▏   | 423/679 [01:01<00:37,  6.83it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  62%|██████▏   | 423/679 [01:01<00:37,  6.83it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  62%|██████▏   | 424/679 [01:02<00:37,  6.83it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  62%|██████▏   | 424/679 [01:02<00:37,  6.83it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  63%|██████▎   | 425/679 [01:02<00:37,  6.84it/s, loss=2.62, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  63%|██████▎   | 425/679 [01:02<00:37,  6.84it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  63%|██████▎   | 426/679 [01:02<00:37,  6.84it/s, loss=2.61, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  63%|██████▎   | 426/679 [01:02<00:37,  6.84it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000] 
Epoch 0:  63%|██████▎   | 427/679 [01:02<00:36,  6.84it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  63%|██████▎   | 427/679 [01:02<00:36,  6.84it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  63%|██████▎   | 428/679 [01:02<00:36,  6.84it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  63%|██████▎   | 428/679 [01:02<00:36,  6.84it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  63%|██████▎   | 429/679 [01:02<00:36,  6.84it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  63%|██████▎   | 429/679 [01:02<00:36,  6.84it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  63%|██████▎   | 430/679 [01:02<00:36,  6.84it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  63%|██████▎   | 430/679 [01:02<00:36,  6.84it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  63%|██████▎   | 431/679 [01:02<00:36,  6.84it/s, loss=2.6, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  63%|██████▎   | 431/679 [01:02<00:36,  6.84it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  64%|██████▎   | 432/679 [01:03<00:36,  6.84it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  64%|██████▎   | 432/679 [01:03<00:36,  6.84it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  64%|██████▍   | 433/679 [01:03<00:35,  6.84it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  64%|██████▍   | 433/679 [01:03<00:35,  6.84it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  64%|██████▍   | 434/679 [01:03<00:35,  6.84it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  64%|██████▍   | 434/679 [01:03<00:35,  6.84it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  64%|██████▍   | 435/679 [01:03<00:35,  6.84it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  64%|██████▍   | 435/679 [01:03<00:35,  6.84it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  64%|██████▍   | 436/679 [01:03<00:35,  6.85it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  64%|██████▍   | 436/679 [01:03<00:35,  6.85it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  64%|██████▍   | 437/679 [01:03<00:35,  6.85it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  64%|██████▍   | 437/679 [01:03<00:35,  6.85it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  65%|██████▍   | 438/679 [01:03<00:35,  6.85it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  65%|██████▍   | 438/679 [01:03<00:35,  6.85it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  65%|██████▍   | 439/679 [01:04<00:35,  6.85it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  65%|██████▍   | 439/679 [01:04<00:35,  6.85it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  65%|██████▍   | 440/679 [01:04<00:34,  6.85it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  65%|██████▍   | 440/679 [01:04<00:34,  6.85it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  65%|██████▍   | 441/679 [01:04<00:34,  6.85it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  65%|██████▍   | 441/679 [01:04<00:34,  6.85it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  65%|██████▌   | 442/679 [01:04<00:34,  6.86it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  65%|██████▌   | 442/679 [01:04<00:34,  6.85it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  65%|██████▌   | 443/679 [01:04<00:34,  6.86it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  65%|██████▌   | 443/679 [01:04<00:34,  6.86it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  65%|██████▌   | 444/679 [01:04<00:34,  6.86it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  65%|██████▌   | 444/679 [01:04<00:34,  6.86it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  66%|██████▌   | 445/679 [01:04<00:34,  6.86it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  66%|██████▌   | 445/679 [01:04<00:34,  6.86it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  66%|██████▌   | 446/679 [01:05<00:33,  6.86it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  66%|██████▌   | 446/679 [01:05<00:33,  6.86it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  66%|██████▌   | 447/679 [01:05<00:33,  6.86it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  66%|██████▌   | 447/679 [01:05<00:33,  6.86it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  66%|██████▌   | 448/679 [01:05<00:33,  6.86it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  66%|██████▌   | 448/679 [01:05<00:33,  6.86it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  66%|██████▌   | 449/679 [01:05<00:33,  6.86it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  66%|██████▌   | 449/679 [01:05<00:33,  6.86it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  66%|██████▋   | 450/679 [01:05<00:33,  6.86it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  66%|██████▋   | 450/679 [01:05<00:33,  6.86it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  66%|██████▋   | 451/679 [01:05<00:33,  6.86it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  66%|██████▋   | 451/679 [01:05<00:33,  6.86it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  67%|██████▋   | 452/679 [01:05<00:33,  6.86it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  67%|██████▋   | 452/679 [01:05<00:33,  6.86it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  67%|██████▋   | 453/679 [01:05<00:32,  6.86it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  67%|██████▋   | 453/679 [01:05<00:32,  6.86it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  67%|██████▋   | 454/679 [01:06<00:32,  6.87it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  67%|██████▋   | 454/679 [01:06<00:32,  6.87it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  67%|██████▋   | 455/679 [01:06<00:32,  6.87it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  67%|██████▋   | 455/679 [01:06<00:32,  6.87it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  67%|██████▋   | 456/679 [01:06<00:32,  6.87it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  67%|██████▋   | 456/679 [01:06<00:32,  6.87it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  67%|██████▋   | 457/679 [01:06<00:32,  6.87it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  67%|██████▋   | 457/679 [01:06<00:32,  6.87it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  67%|██████▋   | 458/679 [01:06<00:32,  6.87it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  67%|██████▋   | 458/679 [01:06<00:32,  6.87it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  68%|██████▊   | 459/679 [01:06<00:32,  6.87it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  68%|██████▊   | 459/679 [01:06<00:32,  6.87it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  68%|██████▊   | 460/679 [01:06<00:31,  6.87it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  68%|██████▊   | 460/679 [01:06<00:31,  6.87it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  68%|██████▊   | 461/679 [01:07<00:31,  6.87it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  68%|██████▊   | 461/679 [01:07<00:31,  6.87it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  68%|██████▊   | 462/679 [01:07<00:31,  6.87it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  68%|██████▊   | 462/679 [01:07<00:31,  6.87it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  68%|██████▊   | 463/679 [01:07<00:31,  6.87it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  68%|██████▊   | 463/679 [01:07<00:31,  6.87it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  68%|██████▊   | 464/679 [01:07<00:31,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  68%|██████▊   | 464/679 [01:07<00:31,  6.88it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  68%|██████▊   | 465/679 [01:07<00:31,  6.88it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  68%|██████▊   | 465/679 [01:07<00:31,  6.88it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  69%|██████▊   | 466/679 [01:07<00:30,  6.88it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  69%|██████▊   | 466/679 [01:07<00:30,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  69%|██████▉   | 467/679 [01:07<00:30,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  69%|██████▉   | 467/679 [01:07<00:30,  6.88it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  69%|██████▉   | 468/679 [01:08<00:30,  6.88it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  69%|██████▉   | 468/679 [01:08<00:30,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  69%|██████▉   | 469/679 [01:08<00:30,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  69%|██████▉   | 469/679 [01:08<00:30,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  69%|██████▉   | 470/679 [01:08<00:30,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  69%|██████▉   | 470/679 [01:08<00:30,  6.88it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  69%|██████▉   | 471/679 [01:08<00:30,  6.88it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  69%|██████▉   | 471/679 [01:08<00:30,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  70%|██████▉   | 472/679 [01:08<00:30,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  70%|██████▉   | 472/679 [01:08<00:30,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  70%|██████▉   | 473/679 [01:08<00:29,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  70%|██████▉   | 473/679 [01:08<00:29,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  70%|██████▉   | 474/679 [01:08<00:29,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  70%|██████▉   | 474/679 [01:08<00:29,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  70%|██████▉   | 475/679 [01:09<00:29,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  70%|██████▉   | 475/679 [01:09<00:29,  6.88it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  70%|███████   | 476/679 [01:09<00:29,  6.88it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  70%|███████   | 476/679 [01:09<00:29,  6.88it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  70%|███████   | 477/679 [01:09<00:29,  6.89it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  70%|███████   | 477/679 [01:09<00:29,  6.88it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  70%|███████   | 478/679 [01:09<00:29,  6.89it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  70%|███████   | 478/679 [01:09<00:29,  6.89it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  71%|███████   | 479/679 [01:09<00:29,  6.89it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  71%|███████   | 479/679 [01:09<00:29,  6.89it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  71%|███████   | 480/679 [01:09<00:28,  6.89it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  71%|███████   | 480/679 [01:09<00:28,  6.89it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  71%|███████   | 481/679 [01:09<00:28,  6.89it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  71%|███████   | 481/679 [01:09<00:28,  6.89it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  71%|███████   | 482/679 [01:09<00:28,  6.89it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  71%|███████   | 482/679 [01:09<00:28,  6.89it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  71%|███████   | 483/679 [01:10<00:28,  6.89it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  71%|███████   | 483/679 [01:10<00:28,  6.89it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  71%|███████▏  | 484/679 [01:10<00:28,  6.89it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  71%|███████▏  | 484/679 [01:10<00:28,  6.89it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  71%|███████▏  | 485/679 [01:10<00:28,  6.89it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  71%|███████▏  | 485/679 [01:10<00:28,  6.89it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  72%|███████▏  | 486/679 [01:10<00:27,  6.90it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  72%|███████▏  | 486/679 [01:10<00:27,  6.90it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  72%|███████▏  | 487/679 [01:10<00:27,  6.90it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  72%|███████▏  | 487/679 [01:10<00:27,  6.90it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  72%|███████▏  | 488/679 [01:10<00:27,  6.90it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  72%|███████▏  | 488/679 [01:10<00:27,  6.90it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  72%|███████▏  | 489/679 [01:10<00:27,  6.90it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  72%|███████▏  | 489/679 [01:10<00:27,  6.90it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  72%|███████▏  | 490/679 [01:11<00:27,  6.90it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  72%|███████▏  | 490/679 [01:11<00:27,  6.90it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  72%|███████▏  | 491/679 [01:11<00:27,  6.90it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  72%|███████▏  | 491/679 [01:11<00:27,  6.90it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  72%|███████▏  | 492/679 [01:11<00:27,  6.90it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  72%|███████▏  | 492/679 [01:11<00:27,  6.90it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  73%|███████▎  | 493/679 [01:11<00:26,  6.90it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  73%|███████▎  | 493/679 [01:11<00:26,  6.90it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  73%|███████▎  | 494/679 [01:11<00:26,  6.90it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  73%|███████▎  | 494/679 [01:11<00:26,  6.90it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  73%|███████▎  | 495/679 [01:11<00:26,  6.90it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  73%|███████▎  | 495/679 [01:11<00:26,  6.90it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  73%|███████▎  | 496/679 [01:11<00:26,  6.90it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  73%|███████▎  | 496/679 [01:11<00:26,  6.90it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  73%|███████▎  | 497/679 [01:11<00:26,  6.90it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  73%|███████▎  | 497/679 [01:11<00:26,  6.90it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  73%|███████▎  | 498/679 [01:12<00:26,  6.91it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  73%|███████▎  | 498/679 [01:12<00:26,  6.91it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  73%|███████▎  | 499/679 [01:12<00:26,  6.91it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  73%|███████▎  | 499/679 [01:12<00:26,  6.91it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  74%|███████▎  | 500/679 [01:12<00:25,  6.91it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  74%|███████▎  | 500/679 [01:12<00:25,  6.91it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  74%|███████▍  | 501/679 [01:12<00:25,  6.91it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  74%|███████▍  | 501/679 [01:12<00:25,  6.91it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  74%|███████▍  | 502/679 [01:12<00:25,  6.91it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  74%|███████▍  | 502/679 [01:12<00:25,  6.91it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  74%|███████▍  | 503/679 [01:12<00:25,  6.91it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  74%|███████▍  | 503/679 [01:12<00:25,  6.91it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  74%|███████▍  | 504/679 [01:12<00:25,  6.91it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  74%|███████▍  | 504/679 [01:12<00:25,  6.91it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  74%|███████▍  | 505/679 [01:13<00:25,  6.91it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  74%|███████▍  | 505/679 [01:13<00:25,  6.91it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  75%|███████▍  | 506/679 [01:13<00:25,  6.91it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  75%|███████▍  | 506/679 [01:13<00:25,  6.91it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  75%|███████▍  | 507/679 [01:13<00:24,  6.91it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  75%|███████▍  | 507/679 [01:13<00:24,  6.91it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  75%|███████▍  | 508/679 [01:13<00:24,  6.92it/s, loss=2.59, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  75%|███████▍  | 508/679 [01:13<00:24,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  75%|███████▍  | 509/679 [01:13<00:24,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  75%|███████▍  | 509/679 [01:13<00:24,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  75%|███████▌  | 510/679 [01:13<00:24,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  75%|███████▌  | 510/679 [01:13<00:24,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  75%|███████▌  | 511/679 [01:13<00:24,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  75%|███████▌  | 511/679 [01:13<00:24,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  75%|███████▌  | 512/679 [01:13<00:24,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  75%|███████▌  | 512/679 [01:13<00:24,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  76%|███████▌  | 513/679 [01:14<00:23,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  76%|███████▌  | 513/679 [01:14<00:23,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  76%|███████▌  | 514/679 [01:14<00:23,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  76%|███████▌  | 514/679 [01:14<00:23,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  76%|███████▌  | 515/679 [01:14<00:23,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  76%|███████▌  | 515/679 [01:14<00:23,  6.92it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  76%|███████▌  | 516/679 [01:14<00:23,  6.92it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  76%|███████▌  | 516/679 [01:14<00:23,  6.92it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  76%|███████▌  | 517/679 [01:14<00:23,  6.92it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  76%|███████▌  | 517/679 [01:14<00:23,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  76%|███████▋  | 518/679 [01:14<00:23,  6.92it/s, loss=2.58, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  76%|███████▋  | 518/679 [01:14<00:23,  6.92it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  76%|███████▋  | 519/679 [01:14<00:23,  6.92it/s, loss=2.57, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  76%|███████▋  | 519/679 [01:14<00:23,  6.92it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  77%|███████▋  | 520/679 [01:15<00:22,  6.93it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  77%|███████▋  | 520/679 [01:15<00:22,  6.93it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  77%|███████▋  | 521/679 [01:15<00:22,  6.93it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  77%|███████▋  | 521/679 [01:15<00:22,  6.93it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  77%|███████▋  | 522/679 [01:15<00:22,  6.93it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  77%|███████▋  | 522/679 [01:15<00:22,  6.93it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  77%|███████▋  | 523/679 [01:15<00:22,  6.93it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  77%|███████▋  | 523/679 [01:15<00:22,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  77%|███████▋  | 524/679 [01:15<00:22,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  77%|███████▋  | 524/679 [01:15<00:22,  6.93it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  77%|███████▋  | 525/679 [01:15<00:22,  6.93it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  77%|███████▋  | 525/679 [01:15<00:22,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  77%|███████▋  | 526/679 [01:15<00:22,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  77%|███████▋  | 526/679 [01:15<00:22,  6.93it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  78%|███████▊  | 527/679 [01:16<00:21,  6.93it/s, loss=2.56, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  78%|███████▊  | 527/679 [01:16<00:21,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  78%|███████▊  | 528/679 [01:16<00:21,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  78%|███████▊  | 528/679 [01:16<00:21,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  78%|███████▊  | 529/679 [01:16<00:21,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  78%|███████▊  | 529/679 [01:16<00:21,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  78%|███████▊  | 530/679 [01:16<00:21,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  78%|███████▊  | 530/679 [01:16<00:21,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  78%|███████▊  | 531/679 [01:16<00:21,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  78%|███████▊  | 531/679 [01:16<00:21,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  78%|███████▊  | 532/679 [01:16<00:21,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  78%|███████▊  | 532/679 [01:16<00:21,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  78%|███████▊  | 533/679 [01:16<00:21,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  78%|███████▊  | 533/679 [01:16<00:21,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  79%|███████▊  | 534/679 [01:16<00:20,  6.94it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  79%|███████▊  | 534/679 [01:16<00:20,  6.94it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  79%|███████▉  | 535/679 [01:17<00:20,  6.94it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  79%|███████▉  | 535/679 [01:17<00:20,  6.94it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  79%|███████▉  | 536/679 [01:17<00:20,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  79%|███████▉  | 536/679 [01:17<00:20,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  79%|███████▉  | 537/679 [01:17<00:20,  6.93it/s, loss=2.55, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  79%|███████▉  | 537/679 [01:17<00:20,  6.93it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  79%|███████▉  | 538/679 [01:17<00:20,  6.93it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  79%|███████▉  | 538/679 [01:17<00:20,  6.93it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  79%|███████▉  | 539/679 [01:17<00:20,  6.93it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  79%|███████▉  | 539/679 [01:17<00:20,  6.93it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  80%|███████▉  | 540/679 [01:17<00:20,  6.93it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  80%|███████▉  | 540/679 [01:17<00:20,  6.93it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  80%|███████▉  | 541/679 [01:18<00:19,  6.93it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  80%|███████▉  | 541/679 [01:18<00:19,  6.93it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  80%|███████▉  | 542/679 [01:18<00:19,  6.93it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  80%|███████▉  | 542/679 [01:18<00:19,  6.93it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  80%|███████▉  | 543/679 [01:18<00:19,  6.93it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  80%|███████▉  | 543/679 [01:18<00:19,  6.93it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  80%|████████  | 544/679 [01:18<00:19,  6.94it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  80%|████████  | 544/679 [01:18<00:19,  6.94it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  80%|████████  | 545/679 [01:18<00:19,  6.94it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  80%|████████  | 545/679 [01:18<00:19,  6.94it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  80%|████████  | 546/679 [01:18<00:19,  6.94it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  80%|████████  | 546/679 [01:18<00:19,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  81%|████████  | 547/679 [01:18<00:19,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  81%|████████  | 547/679 [01:18<00:19,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  81%|████████  | 548/679 [01:18<00:18,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  81%|████████  | 548/679 [01:18<00:18,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  81%|████████  | 549/679 [01:19<00:18,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  81%|████████  | 549/679 [01:19<00:18,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  81%|████████  | 550/679 [01:19<00:18,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  81%|████████  | 550/679 [01:19<00:18,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  81%|████████  | 551/679 [01:19<00:18,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  81%|████████  | 551/679 [01:19<00:18,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  81%|████████▏ | 552/679 [01:19<00:18,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  81%|████████▏ | 552/679 [01:19<00:18,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  81%|████████▏ | 553/679 [01:19<00:18,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  81%|████████▏ | 553/679 [01:19<00:18,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  82%|████████▏ | 554/679 [01:19<00:18,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  82%|████████▏ | 554/679 [01:19<00:18,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  82%|████████▏ | 555/679 [01:19<00:17,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  82%|████████▏ | 555/679 [01:19<00:17,  6.94it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  82%|████████▏ | 556/679 [01:20<00:17,  6.95it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  82%|████████▏ | 556/679 [01:20<00:17,  6.95it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  82%|████████▏ | 557/679 [01:20<00:17,  6.95it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  82%|████████▏ | 557/679 [01:20<00:17,  6.95it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  82%|████████▏ | 558/679 [01:20<00:17,  6.95it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  82%|████████▏ | 558/679 [01:20<00:17,  6.95it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  82%|████████▏ | 559/679 [01:20<00:17,  6.95it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  82%|████████▏ | 559/679 [01:20<00:17,  6.95it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  82%|████████▏ | 560/679 [01:20<00:17,  6.95it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  82%|████████▏ | 560/679 [01:20<00:17,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  83%|████████▎ | 561/679 [01:20<00:16,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  83%|████████▎ | 561/679 [01:20<00:16,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  83%|████████▎ | 562/679 [01:20<00:16,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  83%|████████▎ | 562/679 [01:20<00:16,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  83%|████████▎ | 563/679 [01:20<00:16,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  83%|████████▎ | 563/679 [01:20<00:16,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  83%|████████▎ | 564/679 [01:21<00:16,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  83%|████████▎ | 564/679 [01:21<00:16,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  83%|████████▎ | 565/679 [01:21<00:16,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  83%|████████▎ | 565/679 [01:21<00:16,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  83%|████████▎ | 566/679 [01:21<00:16,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  83%|████████▎ | 566/679 [01:21<00:16,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  84%|████████▎ | 567/679 [01:21<00:16,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  84%|████████▎ | 567/679 [01:21<00:16,  6.95it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  84%|████████▎ | 568/679 [01:21<00:15,  6.96it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  84%|████████▎ | 568/679 [01:21<00:15,  6.96it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  84%|████████▍ | 569/679 [01:21<00:15,  6.96it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  84%|████████▍ | 569/679 [01:21<00:15,  6.96it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  84%|████████▍ | 570/679 [01:21<00:15,  6.96it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  84%|████████▍ | 570/679 [01:21<00:15,  6.96it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  84%|████████▍ | 571/679 [01:22<00:15,  6.96it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  84%|████████▍ | 571/679 [01:22<00:15,  6.96it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  84%|████████▍ | 572/679 [01:22<00:15,  6.96it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  84%|████████▍ | 572/679 [01:22<00:15,  6.96it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  84%|████████▍ | 573/679 [01:22<00:15,  6.96it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  84%|████████▍ | 573/679 [01:22<00:15,  6.96it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  85%|████████▍ | 574/679 [01:22<00:15,  6.96it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  85%|████████▍ | 574/679 [01:22<00:15,  6.96it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  85%|████████▍ | 575/679 [01:22<00:14,  6.96it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  85%|████████▍ | 575/679 [01:22<00:14,  6.96it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  85%|████████▍ | 576/679 [01:22<00:14,  6.96it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  85%|████████▍ | 576/679 [01:22<00:14,  6.96it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  85%|████████▍ | 577/679 [01:22<00:14,  6.96it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  85%|████████▍ | 577/679 [01:22<00:14,  6.96it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  85%|████████▌ | 578/679 [01:23<00:14,  6.96it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  85%|████████▌ | 578/679 [01:23<00:14,  6.96it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  85%|████████▌ | 579/679 [01:23<00:14,  6.96it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  85%|████████▌ | 579/679 [01:23<00:14,  6.96it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  85%|████████▌ | 580/679 [01:23<00:14,  6.96it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  85%|████████▌ | 580/679 [01:23<00:14,  6.96it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  86%|████████▌ | 581/679 [01:23<00:14,  6.96it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  86%|████████▌ | 581/679 [01:23<00:14,  6.96it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  86%|████████▌ | 582/679 [01:23<00:13,  6.97it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  86%|████████▌ | 582/679 [01:23<00:13,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  86%|████████▌ | 583/679 [01:23<00:13,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  86%|████████▌ | 583/679 [01:23<00:13,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  86%|████████▌ | 584/679 [01:23<00:13,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  86%|████████▌ | 584/679 [01:23<00:13,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  86%|████████▌ | 585/679 [01:23<00:13,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  86%|████████▌ | 585/679 [01:23<00:13,  6.97it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  86%|████████▋ | 586/679 [01:24<00:13,  6.97it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  86%|████████▋ | 586/679 [01:24<00:13,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  86%|████████▋ | 587/679 [01:24<00:13,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  86%|████████▋ | 587/679 [01:24<00:13,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  87%|████████▋ | 588/679 [01:24<00:13,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  87%|████████▋ | 588/679 [01:24<00:13,  6.97it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  87%|████████▋ | 589/679 [01:24<00:12,  6.97it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  87%|████████▋ | 589/679 [01:24<00:12,  6.97it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  87%|████████▋ | 590/679 [01:24<00:12,  6.97it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  87%|████████▋ | 590/679 [01:24<00:12,  6.97it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  87%|████████▋ | 591/679 [01:24<00:12,  6.97it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  87%|████████▋ | 591/679 [01:24<00:12,  6.97it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  87%|████████▋ | 592/679 [01:24<00:12,  6.97it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  87%|████████▋ | 592/679 [01:24<00:12,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  87%|████████▋ | 593/679 [01:25<00:12,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  87%|████████▋ | 593/679 [01:25<00:12,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  87%|████████▋ | 594/679 [01:25<00:12,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  87%|████████▋ | 594/679 [01:25<00:12,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  88%|████████▊ | 595/679 [01:25<00:12,  6.97it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  88%|████████▊ | 595/679 [01:25<00:12,  6.97it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  88%|████████▊ | 596/679 [01:25<00:11,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  88%|████████▊ | 596/679 [01:25<00:11,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  88%|████████▊ | 597/679 [01:25<00:11,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  88%|████████▊ | 597/679 [01:25<00:11,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  88%|████████▊ | 598/679 [01:25<00:11,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  88%|████████▊ | 598/679 [01:25<00:11,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  88%|████████▊ | 599/679 [01:25<00:11,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  88%|████████▊ | 599/679 [01:25<00:11,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  88%|████████▊ | 600/679 [01:25<00:11,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  88%|████████▊ | 600/679 [01:25<00:11,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  89%|████████▊ | 601/679 [01:26<00:11,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  89%|████████▊ | 601/679 [01:26<00:11,  6.98it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  89%|████████▊ | 602/679 [01:26<00:11,  6.98it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  89%|████████▊ | 602/679 [01:26<00:11,  6.98it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  89%|████████▉ | 603/679 [01:26<00:10,  6.98it/s, loss=2.51, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  89%|████████▉ | 603/679 [01:26<00:10,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  89%|████████▉ | 604/679 [01:26<00:10,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  89%|████████▉ | 604/679 [01:26<00:10,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  89%|████████▉ | 605/679 [01:26<00:10,  6.98it/s, loss=2.52, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  89%|████████▉ | 605/679 [01:26<00:10,  6.98it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  89%|████████▉ | 606/679 [01:26<00:10,  6.98it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  89%|████████▉ | 606/679 [01:26<00:10,  6.98it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  89%|████████▉ | 607/679 [01:26<00:10,  6.98it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  89%|████████▉ | 607/679 [01:26<00:10,  6.98it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  90%|████████▉ | 608/679 [01:27<00:10,  6.98it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  90%|████████▉ | 608/679 [01:27<00:10,  6.98it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  90%|████████▉ | 609/679 [01:27<00:10,  6.98it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  90%|████████▉ | 609/679 [01:27<00:10,  6.98it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  90%|████████▉ | 610/679 [01:27<00:09,  6.98it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  90%|████████▉ | 610/679 [01:27<00:09,  6.98it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  90%|████████▉ | 611/679 [01:27<00:09,  6.98it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  90%|████████▉ | 611/679 [01:27<00:09,  6.98it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  90%|█████████ | 612/679 [01:27<00:09,  6.99it/s, loss=2.54, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  90%|█████████ | 612/679 [01:27<00:09,  6.99it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  90%|█████████ | 613/679 [01:27<00:09,  6.99it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  90%|█████████ | 613/679 [01:27<00:09,  6.99it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  90%|█████████ | 614/679 [01:27<00:09,  6.99it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  90%|█████████ | 614/679 [01:27<00:09,  6.99it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  91%|█████████ | 615/679 [01:28<00:09,  6.95it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]
Epoch 0:  91%|█████████ | 615/679 [01:28<00:09,  6.95it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating: 0it [00:00, ?it/s]

Validating:   0%|          | 0/64 [00:00<?, ?it/s]

Validating:   2%|▏         | 1/64 [00:05<05:54,  5.62s/it]
Epoch 0:  91%|█████████ | 617/679 [01:34<00:09,  6.56it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:   3%|▎         | 2/64 [00:06<02:56,  2.84s/it]

Validating:   5%|▍         | 3/64 [00:06<01:45,  1.73s/it]
Epoch 0:  91%|█████████ | 619/679 [01:35<00:09,  6.49it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:   6%|▋         | 4/64 [00:07<01:05,  1.09s/it]

Validating:   8%|▊         | 5/64 [00:07<00:43,  1.36it/s]
Epoch 0:  91%|█████████▏| 621/679 [01:35<00:08,  6.49it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:   9%|▉         | 6/64 [00:07<00:30,  1.91it/s]

Validating:  11%|█         | 7/64 [00:07<00:22,  2.57it/s]
Epoch 0:  92%|█████████▏| 623/679 [01:35<00:08,  6.50it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  12%|█▎        | 8/64 [00:07<00:16,  3.33it/s]

Validating:  14%|█▍        | 9/64 [00:07<00:13,  4.19it/s]
Epoch 0:  92%|█████████▏| 625/679 [01:36<00:08,  6.51it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  16%|█▌        | 10/64 [00:07<00:10,  5.08it/s]

Validating:  17%|█▋        | 11/64 [00:07<00:08,  5.94it/s]
Epoch 0:  92%|█████████▏| 627/679 [01:36<00:07,  6.51it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  19%|█▉        | 12/64 [00:07<00:07,  6.59it/s]

Validating:  20%|██        | 13/64 [00:08<00:07,  7.20it/s]
Epoch 0:  93%|█████████▎| 629/679 [01:36<00:07,  6.52it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  22%|██▏       | 14/64 [00:08<00:06,  7.84it/s]

Validating:  23%|██▎       | 15/64 [00:08<00:05,  8.22it/s]
Epoch 0:  93%|█████████▎| 631/679 [01:36<00:07,  6.53it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  27%|██▋       | 17/64 [00:08<00:05,  8.94it/s]
Epoch 0:  93%|█████████▎| 633/679 [01:36<00:07,  6.53it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  28%|██▊       | 18/64 [00:08<00:05,  8.84it/s]

Validating:  30%|██▉       | 19/64 [00:08<00:05,  8.38it/s]
Epoch 0:  94%|█████████▎| 635/679 [01:37<00:06,  6.54it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  31%|███▏      | 20/64 [00:08<00:05,  8.53it/s]

Validating:  33%|███▎      | 21/64 [00:08<00:04,  8.65it/s]
Epoch 0:  94%|█████████▍| 637/679 [01:37<00:06,  6.54it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  34%|███▍      | 22/64 [00:09<00:04,  8.81it/s]
Epoch 0:  94%|█████████▍| 639/679 [01:37<00:06,  6.55it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  38%|███▊      | 24/64 [00:09<00:04,  9.68it/s]
Epoch 0:  94%|█████████▍| 641/679 [01:37<00:05,  6.56it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  41%|████      | 26/64 [00:09<00:03, 10.28it/s]
Epoch 0:  95%|█████████▍| 643/679 [01:37<00:05,  6.57it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  44%|████▍     | 28/64 [00:09<00:03, 10.52it/s]
Epoch 0:  95%|█████████▍| 645/679 [01:38<00:05,  6.57it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  47%|████▋     | 30/64 [00:09<00:03, 10.35it/s]
Epoch 0:  95%|█████████▌| 647/679 [01:38<00:04,  6.58it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  50%|█████     | 32/64 [00:09<00:03,  9.80it/s]

Validating:  52%|█████▏    | 33/64 [00:10<00:03,  9.39it/s]
Epoch 0:  96%|█████████▌| 649/679 [01:38<00:04,  6.58it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  53%|█████▎    | 34/64 [00:10<00:03,  9.37it/s]
Epoch 0:  96%|█████████▌| 651/679 [01:38<00:04,  6.59it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  56%|█████▋    | 36/64 [00:10<00:02, 10.09it/s]
Epoch 0:  96%|█████████▌| 653/679 [01:38<00:03,  6.60it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  59%|█████▉    | 38/64 [00:10<00:02, 10.29it/s]
Epoch 0:  96%|█████████▋| 655/679 [01:39<00:03,  6.61it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  62%|██████▎   | 40/64 [00:10<00:02, 10.05it/s]
Epoch 0:  97%|█████████▋| 657/679 [01:39<00:03,  6.61it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  66%|██████▌   | 42/64 [00:10<00:02, 10.00it/s]
Epoch 0:  97%|█████████▋| 659/679 [01:39<00:03,  6.62it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  69%|██████▉   | 44/64 [00:11<00:01, 10.04it/s]
Epoch 0:  97%|█████████▋| 661/679 [01:39<00:02,  6.63it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  72%|███████▏  | 46/64 [00:11<00:01, 10.05it/s]
Epoch 0:  98%|█████████▊| 663/679 [01:39<00:02,  6.63it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  75%|███████▌  | 48/64 [00:11<00:01, 10.11it/s]
Epoch 0:  98%|█████████▊| 665/679 [01:40<00:02,  6.64it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  78%|███████▊  | 50/64 [00:11<00:01, 10.07it/s]
Epoch 0:  98%|█████████▊| 667/679 [01:40<00:01,  6.65it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  81%|████████▏ | 52/64 [00:11<00:01, 10.08it/s]
Epoch 0:  99%|█████████▊| 669/679 [01:40<00:01,  6.65it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  84%|████████▍ | 54/64 [00:12<00:00, 10.03it/s]
Epoch 0:  99%|█████████▉| 671/679 [01:40<00:01,  6.66it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  88%|████████▊ | 56/64 [00:12<00:00, 10.22it/s]
Epoch 0:  99%|█████████▉| 673/679 [01:40<00:00,  6.67it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  91%|█████████ | 58/64 [00:12<00:00, 10.41it/s]
Epoch 0:  99%|█████████▉| 675/679 [01:41<00:00,  6.68it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  94%|█████████▍| 60/64 [00:12<00:00, 10.69it/s]
Epoch 0: 100%|█████████▉| 677/679 [01:41<00:00,  6.68it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating:  97%|█████████▋| 62/64 [00:12<00:00, 10.28it/s]
Epoch 0: 100%|██████████| 679/679 [01:41<00:00,  6.69it/s, loss=2.53, v_num=1.94e+7, val_acc=0.000]

Validating: 100%|██████████| 64/64 [00:13<00:00, 10.65it/s]
Epoch 0: 100%|██████████| 679/679 [01:42<00:00,  6.65it/s, loss=2.53, v_num=1.94e+7, val_acc=0.340, train_acc=0.292]

                                                           
Epoch 0: 100%|██████████| 679/679 [01:42<00:00,  6.60it/s, loss=2.53, v_num=1.94e+7, val_acc=0.340, train_acc=0.292]