/Users/xxz/miniforge3/envs/crypto_pred_312/lib/python3.12/site-packages/torch/optim/lr_scheduler.py:62: UserWarning: The verbose parameter is deprecated. Please use get_last_lr() to access the learning rate.
  warnings.warn(

Training:   0%|          | 0/94 [00:00<?, ?it/s]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.7168]
Training:   1%|          | 1/94 [00:00<00:35,  2.59it/s, loss=0.7168]
Training:   1%|          | 1/94 [00:00<00:35,  2.59it/s, loss=0.6595]
Training:   1%|          | 1/94 [00:00<00:35,  2.59it/s, loss=0.6049]
Training:   1%|          | 1/94 [00:00<00:35,  2.59it/s, loss=0.5748]
Training:   1%|          | 1/94 [00:00<00:35,  2.59it/s, loss=0.5226]
Training:   1%|          | 1/94 [00:00<00:35,  2.59it/s, loss=0.4486]
Training:   1%|          | 1/94 [00:00<00:35,  2.59it/s, loss=0.4877]
Training:   1%|          | 1/94 [00:00<00:35,  2.59it/s, loss=0.5901]
Training:   1%|          | 1/94 [00:00<00:35,  2.59it/s, loss=0.5791]
Training:   1%|          | 1/94 [00:00<00:35,  2.59it/s, loss=0.5877]
Training:   1%|          | 1/94 [00:00<00:35,  2.59it/s, loss=0.6432]
Training:   1%|          | 1/94 [00:00<00:35,  2.59it/s, loss=0.6621]
Training:  13%|█▎        | 12/94 [00:00<00:02, 31.56it/s, loss=0.6621]
Training:  13%|█▎        | 12/94 [00:00<00:02, 31.56it/s, loss=0.4394]
Training:  13%|█▎        | 12/94 [00:00<00:02, 31.56it/s, loss=0.6063]
Training:  13%|█▎        | 12/94 [00:00<00:02, 31.56it/s, loss=0.3203]
Training:  13%|█▎        | 12/94 [00:00<00:02, 31.56it/s, loss=0.5585]
Training:  13%|█▎        | 12/94 [00:00<00:02, 31.56it/s, loss=0.4345]
Training:  13%|█▎        | 12/94 [00:00<00:02, 31.56it/s, loss=0.3812]
Training:  13%|█▎        | 12/94 [00:00<00:02, 31.56it/s, loss=0.5402]
Training:  13%|█▎        | 12/94 [00:00<00:02, 31.56it/s, loss=0.3985]
Training:  13%|█▎        | 12/94 [00:00<00:02, 31.56it/s, loss=0.5145]
Training:  13%|█▎        | 12/94 [00:00<00:02, 31.56it/s, loss=0.4234]
Training:  13%|█▎        | 12/94 [00:00<00:02, 31.56it/s, loss=0.4651]
Training:  13%|█▎        | 12/94 [00:00<00:02, 31.56it/s, loss=0.5034]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.5034]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.4430]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.5151]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.5558]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.5381]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.3953]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.5259]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.3471]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.5000]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.4584]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.4164]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.4170]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.4764]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.4198]
Training:  26%|██▌       | 24/94 [00:00<00:01, 55.53it/s, loss=0.5819]
Training:  40%|████      | 38/94 [00:00<00:00, 78.65it/s, loss=0.5819]
Training:  40%|████      | 38/94 [00:00<00:00, 78.65it/s, loss=0.3672]
Training:  40%|████      | 38/94 [00:00<00:00, 78.65it/s, loss=0.3455]
Training:  40%|████      | 38/94 [00:00<00:00, 78.65it/s, loss=0.3849]
Training:  40%|████      | 38/94 [00:00<00:00, 78.65it/s, loss=0.5532]
Training:  40%|████      | 38/94 [00:00<00:00, 78.65it/s, loss=0.6393]
Training:  40%|████      | 38/94 [00:00<00:00, 78.65it/s, loss=0.5317]
Training:  40%|████      | 38/94 [00:00<00:00, 78.65it/s, loss=0.5242]
Training:  40%|████      | 38/94 [00:00<00:00, 78.65it/s, loss=0.5852]
Training:  40%|████      | 38/94 [00:00<00:00, 78.65it/s, loss=0.6073]
Training:  40%|████      | 38/94 [00:00<00:00, 78.65it/s, loss=0.4834]
Training:  40%|████      | 38/94 [00:00<00:00, 78.65it/s, loss=0.4823]
Training:  40%|████      | 38/94 [00:00<00:00, 78.65it/s, loss=0.5609]
Training:  40%|████      | 38/94 [00:00<00:00, 78.65it/s, loss=0.4749]
Training:  54%|█████▍    | 51/94 [00:00<00:00, 93.18it/s, loss=0.4749]
Training:  54%|█████▍    | 51/94 [00:00<00:00, 93.18it/s, loss=0.4606]
Training:  54%|█████▍    | 51/94 [00:00<00:00, 93.18it/s, loss=0.5115]
Training:  54%|█████▍    | 51/94 [00:00<00:00, 93.18it/s, loss=0.4524]
Training:  54%|█████▍    | 51/94 [00:00<00:00, 93.18it/s, loss=0.4104]
Training:  54%|█████▍    | 51/94 [00:00<00:00, 93.18it/s, loss=0.4536]
Training:  54%|█████▍    | 51/94 [00:00<00:00, 93.18it/s, loss=0.5516]
Training:  54%|█████▍    | 51/94 [00:00<00:00, 93.18it/s, loss=0.4672]
Training:  54%|█████▍    | 51/94 [00:00<00:00, 93.18it/s, loss=0.4452]
Training:  54%|█████▍    | 51/94 [00:00<00:00, 93.18it/s, loss=0.4215]
Training:  54%|█████▍    | 51/94 [00:00<00:00, 93.18it/s, loss=0.3714]
Training:  54%|█████▍    | 51/94 [00:00<00:00, 93.18it/s, loss=0.5522]
Training:  54%|█████▍    | 51/94 [00:00<00:00, 93.18it/s, loss=0.4421]
Training:  54%|█████▍    | 51/94 [00:00<00:00, 93.18it/s, loss=0.4687]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.4687]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.3902]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.4271]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.4237]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.6400]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.4827]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.4870]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.4652]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.3968]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.3842]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.4910]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.4180]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.3919]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.4352]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.4297]
Training:  68%|██████▊   | 64/94 [00:00<00:00, 103.30it/s, loss=0.3860]
Training:  68%|██████▊   | 64/94 [00:01<00:00, 103.30it/s, loss=0.5400]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.5400]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.5715]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.3731]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.4430]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.4812]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.3721]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.5470]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.4511]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.4308]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.4820]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.5376]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.5761]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.4402]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.4282]
Training:  85%|████████▌ | 80/94 [00:01<00:00, 118.25it/s, loss=0.3301]
Training: 100%|██████████| 94/94 [00:01<00:00, 104.29it/s, loss=0.3301]
Training: 100%|██████████| 94/94 [00:01<00:00, 80.51it/s, loss=0.3301] 

Training:   0%|          | 0/94 [00:00<?, ?it/s]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.6942]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5369]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5277]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4376]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4560]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3996]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5032]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4184]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4806]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3779]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3471]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4921]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3611]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.6159]
Training:  15%|█▍        | 14/94 [00:00<00:00, 129.22it/s, loss=0.6159]
Training:  15%|█▍        | 14/94 [00:00<00:00, 129.22it/s, loss=0.6085]
Training:  15%|█▍        | 14/94 [00:00<00:00, 129.22it/s, loss=0.3420]
Training:  15%|█▍        | 14/94 [00:00<00:00, 129.22it/s, loss=0.3622]
Training:  15%|█▍        | 14/94 [00:00<00:00, 129.22it/s, loss=0.4997]
Training:  15%|█▍        | 14/94 [00:00<00:00, 129.22it/s, loss=0.5844]
Training:  15%|█▍        | 14/94 [00:00<00:00, 129.22it/s, loss=0.4511]
Training:  15%|█▍        | 14/94 [00:00<00:00, 129.22it/s, loss=0.4572]
Training:  15%|█▍        | 14/94 [00:00<00:00, 129.22it/s, loss=0.4811]
Training:  15%|█▍        | 14/94 [00:00<00:00, 129.22it/s, loss=0.4829]
Training:  15%|█▍        | 14/94 [00:00<00:00, 129.22it/s, loss=0.5305]
Training:  15%|█▍        | 14/94 [00:00<00:00, 129.22it/s, loss=0.4361]
Training:  15%|█▍        | 14/94 [00:00<00:00, 129.22it/s, loss=0.4503]
Training:  15%|█▍        | 14/94 [00:00<00:00, 129.22it/s, loss=0.5293]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.5293]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.4453]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.4625]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.4712]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.5180]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.4569]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.3907]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.3456]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.5264]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.3645]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.3797]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.6586]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.4630]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.4284]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.2491]
Training:  29%|██▊       | 27/94 [00:00<00:00, 126.36it/s, loss=0.3980]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.3980]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.4759]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.3675]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.5160]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.6695]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.4799]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.4301]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.5187]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.4250]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.4671]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.5631]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.5655]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.3874]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.3981]
Training:  45%|████▍     | 42/94 [00:00<00:00, 133.52it/s, loss=0.4190]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.4190]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.3692]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.4735]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.3823]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.4875]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.5613]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.4230]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.5423]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.4238]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.4802]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.4146]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.5619]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.4942]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.4433]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.4525]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 130.30it/s, loss=0.3926]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.3926]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.4796]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.4925]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.5020]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.4433]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.6075]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.3935]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.5762]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.4340]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.5195]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.4835]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.3112]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.3654]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.2996]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 134.49it/s, loss=0.3732]
Training:  90%|█████████ | 85/94 [00:00<00:00, 131.13it/s, loss=0.3732]
Training:  90%|█████████ | 85/94 [00:00<00:00, 131.13it/s, loss=0.4738]
Training:  90%|█████████ | 85/94 [00:00<00:00, 131.13it/s, loss=0.4914]
Training:  90%|█████████ | 85/94 [00:00<00:00, 131.13it/s, loss=0.4078]
Training:  90%|█████████ | 85/94 [00:00<00:00, 131.13it/s, loss=0.4495]
Training:  90%|█████████ | 85/94 [00:00<00:00, 131.13it/s, loss=0.5037]
Training:  90%|█████████ | 85/94 [00:00<00:00, 131.13it/s, loss=0.4693]
Training:  90%|█████████ | 85/94 [00:00<00:00, 131.13it/s, loss=0.4613]
Training:  90%|█████████ | 85/94 [00:00<00:00, 131.13it/s, loss=0.4586]
Training:  90%|█████████ | 85/94 [00:00<00:00, 131.13it/s, loss=0.4965]
Training: 100%|██████████| 94/94 [00:00<00:00, 130.94it/s, loss=0.4965]

Training:   0%|          | 0/94 [00:00<?, ?it/s]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3337]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4799]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3817]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5206]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4601]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3676]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4066]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4762]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4665]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4810]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4863]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5174]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3743]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3406]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.3406]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.5045]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.4257]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.5210]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.5494]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.4728]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.5735]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.4473]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.4376]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.3706]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.4251]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.4269]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.5253]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.4464]
Training:  15%|█▍        | 14/94 [00:00<00:00, 136.35it/s, loss=0.4516]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.4516]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.4232]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.4467]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.4149]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.4777]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.4250]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.5895]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.4141]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.4527]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.3251]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.4414]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.4823]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.4666]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.5667]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.99it/s, loss=0.4662]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.4662]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.4303]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.5326]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.4908]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.4696]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.3981]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.4161]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.5148]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.5221]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.5126]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.4756]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.5191]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.4795]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.3316]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.57it/s, loss=0.3976]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.3976]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.4718]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.4483]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.4744]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.5210]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.4603]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.4925]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.2829]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.4539]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.3695]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.4541]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.5132]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.4117]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.3899]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.3353]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.86it/s, loss=0.4187]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.4187]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.4316]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.4736]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.4940]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.3154]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.5931]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.3877]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.4681]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.3438]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.4688]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.3857]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.4046]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.2901]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.4292]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.5075]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 141.21it/s, loss=0.4434]
Training:  91%|█████████▏| 86/94 [00:00<00:00, 138.97it/s, loss=0.4434]
Training:  91%|█████████▏| 86/94 [00:00<00:00, 138.97it/s, loss=0.4096]
Training:  91%|█████████▏| 86/94 [00:00<00:00, 138.97it/s, loss=0.4498]
Training:  91%|█████████▏| 86/94 [00:00<00:00, 138.97it/s, loss=0.4245]
Training:  91%|█████████▏| 86/94 [00:00<00:00, 138.97it/s, loss=0.3618]
Training:  91%|█████████▏| 86/94 [00:00<00:00, 138.97it/s, loss=0.4112]
Training:  91%|█████████▏| 86/94 [00:00<00:00, 138.97it/s, loss=0.4533]
Training:  91%|█████████▏| 86/94 [00:00<00:00, 138.97it/s, loss=0.3740]
Training:  91%|█████████▏| 86/94 [00:00<00:00, 138.97it/s, loss=0.4008]
Training: 100%|██████████| 94/94 [00:00<00:00, 140.13it/s, loss=0.4008]

Training:   0%|          | 0/94 [00:00<?, ?it/s]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3605]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5193]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3990]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3461]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4838]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4287]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3876]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3799]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4221]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3482]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4927]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4269]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3886]
Training:  14%|█▍        | 13/94 [00:00<00:00, 126.67it/s, loss=0.3886]
Training:  14%|█▍        | 13/94 [00:00<00:00, 126.67it/s, loss=0.2812]
Training:  14%|█▍        | 13/94 [00:00<00:00, 126.67it/s, loss=0.3355]
Training:  14%|█▍        | 13/94 [00:00<00:00, 126.67it/s, loss=0.2470]
Training:  14%|█▍        | 13/94 [00:00<00:00, 126.67it/s, loss=0.5115]
Training:  14%|█▍        | 13/94 [00:00<00:00, 126.67it/s, loss=0.3684]
Training:  14%|█▍        | 13/94 [00:00<00:00, 126.67it/s, loss=0.4404]
Training:  14%|█▍        | 13/94 [00:00<00:00, 126.67it/s, loss=0.4557]
Training:  14%|█▍        | 13/94 [00:00<00:00, 126.67it/s, loss=0.4453]
Training:  14%|█▍        | 13/94 [00:00<00:00, 126.67it/s, loss=0.3684]
Training:  14%|█▍        | 13/94 [00:00<00:00, 126.67it/s, loss=0.5637]
Training:  14%|█▍        | 13/94 [00:00<00:00, 126.67it/s, loss=0.4240]
Training:  14%|█▍        | 13/94 [00:00<00:00, 126.67it/s, loss=0.3840]
Training:  14%|█▍        | 13/94 [00:00<00:00, 126.67it/s, loss=0.5031]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.5031]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.4172]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.4458]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.4824]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.3923]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.3541]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.4766]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.4010]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.5577]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.4395]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.5614]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.5558]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.3834]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.5448]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.3557]
Training:  28%|██▊       | 26/94 [00:00<00:00, 124.15it/s, loss=0.4309]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.4309]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.3687]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.5299]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.3367]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.4530]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.4165]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.3860]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.5076]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.5862]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.4486]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.4731]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.4141]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.4113]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.3807]
Training:  44%|████▎     | 41/94 [00:00<00:00, 131.18it/s, loss=0.4452]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.4452]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.3777]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.3128]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.3733]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.4156]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.3829]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.4313]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.5900]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.4278]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.2757]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.5201]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.4245]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.3193]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.5003]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.3790]
Training:  59%|█████▊    | 55/94 [00:00<00:00, 130.92it/s, loss=0.4940]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.4940]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.4529]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.4478]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.3850]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.4427]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.4588]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.4181]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.4024]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.3996]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.4499]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.5409]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.4550]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.3565]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.4057]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.3603]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 135.85it/s, loss=0.4481]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.93it/s, loss=0.4481]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.93it/s, loss=0.4239]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.93it/s, loss=0.5095]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.93it/s, loss=0.4164]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.93it/s, loss=0.3377]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.93it/s, loss=0.4610]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.93it/s, loss=0.4436]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.93it/s, loss=0.5081]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.93it/s, loss=0.3975]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.93it/s, loss=0.7232]
Training: 100%|██████████| 94/94 [00:00<00:00, 132.34it/s, loss=0.7232]

Training:   0%|          | 0/94 [00:00<?, ?it/s]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3772]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4693]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4318]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3868]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4260]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5460]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3571]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3973]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.2778]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5060]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.2935]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4625]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4059]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.4059]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.3858]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.4448]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.4809]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.3521]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.3496]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.4314]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.4963]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.4712]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.3770]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.4553]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.5241]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.3510]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.3949]
Training:  14%|█▍        | 13/94 [00:00<00:00, 124.44it/s, loss=0.4070]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.4070]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.5450]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.3691]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.3372]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.4467]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.4468]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.4550]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.3227]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.3423]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.3681]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.3580]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.3762]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.3852]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.3740]
Training:  29%|██▊       | 27/94 [00:00<00:00, 130.73it/s, loss=0.5620]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.5620]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.3452]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.5199]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.4223]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.4796]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.4477]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.5068]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.4962]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.5368]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.4848]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.5721]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.3834]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.4895]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.4611]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.3328]
Training:  44%|████▎     | 41/94 [00:00<00:00, 130.64it/s, loss=0.3469]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.3469]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.4815]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.5007]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.3199]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.2666]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.4433]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.4551]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.3105]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.4375]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.4460]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.3897]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.4375]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.3428]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.3665]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.3166]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 135.88it/s, loss=0.4161]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.4161]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.3341]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.4679]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.4595]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.4512]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.4046]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.3123]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.3814]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.3834]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.3779]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.2713]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.5605]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.4515]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.4348]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 139.44it/s, loss=0.3485]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.18it/s, loss=0.3485]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.18it/s, loss=0.4722]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.18it/s, loss=0.5214]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.18it/s, loss=0.4679]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.18it/s, loss=0.4434]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.18it/s, loss=0.4180]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.18it/s, loss=0.3904]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.18it/s, loss=0.3827]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.18it/s, loss=0.4647]
Training:  90%|█████████ | 85/94 [00:00<00:00, 137.18it/s, loss=0.2823]
Training: 100%|██████████| 94/94 [00:00<00:00, 137.22it/s, loss=0.2823]

Training:   0%|          | 0/94 [00:00<?, ?it/s]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4478]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4281]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3804]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3735]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5388]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5079]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3884]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3322]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3281]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4016]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4666]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3670]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4226]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4144]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.4144]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.5328]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.4137]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.3698]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.5180]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.3525]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.3968]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.3552]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.3977]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.3709]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.3875]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.4152]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.4928]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.5295]
Training:  15%|█▍        | 14/94 [00:00<00:00, 139.47it/s, loss=0.4240]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.4240]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3497]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.2925]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3373]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3728]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.5144]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.4055]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3877]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3912]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3790]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.4059]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3293]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.5936]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.2976]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3832]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3564]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.3564]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.4106]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.3456]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.3263]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.3432]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.3312]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.5526]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.4075]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.4688]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.5852]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.3998]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.4003]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.3881]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.5250]
Training:  46%|████▌     | 43/94 [00:00<00:00, 139.30it/s, loss=0.4350]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.4350]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.4826]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.3650]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.4128]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.3888]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.3094]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.4500]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.2887]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.4241]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.4974]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.3749]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.4039]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.3789]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.3704]
Training:  61%|██████    | 57/94 [00:00<00:00, 138.94it/s, loss=0.6186]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.6186]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.5126]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.3308]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.3557]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.3504]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.4609]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.4161]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.5485]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.3961]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.4171]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.3312]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.3741]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.4570]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.4321]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 138.70it/s, loss=0.3856]
Training:  90%|█████████ | 85/94 [00:00<00:00, 138.02it/s, loss=0.3856]
Training:  90%|█████████ | 85/94 [00:00<00:00, 138.02it/s, loss=0.3394]
Training:  90%|█████████ | 85/94 [00:00<00:00, 138.02it/s, loss=0.3402]
Training:  90%|█████████ | 85/94 [00:00<00:00, 138.02it/s, loss=0.3559]
Training:  90%|█████████ | 85/94 [00:00<00:00, 138.02it/s, loss=0.3888]
Training:  90%|█████████ | 85/94 [00:00<00:00, 138.02it/s, loss=0.3898]
Training:  90%|█████████ | 85/94 [00:00<00:00, 138.02it/s, loss=0.3550]
Training:  90%|█████████ | 85/94 [00:00<00:00, 138.02it/s, loss=0.3690]
Training:  90%|█████████ | 85/94 [00:00<00:00, 138.02it/s, loss=0.3010]
Training:  90%|█████████ | 85/94 [00:00<00:00, 138.02it/s, loss=0.4134]
Training: 100%|██████████| 94/94 [00:00<00:00, 138.08it/s, loss=0.4134]

Training:   0%|          | 0/94 [00:00<?, ?it/s]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3277]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3937]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5060]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4077]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3526]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3353]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3366]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4580]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4642]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4153]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3182]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.2767]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4207]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4334]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5434]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.5434]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.2611]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.4176]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.4054]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.3124]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.3535]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.4377]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.3587]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.5133]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.3527]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.3262]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.2934]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.5297]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.5082]
Training:  16%|█▌        | 15/94 [00:00<00:00, 139.32it/s, loss=0.4834]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.4834]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.4321]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.3238]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.3505]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.4164]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.3668]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.4597]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.3126]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.3594]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.3966]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.5609]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.2380]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.5097]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.3794]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.5720]
Training:  31%|███       | 29/94 [00:00<00:00, 138.62it/s, loss=0.5119]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.5119]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.3062]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.4504]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.4789]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.5026]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.3864]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.3991]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.2980]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.4459]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.4785]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.5120]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.3655]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.5195]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.4370]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.4485]
Training:  47%|████▋     | 44/94 [00:00<00:00, 140.98it/s, loss=0.3862]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.3862]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.3429]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.3198]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.2460]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.5141]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.4284]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.3989]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.3952]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.3463]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.4689]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.4275]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.3055]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.3446]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.3346]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 138.40it/s, loss=0.3676]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.3676]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.3659]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.5908]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.3842]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.3976]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.3463]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.3543]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.3648]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.5090]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.4689]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.4195]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.3785]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.2973]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.4294]
Training:  78%|███████▊  | 73/94 [00:00<00:00, 136.51it/s, loss=0.3884]
Training:  93%|█████████▎| 87/94 [00:00<00:00, 134.36it/s, loss=0.3884]
Training:  93%|█████████▎| 87/94 [00:00<00:00, 134.36it/s, loss=0.2866]
Training:  93%|█████████▎| 87/94 [00:00<00:00, 134.36it/s, loss=0.4266]
Training:  93%|█████████▎| 87/94 [00:00<00:00, 134.36it/s, loss=0.3506]
Training:  93%|█████████▎| 87/94 [00:00<00:00, 134.36it/s, loss=0.4439]
Training:  93%|█████████▎| 87/94 [00:00<00:00, 134.36it/s, loss=0.4078]
Training:  93%|█████████▎| 87/94 [00:00<00:00, 134.36it/s, loss=0.3303]
Training:  93%|█████████▎| 87/94 [00:00<00:00, 134.36it/s, loss=0.2220]
Training: 100%|██████████| 94/94 [00:00<00:00, 136.49it/s, loss=0.2220]

Training:   0%|          | 0/94 [00:00<?, ?it/s]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.6494]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5749]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3792]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4136]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4561]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4604]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3879]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4357]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3410]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3723]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4260]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5176]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3988]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4208]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.4208]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.4715]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.3701]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.2736]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.3628]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.3325]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.5203]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.3033]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.4670]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.3946]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.3758]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.3689]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.4097]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.4007]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.28it/s, loss=0.4032]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.4032]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.3558]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.4009]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.2813]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.3360]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.4572]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.4998]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.3459]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.3786]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.3796]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.5104]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.3570]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.3825]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.3750]
Training:  30%|██▉       | 28/94 [00:00<00:00, 133.82it/s, loss=0.3766]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.3766]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.4502]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.4072]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.4512]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.4150]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.4070]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.3375]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.3574]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.3754]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.2899]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.3554]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.3425]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.3367]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.2551]
Training:  45%|████▍     | 42/94 [00:00<00:00, 134.57it/s, loss=0.3988]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.3988]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.5128]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.2941]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.3542]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.3552]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.3083]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.3585]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.4234]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.2545]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.5138]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.4805]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.3198]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.2584]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.3466]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 136.10it/s, loss=0.4052]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.4052]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.3354]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.4253]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.3704]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.4558]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.4080]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.3806]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.3435]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.3649]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.4643]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.4134]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.3791]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.4047]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.3779]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 137.04it/s, loss=0.4042]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 135.64it/s, loss=0.4042]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 135.64it/s, loss=0.4199]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 135.64it/s, loss=0.4088]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 135.64it/s, loss=0.3946]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 135.64it/s, loss=0.4302]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 135.64it/s, loss=0.4807]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 135.64it/s, loss=0.3108]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 135.64it/s, loss=0.2551]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 135.64it/s, loss=0.3433]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 135.64it/s, loss=0.3367]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 135.64it/s, loss=0.4688]
Training: 100%|██████████| 94/94 [00:00<00:00, 135.08it/s, loss=0.4688]

Training:   0%|          | 0/94 [00:00<?, ?it/s]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4440]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3011]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4217]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4337]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4498]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3977]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3648]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.2746]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.6074]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3580]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3846]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3786]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.2470]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4284]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.2947]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.2947]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.3455]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.4381]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.2795]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.4428]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.3360]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.3441]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.3748]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.4817]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.3379]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.3052]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.2777]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.3663]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.5379]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.4095]
Training:  16%|█▌        | 15/94 [00:00<00:00, 145.19it/s, loss=0.3897]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.3897]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.4851]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.3852]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.3713]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.3372]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.3317]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.3200]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.4493]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.3418]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.4183]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.3588]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.3170]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.4154]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.4036]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.4087]
Training:  32%|███▏      | 30/94 [00:00<00:00, 130.94it/s, loss=0.3843]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.3843]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.3770]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.3774]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.3591]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.4786]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.3191]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.4546]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.4854]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.3953]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.4010]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.4631]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.3445]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.3427]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.3640]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.3466]
Training:  48%|████▊     | 45/94 [00:00<00:00, 137.29it/s, loss=0.3661]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.3661]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.4314]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.3410]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.5349]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.3231]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.2797]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.3318]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.4299]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.2560]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.3073]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.3266]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.4261]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.3766]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.2721]
Training:  64%|██████▍   | 60/94 [00:00<00:00, 139.00it/s, loss=0.2720]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.2720]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.3266]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.3448]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.2762]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.3984]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.3254]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.3474]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.4617]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.3354]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.4357]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.4727]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.4343]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.3278]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.4174]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.2660]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 138.79it/s, loss=0.4200]
Training:  95%|█████████▍| 89/94 [00:00<00:00, 140.84it/s, loss=0.4200]
Training:  95%|█████████▍| 89/94 [00:00<00:00, 140.84it/s, loss=0.3508]
Training:  95%|█████████▍| 89/94 [00:00<00:00, 140.84it/s, loss=0.4717]
Training:  95%|█████████▍| 89/94 [00:00<00:00, 140.84it/s, loss=0.4233]
Training:  95%|█████████▍| 89/94 [00:00<00:00, 140.84it/s, loss=0.2768]
Training:  95%|█████████▍| 89/94 [00:00<00:00, 140.84it/s, loss=0.3858]
Training: 100%|██████████| 94/94 [00:00<00:00, 138.41it/s, loss=0.3858]

Training:   0%|          | 0/94 [00:00<?, ?it/s]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4751]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4202]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3948]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4098]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3284]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.2456]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3795]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.2562]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4175]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4910]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.2704]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4242]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4382]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3662]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.3662]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.3704]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.3589]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.3801]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.3854]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.2969]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.4040]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.3673]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.4495]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.3334]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.2685]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.3467]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.3962]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.3514]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.43it/s, loss=0.2981]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.2981]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3567]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3713]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.2919]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.6764]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.4218]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.4172]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.4425]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3276]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3458]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3305]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3651]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3361]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3691]
Training:  30%|██▉       | 28/94 [00:00<00:00, 131.33it/s, loss=0.3061]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.3061]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.4689]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.3829]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.3169]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.3545]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.3429]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.3749]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.3420]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.3049]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.3057]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.4119]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.3507]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.3286]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.3702]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.4632]
Training:  45%|████▍     | 42/94 [00:00<00:00, 127.26it/s, loss=0.3144]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.3144]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.4519]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.3693]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.3953]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.4334]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.3568]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.4082]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.2876]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.3503]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.3365]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.3857]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.3058]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.2733]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.3761]
Training:  61%|██████    | 57/94 [00:00<00:00, 134.99it/s, loss=0.4654]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.4654]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.3379]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.3519]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.4301]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.2408]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.2346]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.4479]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.3852]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.3601]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.3176]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.3416]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.4088]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.3913]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.3400]
Training:  76%|███████▌  | 71/94 [00:00<00:00, 132.01it/s, loss=0.3842]
Training:  90%|█████████ | 85/94 [00:00<00:00, 127.53it/s, loss=0.3842]
Training:  90%|█████████ | 85/94 [00:00<00:00, 127.53it/s, loss=0.3947]
Training:  90%|█████████ | 85/94 [00:00<00:00, 127.53it/s, loss=0.4098]
Training:  90%|█████████ | 85/94 [00:00<00:00, 127.53it/s, loss=0.3188]
Training:  90%|█████████ | 85/94 [00:00<00:00, 127.53it/s, loss=0.3934]
Training:  90%|█████████ | 85/94 [00:00<00:00, 127.53it/s, loss=0.4428]
Training:  90%|█████████ | 85/94 [00:00<00:00, 127.53it/s, loss=0.3843]
Training:  90%|█████████ | 85/94 [00:00<00:00, 127.53it/s, loss=0.4948]
Training:  90%|█████████ | 85/94 [00:00<00:00, 127.53it/s, loss=0.2812]
Training:  90%|█████████ | 85/94 [00:00<00:00, 127.53it/s, loss=0.2793]
Training: 100%|██████████| 94/94 [00:00<00:00, 129.15it/s, loss=0.2793]

Training:   0%|          | 0/94 [00:00<?, ?it/s]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3964]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3529]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3703]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4307]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3373]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4213]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3911]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4212]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4408]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3499]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4180]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4182]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3601]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4364]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.4364]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.6107]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.3977]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.3690]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.3929]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.3336]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.4076]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.4055]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.4618]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.4002]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.3372]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.2992]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.3302]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.3470]
Training:  15%|█▍        | 14/94 [00:00<00:00, 137.74it/s, loss=0.3056]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.3056]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.3214]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.2758]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.3461]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.3574]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.2704]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.3332]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.3208]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.4866]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.2887]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.3076]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.2542]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.3716]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.3544]
Training:  30%|██▉       | 28/94 [00:00<00:00, 137.19it/s, loss=0.3960]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.3960]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.5041]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.2622]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.2809]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.2747]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.4534]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.4242]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.3393]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.4680]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.3268]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.4203]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.3344]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.3086]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.3278]
Training:  45%|████▍     | 42/94 [00:00<00:00, 137.97it/s, loss=0.3066]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.3066]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.5236]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.2692]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.2806]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.2990]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.2963]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.4548]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.3984]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.5343]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.3611]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.3560]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.3205]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.3814]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.3944]
Training:  60%|█████▉    | 56/94 [00:00<00:00, 132.25it/s, loss=0.3452]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.3452]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.3199]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.3711]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.3727]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.4126]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.4350]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.3135]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.3530]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.4097]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.3952]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.4086]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.3818]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.3214]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.4977]
Training:  74%|███████▍  | 70/94 [00:00<00:00, 134.10it/s, loss=0.3244]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 130.14it/s, loss=0.3244]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 130.14it/s, loss=0.3413]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 130.14it/s, loss=0.3600]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 130.14it/s, loss=0.2342]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 130.14it/s, loss=0.3549]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 130.14it/s, loss=0.3505]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 130.14it/s, loss=0.3054]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 130.14it/s, loss=0.2503]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 130.14it/s, loss=0.4057]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 130.14it/s, loss=0.2228]
Training:  89%|████████▉ | 84/94 [00:00<00:00, 130.14it/s, loss=0.3249]
Training: 100%|██████████| 94/94 [00:00<00:00, 131.52it/s, loss=0.3249]

Training:   0%|          | 0/94 [00:00<?, ?it/s]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3593]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4461]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.5087]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3382]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.4578]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3634]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3054]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3113]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3629]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3471]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3167]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3973]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3426]
Training:   0%|          | 0/94 [00:00<?, ?it/s, loss=0.3917]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.3917]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.3799]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.3696]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.3351]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.3015]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.3481]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.2551]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.3281]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.2997]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.3776]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.3204]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.4140]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.3466]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.2946]
Training:  15%|█▍        | 14/94 [00:00<00:00, 138.24it/s, loss=0.3302]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.3302]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.3792]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.2484]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.4159]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.3060]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.2635]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.2166]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.1904]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.4535]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.4099]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.4123]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.4754]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.4275]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.3489]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.3288]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.2711]
Training:  30%|██▉       | 28/94 [00:00<00:00, 138.55it/s, loss=0.4461]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.4461]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.3333]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.2601]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.3460]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.3780]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.3367]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.3230]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.3329]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.4227]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.2813]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.2993]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.4870]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.3723]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.3048]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.3827]
Training:  47%|████▋     | 44/94 [00:00<00:00, 144.58it/s, loss=0.4952]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.4952]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.3874]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.2413]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.2926]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.3859]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.4540]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.3305]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.3561]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.3573]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.3204]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.3622]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.5269]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.3558]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.3037]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.4573]
Training:  63%|██████▎   | 59/94 [00:00<00:00, 139.97it/s, loss=0.4259]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.4259]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.4623]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.3567]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.3914]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.3867]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.3900]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.3065]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.3399]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.3181]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.4289]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.3519]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.4431]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.3859]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.4889]
Training:  79%|███████▊  | 74/94 [00:00<00:00, 139.35it/s, loss=0.3435]
Training:  94%|█████████▎| 88/94 [00:00<00:00, 137.86it/s, loss=0.3435]
Training:  94%|█████████▎| 88/94 [00:00<00:00, 137.86it/s, loss=0.3468]
Training:  94%|█████████▎| 88/94 [00:00<00:00, 137.86it/s, loss=0.4007]
Training:  94%|█████████▎| 88/94 [00:00<00:00, 137.86it/s, loss=0.3558]
Training:  94%|█████████▎| 88/94 [00:00<00:00, 137.86it/s, loss=0.4067]
Training:  94%|█████████▎| 88/94 [00:00<00:00, 137.86it/s, loss=0.2568]
Training:  94%|█████████▎| 88/94 [00:00<00:00, 137.86it/s, loss=0.2554]
Training: 100%|██████████| 94/94 [00:00<00:00, 138.76it/s, loss=0.2554]
/Users/xxz/PycharmProjects/crypto_predictor/training/trainer.py:285: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  checkpoint = torch.load(self.best_model_path, map_location=self.device)
Traceback (most recent call last):
  File "/Users/xxz/PycharmProjects/crypto_predictor/train_dlinear_real.py", line 163, in <module>
    main()
  File "/Users/xxz/PycharmProjects/crypto_predictor/train_dlinear_real.py", line 80, in main
    metrics = trainer.evaluate(test_loader)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/xxz/PycharmProjects/crypto_predictor/training/trainer.py", line 289, in evaluate
    metrics = evaluate_model(self.model, test_loader, self.task, self.device)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/xxz/PycharmProjects/crypto_predictor/training/evaluator.py", line 248, in evaluate_model
    all_preds.extend(preds)
TypeError: 'numpy.int64' object is not iterable

ERROR conda.cli.main_run:execute(127): `conda run python train_dlinear_real.py` failed. (See above for error)
================================================================================
DLinear模型训练 - 真实Binance数据
================================================================================

[1/7] 从Binance获取BTC 1h真实数据...
✓ 使用SOCKS5代理: socks5://127.0.0.1:7890
✓ 已成功连接到Binance API
从缓存加载数据：data/cache/BTC_1h_1y_now.csv
✓ 已获取 8760 行真实数据
✓ 时间范围：2025-01-28 15:00:00 至 2026-01-28 14:00:00

[2/7] 数据预处理（技术指标 + 特征工程）...
Created 8535 sequences with shape (8535, 168, 26)
✓ 已创建序列：X形状 = (8535, 168, 26), y形状 = (8535,)
✓ 特征数量：26
✓ 标签分布：下跌(0) = 6970, 上涨(1) = 1565

[3/7] 划分训练/验证/测试集 (70/15/15)...
Train: 5974 samples
Val: 1280 samples
Test: 1281 samples

[4/7] 创建PyTorch数据加载器...
✓ 训练批次：94
✓ 验证批次：20
✓ 测试批次：21

[5/7] 创建DLinear模型...
✓ 模型已创建，可训练参数：14,675 个

[6/7] 开始训练模型...
Training on device: mps
Starting training for 50 epochs...
Model parameters: 14675
Epoch 1/50
  Train loss: 0.4835
  Val loss: 0.4939
  LR: 0.001000
  Saved best model (val_loss: 0.4939)
Epoch 2/50
  Train loss: 0.4628
  Val loss: 0.4833
  LR: 0.001000
  Saved best model (val_loss: 0.4833)
Epoch 3/50
  Train loss: 0.4444
  Val loss: 0.5080
  LR: 0.001000
Epoch 4/50
  Train loss: 0.4312
  Val loss: 0.4956
  LR: 0.001000
Epoch 5/50
  Train loss: 0.4169
  Val loss: 0.5220
  LR: 0.001000
Epoch 6/50
  Train loss: 0.4070
  Val loss: 0.5491
  LR: 0.001000
Epoch 7/50
  Train loss: 0.3995
  Val loss: 0.5842
  LR: 0.001000
Epoch 8/50
  Train loss: 0.3922
  Val loss: 0.5482
  LR: 0.001000
Epoch 9/50
  Train loss: 0.3773
  Val loss: 0.5535
  LR: 0.000500
Epoch 10/50
  Train loss: 0.3690
  Val loss: 0.5738
  LR: 0.000500
Epoch 11/50
  Train loss: 0.3653
  Val loss: 0.6210
  LR: 0.000500
Epoch 12/50
  Train loss: 0.3603
  Val loss: 0.5912
  LR: 0.000500
Early stopping at epoch 12

Training completed!
Best validation loss: 0.4833
Best model saved to: models/checkpoints/dlinear_btc_1h_real/best_model.pt

[7/7] 在测试集上评估模型...
Loading best model from models/checkpoints/dlinear_btc_1h_real/best_model.pt

