nohup.out

12/28/2018 20:54:12 - INFO - __main__ -   device: cuda n_gpu: 2, distributed training: False, 16-bits training: False
12/28/2018 20:54:12 - INFO - pytorch_pretrained_bert.tokenization -   loading vocabulary file /data/nfsdata/meijie/data/uncased_L-12_H-768_A-12/vocab.txt
12/28/2018 20:54:13 - INFO - pytorch_pretrained_bert.modeling -   loading archive file /data/nfsdata/meijie/data/uncased_L-12_H-768_A-12
12/28/2018 20:54:13 - INFO - pytorch_pretrained_bert.modeling -   Model config {
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "max_position_embeddings": 512,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "type_vocab_size": 2,
  "vocab_size": 30522
}

12/28/2018 20:54:23 - INFO - pytorch_pretrained_bert.modeling -   Weights of BertForQuestionAnswering not initialized from pretrained model: ['qa_outputs.weight', 'qa_outputs.bias']
12/28/2018 20:54:23 - INFO - pytorch_pretrained_bert.modeling -   Weights from pretrained model not used in BertForQuestionAnswering: ['cls.predictions.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.decoder.weight', 'cls.seq_relationship.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.LayerNorm.bias']
12/28/2018 20:54:29 - INFO - __main__ -   ***** Running training *****
12/28/2018 20:54:29 - INFO - __main__ -     Num orig examples = 1177
12/28/2018 20:54:29 - INFO - __main__ -     Num split examples = 1196
12/28/2018 20:54:29 - INFO - __main__ -     Batch size = 12
12/28/2018 20:54:29 - INFO - __main__ -     Num steps = 2942
Epoch:   0%|          | 0/30 [00:00<?, ?it/s]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A/home/meefly/.local/lib/python3.6/site-packages/torch/nn/parallel/_functions.py:58: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
  warnings.warn('Was asked to gather along dimension 0, but all '

Iteration:   1%|          | 1/100 [00:06<10:58,  6.65s/it][A
Iteration:   2%|▏         | 2/100 [00:07<07:57,  4.87s/it][A
Iteration:   3%|▎         | 3/100 [00:07<05:46,  3.58s/it][A
Iteration:   4%|▍         | 4/100 [00:08<04:16,  2.67s/it][A
Iteration:   5%|▌         | 5/100 [00:09<03:12,  2.03s/it][A
Iteration:   6%|▌         | 6/100 [00:09<02:28,  1.58s/it][A
Iteration:   7%|▋         | 7/100 [00:10<01:57,  1.26s/it][A
Iteration:   8%|▊         | 8/100 [00:10<01:35,  1.04s/it][A
Iteration:   9%|▉         | 9/100 [00:11<01:20,  1.14it/s][A
Iteration:  10%|█         | 10/100 [00:11<01:09,  1.30it/s][A
Iteration:  11%|█         | 11/100 [00:12<01:01,  1.44it/s][A
Iteration:  12%|█▏        | 12/100 [00:12<00:57,  1.53it/s][A
Iteration:  13%|█▎        | 13/100 [00:13<00:53,  1.62it/s][A
Iteration:  14%|█▍        | 14/100 [00:13<00:51,  1.67it/s][A
Iteration:  15%|█▌        | 15/100 [00:14<00:49,  1.71it/s][A
Iteration:  16%|█▌        | 16/100 [00:14<00:48,  1.74it/s][A
Iteration:  17%|█▋        | 17/100 [00:15<00:47,  1.76it/s][A
Iteration:  18%|█▊        | 18/100 [00:15<00:45,  1.79it/s][A
Iteration:  19%|█▉        | 19/100 [00:16<00:44,  1.81it/s][A
Iteration:  20%|██        | 20/100 [00:17<00:44,  1.81it/s][A
Iteration:  21%|██        | 21/100 [00:17<00:43,  1.81it/s][A
Iteration:  22%|██▏       | 22/100 [00:18<00:43,  1.81it/s][A
Iteration:  23%|██▎       | 23/100 [00:18<00:42,  1.81it/s][A
Iteration:  24%|██▍       | 24/100 [00:19<00:41,  1.82it/s][A
Iteration:  25%|██▌       | 25/100 [00:19<00:41,  1.83it/s][A
Iteration:  26%|██▌       | 26/100 [00:20<00:40,  1.83it/s][A
Iteration:  27%|██▋       | 27/100 [00:20<00:39,  1.84it/s][A
Iteration:  28%|██▊       | 28/100 [00:21<00:39,  1.83it/s][A
Iteration:  29%|██▉       | 29/100 [00:21<00:38,  1.83it/s][A
Iteration:  30%|███       | 30/100 [00:22<00:38,  1.83it/s][A
Iteration:  31%|███       | 31/100 [00:23<00:37,  1.83it/s][A
Iteration:  32%|███▏      | 32/100 [00:23<00:37,  1.83it/s][A
Iteration:  33%|███▎      | 33/100 [00:24<00:36,  1.83it/s][A
Iteration:  34%|███▍      | 34/100 [00:24<00:35,  1.84it/s][A
Iteration:  35%|███▌      | 35/100 [00:25<00:35,  1.85it/s][A
Iteration:  36%|███▌      | 36/100 [00:25<00:34,  1.84it/s][A
Iteration:  37%|███▋      | 37/100 [00:26<00:34,  1.83it/s][A
Iteration:  38%|███▊      | 38/100 [00:26<00:33,  1.83it/s][A
Iteration:  39%|███▉      | 39/100 [00:27<00:33,  1.84it/s][A
Iteration:  40%|████      | 40/100 [00:27<00:32,  1.85it/s][A
Iteration:  41%|████      | 41/100 [00:28<00:31,  1.86it/s][A
Iteration:  42%|████▏     | 42/100 [00:29<00:31,  1.87it/s][A
Iteration:  43%|████▎     | 43/100 [00:29<00:30,  1.86it/s][A
Iteration:  44%|████▍     | 44/100 [00:30<00:30,  1.85it/s][A
Iteration:  45%|████▌     | 45/100 [00:30<00:29,  1.84it/s][A
Iteration:  46%|████▌     | 46/100 [00:31<00:29,  1.84it/s][A
Iteration:  47%|████▋     | 47/100 [00:31<00:28,  1.87it/s][A
Iteration:  48%|████▊     | 48/100 [00:32<00:27,  1.89it/s][A
Iteration:  49%|████▉     | 49/100 [00:32<00:26,  1.91it/s][A
Iteration:  50%|█████     | 50/100 [00:33<00:26,  1.92it/s][A12/28/2018 21:00:36 - INFO - __main__ -   device: cuda n_gpu: 2, distributed training: False, 16-bits training: False
12/28/2018 21:00:36 - INFO - pytorch_pretrained_bert.tokenization -   loading vocabulary file /data/nfsdata/meijie/data/uncased_L-12_H-768_A-12/vocab.txt
12/28/2018 21:00:36 - INFO - pytorch_pretrained_bert.modeling -   loading archive file /data/nfsdata/meijie/data/uncased_L-12_H-768_A-12
12/28/2018 21:00:36 - INFO - pytorch_pretrained_bert.modeling -   Model config {
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "max_position_embeddings": 512,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "type_vocab_size": 2,
  "vocab_size": 30522
}

12/28/2018 21:00:47 - INFO - pytorch_pretrained_bert.modeling -   Weights of BertForQuestionAnswering not initialized from pretrained model: ['qa_outputs.weight', 'qa_outputs.bias']
12/28/2018 21:00:47 - INFO - pytorch_pretrained_bert.modeling -   Weights from pretrained model not used in BertForQuestionAnswering: ['cls.predictions.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.decoder.weight', 'cls.seq_relationship.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.LayerNorm.bias']
12/28/2018 21:00:52 - INFO - __main__ -   ***** Running training *****
12/28/2018 21:00:52 - INFO - __main__ -     Num orig examples = 1177
12/28/2018 21:00:52 - INFO - __main__ -     Num split examples = 1196
12/28/2018 21:00:52 - INFO - __main__ -     Batch size = 12
12/28/2018 21:00:52 - INFO - __main__ -     Num steps = 2942
Epoch:   0%|          | 0/30 [00:00<?, ?it/s]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A/home/meefly/.local/lib/python3.6/site-packages/torch/nn/parallel/_functions.py:58: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
  warnings.warn('Was asked to gather along dimension 0, but all '

Iteration:   1%|          | 1/100 [00:06<10:49,  6.56s/it][A
Iteration:   2%|▏         | 2/100 [00:07<07:48,  4.78s/it][A
Iteration:   3%|▎         | 3/100 [00:07<05:40,  3.51s/it][A
Iteration:   4%|▍         | 4/100 [00:08<04:11,  2.62s/it][A
Iteration:   5%|▌         | 5/100 [00:08<03:09,  2.00s/it][A
Iteration:   6%|▌         | 6/100 [00:09<02:26,  1.56s/it][A
Iteration:   7%|▋         | 7/100 [00:09<01:56,  1.25s/it][A
Iteration:   8%|▊         | 8/100 [00:10<01:35,  1.04s/it][A
Iteration:   9%|▉         | 9/100 [00:10<01:21,  1.12it/s][A
Iteration:  10%|█         | 10/100 [00:11<01:10,  1.27it/s][A
Iteration:  11%|█         | 11/100 [00:12<01:03,  1.40it/s][A
Iteration:  12%|█▏        | 12/100 [00:12<00:58,  1.51it/s][A
Iteration:  13%|█▎        | 13/100 [00:13<00:54,  1.60it/s][A
Iteration:  14%|█▍        | 14/100 [00:13<00:51,  1.67it/s][A
Iteration:  15%|█▌        | 15/100 [00:14<00:49,  1.72it/s][A
Iteration:  16%|█▌        | 16/100 [00:14<00:47,  1.75it/s][A
Iteration:  17%|█▋        | 17/100 [00:15<00:46,  1.79it/s][A
Iteration:  18%|█▊        | 18/100 [00:15<00:45,  1.81it/s][A
Iteration:  19%|█▉        | 19/100 [00:16<00:44,  1.83it/s][A
Iteration:  20%|██        | 20/100 [00:16<00:43,  1.83it/s][A
Iteration:  21%|██        | 21/100 [00:17<00:43,  1.83it/s][A
Iteration:  22%|██▏       | 22/100 [00:18<00:42,  1.83it/s][A
Iteration:  23%|██▎       | 23/100 [00:18<00:41,  1.83it/s][A
Iteration:  24%|██▍       | 24/100 [00:19<00:41,  1.84it/s][A
Iteration:  25%|██▌       | 25/100 [00:19<00:40,  1.85it/s][A
Iteration:  26%|██▌       | 26/100 [00:20<00:39,  1.85it/s][A
Iteration:  27%|██▋       | 27/100 [00:20<00:39,  1.86it/s][A
Iteration:  28%|██▊       | 28/100 [00:21<00:38,  1.87it/s][A
Iteration:  29%|██▉       | 29/100 [00:21<00:37,  1.88it/s][A
Iteration:  30%|███       | 30/100 [00:22<00:37,  1.88it/s][A
Iteration:  31%|███       | 31/100 [00:22<00:36,  1.88it/s][A
Iteration:  32%|███▏      | 32/100 [00:23<00:36,  1.88it/s][A
Iteration:  33%|███▎      | 33/100 [00:23<00:35,  1.88it/s][A
Iteration:  34%|███▍      | 34/100 [00:24<00:35,  1.89it/s][A
Iteration:  35%|███▌      | 35/100 [00:24<00:34,  1.89it/s][A
Iteration:  36%|███▌      | 36/100 [00:25<00:34,  1.88it/s][A
Iteration:  37%|███▋      | 37/100 [00:26<00:33,  1.87it/s][A
Iteration:  38%|███▊      | 38/100 [00:26<00:33,  1.87it/s][A
Iteration:  39%|███▉      | 39/100 [00:27<00:32,  1.87it/s][A
Iteration:  40%|████      | 40/100 [00:27<00:32,  1.87it/s][A
Iteration:  41%|████      | 41/100 [00:28<00:31,  1.87it/s][A
Iteration:  42%|████▏     | 42/100 [00:28<00:30,  1.88it/s][A
Iteration:  43%|████▎     | 43/100 [00:29<00:30,  1.87it/s][A
Iteration:  44%|████▍     | 44/100 [00:29<00:30,  1.87it/s][A
Iteration:  45%|████▌     | 45/100 [00:30<00:29,  1.86it/s][A
Iteration:  46%|████▌     | 46/100 [00:30<00:29,  1.85it/s][A
Iteration:  47%|████▋     | 47/100 [00:31<00:28,  1.85it/s][A
Iteration:  48%|████▊     | 48/100 [00:31<00:28,  1.84it/s][A
Iteration:  49%|████▉     | 49/100 [00:32<00:27,  1.84it/s][A
Iteration:  50%|█████     | 50/100 [00:33<00:27,  1.84it/s][A
Iteration:  51%|█████     | 51/100 [00:33<00:26,  1.84it/s][A
Iteration:  52%|█████▏    | 52/100 [00:34<00:26,  1.84it/s][A
Iteration:  53%|█████▎    | 53/100 [00:34<00:25,  1.84it/s][A
Iteration:  54%|█████▍    | 54/100 [00:35<00:24,  1.84it/s][A
Iteration:  55%|█████▌    | 55/100 [00:35<00:24,  1.84it/s][A
Iteration:  56%|█████▌    | 56/100 [00:36<00:23,  1.84it/s][A
Iteration:  57%|█████▋    | 57/100 [00:36<00:23,  1.85it/s][A
Iteration:  58%|█████▊    | 58/100 [00:37<00:22,  1.86it/s][A
Iteration:  59%|█████▉    | 59/100 [00:37<00:22,  1.85it/s][A
Iteration:  60%|██████    | 60/100 [00:38<00:21,  1.85it/s][A
Iteration:  61%|██████    | 61/100 [00:38<00:21,  1.84it/s][A
Iteration:  62%|██████▏   | 62/100 [00:39<00:20,  1.85it/s][A
Iteration:  63%|██████▎   | 63/100 [00:40<00:20,  1.83it/s][A
Iteration:  64%|██████▍   | 64/100 [00:40<00:19,  1.83it/s][A
Iteration:  65%|██████▌   | 65/100 [00:41<00:19,  1.82it/s][A
Iteration:  66%|██████▌   | 66/100 [00:41<00:18,  1.82it/s][A
Iteration:  67%|██████▋   | 67/100 [00:42<00:18,  1.82it/s][A
Iteration:  68%|██████▊   | 68/100 [00:42<00:17,  1.83it/s][A
Iteration:  69%|██████▉   | 69/100 [00:43<00:16,  1.84it/s][A
Iteration:  70%|███████   | 70/100 [00:43<00:16,  1.85it/s][A
Iteration:  71%|███████   | 71/100 [00:44<00:15,  1.85it/s][A
Iteration:  72%|███████▏  | 72/100 [00:44<00:15,  1.85it/s][A
Iteration:  73%|███████▎  | 73/100 [00:45<00:14,  1.85it/s][A
Iteration:  74%|███████▍  | 74/100 [00:46<00:13,  1.86it/s][A
Iteration:  75%|███████▌  | 75/100 [00:46<00:13,  1.87it/s][A
Iteration:  76%|███████▌  | 76/100 [00:47<00:12,  1.87it/s][A
Iteration:  77%|███████▋  | 77/100 [00:47<00:12,  1.87it/s][A
Iteration:  78%|███████▊  | 78/100 [00:48<00:11,  1.87it/s][A
Iteration:  79%|███████▉  | 79/100 [00:48<00:11,  1.88it/s][A
Iteration:  80%|████████  | 80/100 [00:49<00:10,  1.88it/s][A
Iteration:  81%|████████  | 81/100 [00:49<00:10,  1.88it/s][A
Iteration:  82%|████████▏ | 82/100 [00:50<00:09,  1.87it/s][A
Iteration:  83%|████████▎ | 83/100 [00:50<00:09,  1.86it/s][A
Iteration:  84%|████████▍ | 84/100 [00:51<00:08,  1.86it/s][A
Iteration:  85%|████████▌ | 85/100 [00:51<00:08,  1.85it/s][A
Iteration:  86%|████████▌ | 86/100 [00:52<00:07,  1.84it/s][A
Iteration:  87%|████████▋ | 87/100 [00:53<00:07,  1.85it/s][A
Iteration:  88%|████████▊ | 88/100 [00:53<00:06,  1.88it/s][A
Iteration:  89%|████████▉ | 89/100 [00:54<00:05,  1.91it/s][A
Iteration:  90%|█████████ | 90/100 [00:54<00:05,  1.91it/s][A
Iteration:  91%|█████████ | 91/100 [00:55<00:04,  1.93it/s][A
Iteration:  92%|█████████▏| 92/100 [00:55<00:04,  1.90it/s][A
Iteration:  93%|█████████▎| 93/100 [00:56<00:03,  1.88it/s][A
Iteration:  94%|█████████▍| 94/100 [00:56<00:03,  1.87it/s][A
Iteration:  95%|█████████▌| 95/100 [00:57<00:02,  1.85it/s][A
Iteration:  96%|█████████▌| 96/100 [00:57<00:02,  1.85it/s][A
Iteration:  97%|█████████▋| 97/100 [00:58<00:01,  1.82it/s][A
Iteration:  98%|█████████▊| 98/100 [00:58<00:01,  1.81it/s][A
Iteration:  99%|█████████▉| 99/100 [00:59<00:00,  1.81it/s][A
Iteration: 100%|██████████| 100/100 [00:59<00:00,  1.90it/s][A
[AEpoch:   3%|▎         | 1/30 [00:59<28:58, 59.94s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:54,  1.83it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.84it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.84it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:51,  1.85it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.85it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:50,  1.86it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:49,  1.86it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:49,  1.86it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:48,  1.86it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.85it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:48,  1.84it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.84it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.84it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.84it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.84it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.84it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:44,  1.85it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.84it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.84it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.84it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:42,  1.84it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.84it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:41,  1.84it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.83it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:40,  1.83it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.83it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.87it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:38,  1.89it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:37,  1.91it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:36,  1.92it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:35,  1.93it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:35,  1.91it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:35,  1.90it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:35,  1.88it/s][A
Iteration:  35%|███▌      | 35/100 [00:18<00:34,  1.86it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.85it/s][A
Iteration:  37%|███▋      | 37/100 [00:19<00:34,  1.85it/s][ABetter speed can be achieved with apex installed from https://www.github.com/nvidia/apex.
tensor(35.7190, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.5284, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.6775, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.6649, device='cuda:0', grad_fn=<MeanBackward1>) tensor(36.0738, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.6258, device='cuda:0', grad_fn=<MeanBackward1>) tensor(36.3579, device='cuda:0', grad_fn=<MeanBackward1>) tensor(36.2161, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.5443, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.5191, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.7809, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.5433, device='cuda:0', grad_fn=<MeanBackward1>) tensor(36.2103, device='cuda:0', grad_fn=<MeanBackward1>) tensor(36.0296, device='cuda:0', grad_fn=<MeanBackward1>) tensor(36.1959, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.4065, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.7888, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.0770, device='cuda:0', grad_fn=<MeanBackward1>) tensor(36.2357, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.6453, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.5829, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.5944, device='cuda:0', grad_fn=<MeanBackward1>) tensor(36.0803, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.4188, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.3667, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.4666, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.6988, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.8574, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.6057, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.1521, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.4946, device='cuda:0', grad_fn=<MeanBackward1>) tensor(36.1301, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.2759, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.5610, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.9933, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.2952, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.4758, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.0467, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.4220, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.8205, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.2079, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.8988, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.1239, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.1106, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.4959, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.1998, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.4077, device='cuda:0', grad_fn=<MeanBackward1>) tensor(35.2854, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.8783, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.3283, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.4950, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.9320, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.4494, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.6740, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.3991, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.3139, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.0329, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.8319, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.2566, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.0327, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.8646, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.2083, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.8513, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.9766, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.7691, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.0155, device='cuda:0', grad_fn=<MeanBackward1>) tensor(34.1935, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.4364, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.7150, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.8655, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.9587, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.1649, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.5211, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.7156, device='cuda:0', grad_fn=<MeanBackward1>) tensor(32.3505, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.0286, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.1351, device='cuda:0', grad_fn=<MeanBackward1>) tensor(33.1459, device='cuda:0', grad_fn=<MeanBackward1>) tensor(32.2339, device='cuda:0', grad_fn=<MeanBackward1>) tensor(32.9354, device='cuda:0', grad_fn=<MeanBackward1>) tensor(31.9212, device='cuda:0', grad_fn=<MeanBackward1>) tensor(32.0864, device='cuda:0', grad_fn=<MeanBackward1>) tensor(31.9971, device='cuda:0', grad_fn=<MeanBackward1>) tensor(32.5682, device='cuda:0', grad_fn=<MeanBackward1>) tensor(31.3718, device='cuda:0', grad_fn=<MeanBackward1>) tensor(31.2569, device='cuda:0', grad_fn=<MeanBackward1>) tensor(31.0495, device='cuda:0', grad_fn=<MeanBackward1>) tensor(32.3168, device='cuda:0', grad_fn=<MeanBackward1>) tensor(29.0517, device='cuda:0', grad_fn=<MeanBackward1>) tensor(30.3467, device='cuda:0', grad_fn=<MeanBackward1>) tensor(30.4135, device='cuda:0', grad_fn=<MeanBackward1>) tensor(30.1993, device='cuda:0', grad_fn=<MeanBackward1>) tensor(30.8677, device='cuda:0', grad_fn=<MeanBackward1>) tensor(29.3833, device='cuda:0', grad_fn=<MeanBackward1>) tensor(28.3529, device='cuda:0', grad_fn=<MeanBackward1>) tensor(28.7499, device='cuda:0', grad_fn=<MeanBackward1>) tensor(28.7933, device='cuda:0', grad_fn=<MeanBackward1>) tensor(28.4807, device='cuda:0', grad_fn=<MeanBackward1>) tensor(28.5933, device='cuda:0', grad_fn=<MeanBackward1>) tensor(19.8771, device='cuda:0', grad_fn=<MeanBackward1>) tensor(27.2718, device='cuda:0', grad_fn=<MeanBackward1>) tensor(27.7017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(28.1623, device='cuda:0', grad_fn=<MeanBackward1>) tensor(26.9756, device='cuda:0', grad_fn=<MeanBackward1>) tensor(28.6890, device='cuda:0', grad_fn=<MeanBackward1>) tensor(25.2464, device='cuda:0', grad_fn=<MeanBackward1>) tensor(26.9185, device='cuda:0', grad_fn=<MeanBackward1>) tensor(28.6738, device='cuda:0', grad_fn=<MeanBackward1>) tensor(25.9392, device='cuda:0', grad_fn=<MeanBackward1>) tensor(27.9710, device='cuda:0', grad_fn=<MeanBackward1>) tensor(26.0500, device='cuda:0', grad_fn=<MeanBackward1>) tensor(26.6261, device='cuda:0', grad_fn=<MeanBackward1>) tensor(26.4814, device='cuda:0', grad_fn=<MeanBackward1>) tensor(26.8821, device='cuda:0', grad_fn=<MeanBackward1>) tensor(25.4883, device='cuda:0', grad_fn=<MeanBackward1>) tensor(24.4640, device='cuda:0', grad_fn=<MeanBackward1>) tensor(23.5847, device='cuda:0', grad_fn=<MeanBackward1>) tensor(23.7877, device='cuda:0', grad_fn=<MeanBackward1>) tensor(26.0315, device='cuda:0', grad_fn=<MeanBackward1>) tensor(26.6754, device='cuda:0', grad_fn=<MeanBackward1>) tensor(27.4110, device='cuda:0', grad_fn=<MeanBackward1>) tensor(21.5436, device='cuda:0', grad_fn=<MeanBackward1>) tensor(22.5789, device='cuda:0', grad_fn=<MeanBackward1>) tensor(26.0395, device='cuda:0', grad_fn=<MeanBackward1>) tensor(26.2672, device='cuda:0', grad_fn=<MeanBackward1>) tensor(25.1768, device='cuda:0', grad_fn=<MeanBackward1>) tensor(22.8602, device='cuda:0', grad_fn=<MeanBackward1>) tensor(22.4364, device='cuda:0', grad_fn=<MeanBackward1>) tensor(24.2987, device='cuda:0', grad_fn=<MeanBackward1>) tensor(23.7889, device='cuda:0', grad_fn=<MeanBackward1>) tensor(21.5325, device='cuda:0', grad_fn=<MeanBackward1>) tensor(21.4440, device='cuda:0', grad_fn=<MeanBackward1>) tensor(23.0542, device='cuda:0', grad_fn=<MeanBackward1>) tensor(20.4385, device='cuda:0', grad_fn=<MeanBackward1>) tensor(22.1981, device='cuda:0', grad_fn=<MeanBackward1>) tensor(21.7050, device='cuda:0', grad_fn=<MeanBackward1>) tensor(21.1709, device='cuda:0', grad_fn=<MeanBackward1>) tensor(21.6080, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.85it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:32,  1.85it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.85it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:31,  1.85it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.85it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.83it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.83it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.83it/s][A
Iteration:  46%|████▌     | 46/100 [00:24<00:29,  1.82it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:29,  1.82it/s][A
Iteration:  48%|████▊     | 48/100 [00:25<00:28,  1.82it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.82it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.81it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.82it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.82it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.83it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.83it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.84it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:23,  1.84it/s][A
Iteration:  57%|█████▋    | 57/100 [00:30<00:23,  1.85it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.85it/s][A
Iteration:  59%|█████▉    | 59/100 [00:31<00:22,  1.84it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.85it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.84it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.84it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.84it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.83it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.84it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.83it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:17,  1.85it/s][A
Iteration:  68%|██████▊   | 68/100 [00:36<00:17,  1.87it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.87it/s][A
Iteration:  70%|███████   | 70/100 [00:37<00:15,  1.89it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.91it/s][A
Iteration:  72%|███████▏  | 72/100 [00:38<00:14,  1.88it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.87it/s][A
Iteration:  74%|███████▍  | 74/100 [00:39<00:13,  1.87it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.86it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:12,  1.86it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.85it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.84it/s][A
Iteration:  79%|███████▉  | 79/100 [00:42<00:11,  1.83it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.83it/s][A
Iteration:  81%|████████  | 81/100 [00:43<00:10,  1.82it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.82it/s][A
Iteration:  83%|████████▎ | 83/100 [00:44<00:09,  1.83it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.84it/s][A
Iteration:  85%|████████▌ | 85/100 [00:45<00:08,  1.85it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.84it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.85it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.85it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.85it/s][A
Iteration:  90%|█████████ | 90/100 [00:48<00:05,  1.86it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.85it/s][A
Iteration:  92%|█████████▏| 92/100 [00:49<00:04,  1.85it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.85it/s][A
Iteration:  94%|█████████▍| 94/100 [00:50<00:03,  1.85it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.86it/s][A
Iteration:  96%|█████████▌| 96/100 [00:51<00:02,  1.86it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.86it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.84it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.83it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.90it/s][A
[AEpoch:   7%|▋         | 2/30 [01:53<27:08, 58.17s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:53,  1.84it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.82it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:53,  1.83it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.83it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.84it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.84it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.85it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:49,  1.86it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:48,  1.86it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.86it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:47,  1.86it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.87it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:46,  1.87it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.86it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:45,  1.86it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.86it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:44,  1.85it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.85it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:43,  1.85it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.86it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:42,  1.86it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.85it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:41,  1.85it/s][A
Iteration:  24%|██▍       | 24/100 [00:12<00:41,  1.85it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:40,  1.85it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:39,  1.86it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.86it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:38,  1.85it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.86it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:37,  1.85it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.84it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.83it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.83it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.83it/s][A
Iteration:  35%|███▌      | 35/100 [00:18<00:35,  1.83it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.84it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.84it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.83it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.83it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.83it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.83it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.86it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:30,  1.88it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:29,  1.90it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:28,  1.91it/s][A
Iteration:  46%|████▌     | 46/100 [00:24<00:28,  1.92it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:27,  1.90it/s][A
Iteration:  48%|████▊     | 48/100 [00:25<00:27,  1.88it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.87it/s][A
Iteration:  50%|█████     | 50/100 [00:26<00:26,  1.88it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.87it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:25,  1.86it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.86it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:24,  1.86it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.86it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:23,  1.84it/s][A
Iteration:  57%|█████▋    | 57/100 [00:30<00:23,  1.85it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.85it/s][A
Iteration:  59%|█████▉    | 59/100 [00:31<00:22,  1.86it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.85it/s][A
Iteration:  61%|██████    | 61/100 [00:32<00:21,  1.84it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.84it/s][A
Iteration:  63%|██████▎   | 63/100 [00:33<00:20,  1.84it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.84it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:18,  1.85it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.83it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.83it/s][A
Iteration:  68%|██████▊   | 68/100 [00:36<00:17,  1.83it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.83it/s][A
Iteration:  70%|███████   | 70/100 [00:37<00:16,  1.84it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.84it/s][A
Iteration:  72%|███████▏  | 72/100 [00:38<00:15,  1.86it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.86it/s][A
Iteration:  74%|███████▍  | 74/100 [00:39<00:13,  1.86it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.87it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:12,  1.86it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.85it/s][A tensor(19.5217, device='cuda:0', grad_fn=<MeanBackward1>) tensor(19.4931, device='cuda:0', grad_fn=<MeanBackward1>) tensor(25.0291, device='cuda:0', grad_fn=<MeanBackward1>) tensor(23.7079, device='cuda:0', grad_fn=<MeanBackward1>) tensor(21.1116, device='cuda:0', grad_fn=<MeanBackward1>) tensor(28.6230, device='cuda:0', grad_fn=<MeanBackward1>) tensor(20.6984, device='cuda:0', grad_fn=<MeanBackward1>) tensor(14.1518, device='cuda:0', grad_fn=<MeanBackward1>) tensor(21.5892, device='cuda:0', grad_fn=<MeanBackward1>) tensor(16.8634, device='cuda:0', grad_fn=<MeanBackward1>) tensor(22.6581, device='cuda:0', grad_fn=<MeanBackward1>) tensor(17.4013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(19.9627, device='cuda:0', grad_fn=<MeanBackward1>) tensor(21.4767, device='cuda:0', grad_fn=<MeanBackward1>) tensor(21.8233, device='cuda:0', grad_fn=<MeanBackward1>) tensor(16.7135, device='cuda:0', grad_fn=<MeanBackward1>) tensor(19.6345, device='cuda:0', grad_fn=<MeanBackward1>) tensor(22.5731, device='cuda:0', grad_fn=<MeanBackward1>) tensor(20.7074, device='cuda:0', grad_fn=<MeanBackward1>) tensor(21.9474, device='cuda:0', grad_fn=<MeanBackward1>) tensor(17.1525, device='cuda:0', grad_fn=<MeanBackward1>) tensor(18.7872, device='cuda:0', grad_fn=<MeanBackward1>) tensor(19.1300, device='cuda:0', grad_fn=<MeanBackward1>) tensor(18.2275, device='cuda:0', grad_fn=<MeanBackward1>) tensor(15.7096, device='cuda:0', grad_fn=<MeanBackward1>) tensor(19.0289, device='cuda:0', grad_fn=<MeanBackward1>) tensor(16.3454, device='cuda:0', grad_fn=<MeanBackward1>) tensor(16.1548, device='cuda:0', grad_fn=<MeanBackward1>) tensor(18.1166, device='cuda:0', grad_fn=<MeanBackward1>) tensor(22.0522, device='cuda:0', grad_fn=<MeanBackward1>) tensor(19.4081, device='cuda:0', grad_fn=<MeanBackward1>) tensor(19.6903, device='cuda:0', grad_fn=<MeanBackward1>) tensor(19.2761, device='cuda:0', grad_fn=<MeanBackward1>) tensor(14.6820, device='cuda:0', grad_fn=<MeanBackward1>) tensor(20.4354, device='cuda:0', grad_fn=<MeanBackward1>) tensor(18.7604, device='cuda:0', grad_fn=<MeanBackward1>) tensor(17.6286, device='cuda:0', grad_fn=<MeanBackward1>) tensor(18.7149, device='cuda:0', grad_fn=<MeanBackward1>) tensor(22.4134, device='cuda:0', grad_fn=<MeanBackward1>) tensor(17.6916, device='cuda:0', grad_fn=<MeanBackward1>) tensor(17.4945, device='cuda:0', grad_fn=<MeanBackward1>) tensor(12.7009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(18.8083, device='cuda:0', grad_fn=<MeanBackward1>) tensor(13.9626, device='cuda:0', grad_fn=<MeanBackward1>) tensor(16.2995, device='cuda:0', grad_fn=<MeanBackward1>) tensor(11.6117, device='cuda:0', grad_fn=<MeanBackward1>) tensor(14.8884, device='cuda:0', grad_fn=<MeanBackward1>) tensor(13.5581, device='cuda:0', grad_fn=<MeanBackward1>) tensor(13.1327, device='cuda:0', grad_fn=<MeanBackward1>) tensor(15.0537, device='cuda:0', grad_fn=<MeanBackward1>) tensor(10.8806, device='cuda:0', grad_fn=<MeanBackward1>) tensor(14.3943, device='cuda:0', grad_fn=<MeanBackward1>) tensor(16.5873, device='cuda:0', grad_fn=<MeanBackward1>) tensor(16.0849, device='cuda:0', grad_fn=<MeanBackward1>) tensor(17.2781, device='cuda:0', grad_fn=<MeanBackward1>) tensor(10.7485, device='cuda:0', grad_fn=<MeanBackward1>) tensor(16.5903, device='cuda:0', grad_fn=<MeanBackward1>) tensor(20.1337, device='cuda:0', grad_fn=<MeanBackward1>) tensor(13.2532, device='cuda:0', grad_fn=<MeanBackward1>) tensor(12.1556, device='cuda:0', grad_fn=<MeanBackward1>) tensor(12.8779, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.5918, device='cuda:0', grad_fn=<MeanBackward1>) tensor(14.2135, device='cuda:0', grad_fn=<MeanBackward1>) tensor(10.0630, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.3797, device='cuda:0', grad_fn=<MeanBackward1>) tensor(12.6937, device='cuda:0', grad_fn=<MeanBackward1>) tensor(11.2402, device='cuda:0', grad_fn=<MeanBackward1>) tensor(11.3532, device='cuda:0', grad_fn=<MeanBackward1>) tensor(14.2157, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.9583, device='cuda:0', grad_fn=<MeanBackward1>) tensor(11.8444, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.4632, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.9739, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.2960, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.2640, device='cuda:0', grad_fn=<MeanBackward1>) tensor(15.9773, device='cuda:0', grad_fn=<MeanBackward1>) tensor(11.6414, device='cuda:0', grad_fn=<MeanBackward1>) tensor(11.3632, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.8825, device='cuda:0', grad_fn=<MeanBackward1>) tensor(8.3027, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.9856, device='cuda:0', grad_fn=<MeanBackward1>) tensor(8.9571, device='cuda:0', grad_fn=<MeanBackward1>) tensor(10.6716, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.5309, device='cuda:0', grad_fn=<MeanBackward1>) tensor(12.9184, device='cuda:0', grad_fn=<MeanBackward1>) tensor(11.0655, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.9719, device='cuda:0', grad_fn=<MeanBackward1>) tensor(12.8102, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.1327, device='cuda:0', grad_fn=<MeanBackward1>) tensor(10.6970, device='cuda:0', grad_fn=<MeanBackward1>) tensor(12.4478, device='cuda:0', grad_fn=<MeanBackward1>) tensor(13.9610, device='cuda:0', grad_fn=<MeanBackward1>) tensor(10.3259, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.7051, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.1586, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.1950, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.5813, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.8647, device='cuda:0', grad_fn=<MeanBackward1>) tensor(17.3659, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.3702, device='cuda:0', grad_fn=<MeanBackward1>) tensor(12.3091, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.6662, device='cuda:0', grad_fn=<MeanBackward1>) tensor(11.2644, device='cuda:0', grad_fn=<MeanBackward1>) tensor(13.6302, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.4936, device='cuda:0', grad_fn=<MeanBackward1>) tensor(12.3281, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.7969, device='cuda:0', grad_fn=<MeanBackward1>) tensor(8.7796, device='cuda:0', grad_fn=<MeanBackward1>) tensor(8.5798, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.2386, device='cuda:0', grad_fn=<MeanBackward1>) tensor(8.3152, device='cuda:0', grad_fn=<MeanBackward1>) tensor(11.0419, device='cuda:0', grad_fn=<MeanBackward1>) tensor(13.3992, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.6593, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.6577, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.5716, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.2528, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.1090, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.2988, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.8447, device='cuda:0', grad_fn=<MeanBackward1>) tensor(12.5544, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.2986, device='cuda:0', grad_fn=<MeanBackward1>) tensor(11.6539, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.0875, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.0189, device='cuda:0', grad_fn=<MeanBackward1>) tensor(13.9192, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.7054, device='cuda:0', grad_fn=<MeanBackward1>) tensor(8.6291, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.6385, device='cuda:0', grad_fn=<MeanBackward1>) tensor(8.2710, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.9630, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.3582, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.1131, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.4887, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.5389, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.1681, device='cuda:0', grad_fn=<MeanBackward1>) tensor(8.3563, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.8153, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.2369, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.6461, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.84it/s][A
Iteration:  79%|███████▉  | 79/100 [00:42<00:11,  1.84it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.84it/s][A
Iteration:  81%|████████  | 81/100 [00:43<00:10,  1.84it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.87it/s][A
Iteration:  83%|████████▎ | 83/100 [00:44<00:08,  1.89it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.91it/s][A
Iteration:  85%|████████▌ | 85/100 [00:45<00:07,  1.92it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.93it/s][A
Iteration:  87%|████████▋ | 87/100 [00:46<00:06,  1.90it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.89it/s][A
Iteration:  89%|████████▉ | 89/100 [00:47<00:05,  1.87it/s][A
Iteration:  90%|█████████ | 90/100 [00:48<00:05,  1.85it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.85it/s][A
Iteration:  92%|█████████▏| 92/100 [00:49<00:04,  1.85it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.83it/s][A
Iteration:  94%|█████████▍| 94/100 [00:50<00:03,  1.84it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.83it/s][A
Iteration:  96%|█████████▌| 96/100 [00:51<00:02,  1.83it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.81it/s][A
Iteration:  98%|█████████▊| 98/100 [00:52<00:01,  1.81it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.82it/s][A
Iteration: 100%|██████████| 100/100 [00:53<00:00,  1.91it/s][A
[AEpoch:  10%|█         | 3/30 [02:47<25:36, 56.89s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:54,  1.83it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.84it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.85it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:51,  1.85it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.85it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.84it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.84it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.83it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.84it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:49,  1.83it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:48,  1.83it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:48,  1.83it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.83it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.84it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.84it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.83it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.83it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.83it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.82it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:44,  1.81it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.81it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.85it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:41,  1.88it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:40,  1.90it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:39,  1.91it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:38,  1.92it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:38,  1.89it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:38,  1.88it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:37,  1.88it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:37,  1.87it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.85it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:36,  1.86it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.85it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:35,  1.84it/s][A
Iteration:  35%|███▌      | 35/100 [00:18<00:35,  1.84it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.83it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.83it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.83it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.81it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.82it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.82it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.83it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.82it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.82it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.82it/s][A
Iteration:  46%|████▌     | 46/100 [00:24<00:29,  1.83it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.83it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.83it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.83it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.83it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.84it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:25,  1.85it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.84it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.83it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.83it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.83it/s][A
Iteration:  57%|█████▋    | 57/100 [00:30<00:23,  1.83it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.83it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.83it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.83it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.82it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.83it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.82it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.83it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.83it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.84it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:17,  1.83it/s][A
Iteration:  68%|██████▊   | 68/100 [00:36<00:17,  1.85it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.85it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.85it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.84it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.84it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.83it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.83it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.83it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.83it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.84it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.84it/s][A
Iteration:  79%|███████▉  | 79/100 [00:42<00:11,  1.83it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.84it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.84it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.84it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.84it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.83it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.81it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.79it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.80it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.81it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:06,  1.82it/s][A
Iteration:  90%|█████████ | 90/100 [00:48<00:05,  1.82it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.81it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.82it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.82it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.82it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.83it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.84it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.88it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.90it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.91it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  2.01it/s][A
[AEpoch:  13%|█▎        | 4/30 [03:42<24:18, 56.10s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:51,  1.94it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:51,  1.90it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:51,  1.87it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:51,  1.86it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.85it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:50,  1.85it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.85it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:49,  1.86it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:48,  1.86it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.85it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:48,  1.84it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.83it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.83it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.83it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.84it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.84it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.84it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.83it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.82it/s][A tensor(9.6170, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.2795, device='cuda:0', grad_fn=<MeanBackward1>) tensor(10.3238, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.1224, device='cuda:0', grad_fn=<MeanBackward1>) tensor(8.7240, device='cuda:0', grad_fn=<MeanBackward1>) tensor(10.1101, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.9173, device='cuda:0', grad_fn=<MeanBackward1>) tensor(8.3745, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.4841, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.4282, device='cuda:0', grad_fn=<MeanBackward1>) tensor(8.4338, device='cuda:0', grad_fn=<MeanBackward1>) tensor(8.0449, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.6309, device='cuda:0', grad_fn=<MeanBackward1>) tensor(10.4466, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.2646, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.0426, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.9309, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.2764, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.3907, device='cuda:0', grad_fn=<MeanBackward1>) tensor(14.8181, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.4094, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4657, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.1746, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.1144, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7568, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.5564, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.0714, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.3006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.3838, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.7347, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.8105, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.8774, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.4126, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.8704, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.6489, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.5497, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.9307, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.0221, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.3174, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.8198, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.8656, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.5784, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.1578, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.8998, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.5024, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1204, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.4208, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0420, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.2843, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.7830, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.7764, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.7746, device='cuda:0', grad_fn=<MeanBackward1>) tensor(8.6879, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.4311, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.5775, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.4169, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.2333, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.6881, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.6291, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.3746, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.0429, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2904, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.0441, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2340, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.8735, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.4843, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.1458, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.5512, device='cuda:0', grad_fn=<MeanBackward1>) tensor(9.6382, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.3505, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.9071, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.4752, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.6990, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.4931, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.9806, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.0400, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.9883, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.2144, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.9120, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.2387, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9885, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.4355, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.4066, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.2418, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.3946, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.7523, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.5369, device='cuda:0', grad_fn=<MeanBackward1>) tensor(8.2282, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.8749, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.5602, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.7205, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.2373, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.4980, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.8264, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.9793, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.1585, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.3616, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.8725, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.3016, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.4284, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.5315, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.9057, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7600, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9048, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.0392, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.4467, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.8938, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.3599, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.3952, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.5287, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.5668, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.5549, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.7698, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.0979, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.0863, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.7086, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.5307, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.5706, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.8031, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.0357, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.9941, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1504, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9705, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.8705, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.4674, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.5110, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.2759, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.3212, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.4925, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3221, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.4245, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6410, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7257, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9895, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.8878, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.7267, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7761, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9041, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9714, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8723, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.5012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7350, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  20%|██        | 20/100 [00:10<00:44,  1.82it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.83it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.82it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:42,  1.82it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.81it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:41,  1.82it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.82it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.83it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.84it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.84it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.84it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.84it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.83it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.83it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.83it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.84it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:35,  1.83it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.83it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.83it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.83it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.82it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.81it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.82it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.82it/s][A
Iteration:  44%|████▍     | 44/100 [00:24<00:30,  1.82it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.82it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:29,  1.83it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.83it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.84it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.84it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.85it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.85it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:25,  1.85it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.86it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:24,  1.85it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.84it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:23,  1.85it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.86it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.86it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:21,  1.86it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.86it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.84it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.84it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.83it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.83it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.81it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.81it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.81it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.81it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:17,  1.79it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.78it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:16,  1.78it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.78it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:15,  1.80it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.81it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.82it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.83it/s][A
Iteration:  77%|███████▋  | 77/100 [00:42<00:12,  1.84it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.85it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.85it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.84it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.84it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.84it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.84it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.82it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.82it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.81it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.81it/s][A
Iteration:  88%|████████▊ | 88/100 [00:48<00:06,  1.82it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:06,  1.82it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.82it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.82it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.81it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.81it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.81it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.83it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.83it/s][A
Iteration:  97%|█████████▋| 97/100 [00:53<00:01,  1.82it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.82it/s][A
Iteration:  99%|█████████▉| 99/100 [00:54<00:00,  1.82it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.90it/s][A
[AEpoch:  17%|█▋        | 5/30 [04:36<23:11, 55.65s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:54,  1.82it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.82it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:53,  1.82it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.82it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:52,  1.82it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.81it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.84it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:49,  1.86it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:48,  1.87it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:47,  1.90it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:46,  1.91it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:46,  1.88it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.85it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.83it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.83it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.84it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.84it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.83it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.83it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:44,  1.82it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.82it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.83it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:41,  1.85it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:40,  1.86it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:40,  1.86it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:39,  1.86it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.85it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.83it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.83it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.81it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.83it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.83it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.83it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.83it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.84it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.85it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:33,  1.85it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.84it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.83it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:33,  1.81it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.80it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:32,  1.81it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.81it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.82it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.82it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:29,  1.82it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.85it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:27,  1.88it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:26,  1.90it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:26,  1.90it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:25,  1.91it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:25,  1.88it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.87it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:24,  1.85it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.85it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:23,  1.85it/s][A
Iteration:  57%|█████▋    | 57/100 [00:30<00:23,  1.84it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.83it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.83it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.82it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.81it/s][A tensor(1.1081, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8177, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5648, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.8934, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.6917, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4977, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.4188, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.5360, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2302, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6974, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.9631, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.1517, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.0394, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0805, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.2111, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.0659, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1721, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.3797, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7653, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9124, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9455, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.0043, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.6603, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7757, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.9480, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9029, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.8141, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9449, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.3505, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8941, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7033, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.7577, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7977, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6812, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.6969, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.1521, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.1447, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.7582, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1282, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.0421, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.0774, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.5804, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.8813, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.4468, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4122, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.5550, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.1962, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.9861, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9668, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1332, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9180, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.6219, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.5055, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.8967, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.2863, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.5136, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1325, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.8104, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0977, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7893, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.0940, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.9422, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1497, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.9089, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4366, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.7261, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9153, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.2642, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2475, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.5557, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.1212, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2402, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.5081, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8284, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1039, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.1556, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.0285, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.5621, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.5597, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0610, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.3153, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0219, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1338, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.4598, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.3830, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.5409, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2138, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5985, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3845, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9587, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6141, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.3082, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4773, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1898, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.4770, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9666, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.8754, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4914, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6849, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5988, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3344, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3399, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.1651, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7354, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.3303, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4454, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.5658, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2901, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8821, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8476, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5372, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1198, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9477, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5039, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4734, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.1818, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6576, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2035, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4744, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2483, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2178, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5691, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8304, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1605, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5521, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.8657, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.1824, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5191, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8885, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.5927, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3377, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5256, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.8835, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.6478, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.2770, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4553, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6152, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5821, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3016, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3521, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7716, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.8367, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  62%|██████▏   | 62/100 [00:33<00:21,  1.81it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.80it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.80it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.80it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.80it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.80it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.81it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:17,  1.82it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.81it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.82it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.80it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.82it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.83it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.83it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.84it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.86it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.86it/s][A
Iteration:  79%|███████▉  | 79/100 [00:42<00:11,  1.86it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.85it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.84it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.83it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.83it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.82it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.82it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.85it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:06,  1.88it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.90it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.91it/s][A
Iteration:  90%|█████████ | 90/100 [00:48<00:05,  1.92it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.90it/s][A
Iteration:  92%|█████████▏| 92/100 [00:49<00:04,  1.87it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.86it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.85it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.84it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.84it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.85it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.86it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.86it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.93it/s][A
[AEpoch:  20%|██        | 6/30 [05:30<22:05, 55.22s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:55,  1.77it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:54,  1.78it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:53,  1.80it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.82it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.83it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.83it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.83it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:49,  1.84it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.85it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.86it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:48,  1.85it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.84it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.85it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.85it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:45,  1.85it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.86it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:44,  1.86it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.84it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.80it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:44,  1.80it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.80it/s][A
Iteration:  22%|██▏       | 22/100 [00:12<00:43,  1.80it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:42,  1.81it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:42,  1.81it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:41,  1.81it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.85it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:38,  1.88it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:38,  1.88it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:37,  1.88it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:37,  1.89it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.86it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:36,  1.85it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.85it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:35,  1.85it/s][A
Iteration:  35%|███▌      | 35/100 [00:18<00:35,  1.86it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.86it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.85it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.85it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.83it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.83it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.83it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.82it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.80it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:31,  1.80it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.80it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:29,  1.81it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:29,  1.81it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.82it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:28,  1.82it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.82it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.83it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.84it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.85it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:24,  1.85it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.85it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:23,  1.84it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.83it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.84it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.83it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.83it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.83it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.83it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.83it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.83it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.82it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.83it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:17,  1.84it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.83it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.84it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.85it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.85it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.83it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.83it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.84it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.85it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.85it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.83it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:12,  1.83it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.84it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.85it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.84it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.83it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.83it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.83it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.83it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.83it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.83it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.84it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.84it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.84it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.83it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.83it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.81it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.82it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.80it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.81it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.82it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.81it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.82it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.90it/s][A
[AEpoch:  23%|██▎       | 7/30 [06:25<21:04, 54.99s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:55,  1.79it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:54,  1.79it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:53,  1.82it/s][A tensor(2.1750, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.2600, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.5678, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.1569, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.1075, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4970, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9506, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1941, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7229, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3056, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2301, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4112, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9740, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4024, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.5570, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9153, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3852, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3258, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.2480, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4198, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1784, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1883, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2148, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5897, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9266, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.7152, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4451, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4336, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8127, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.6028, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7686, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9159, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.1304, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.8454, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5320, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5033, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4037, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1693, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.6606, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5839, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4180, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7493, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3283, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0153, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5268, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5855, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1863, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5388, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.3705, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2602, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6562, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3641, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5900, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5265, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.1762, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.3156, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6298, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7736, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6361, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3744, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6704, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0662, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9536, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0500, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0606, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4916, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4672, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5074, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0915, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.5359, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.6047, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0464, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2997, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2797, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6955, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6950, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4739, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5573, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9329, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1302, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4602, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2103, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4366, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1661, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2588, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.0366, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.7053, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7450, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4361, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.0249, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4535, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7366, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8457, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2021, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2838, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7775, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2273, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6774, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1070, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.3469, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9098, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.7884, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6653, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1182, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7700, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2538, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3085, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.0935, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0880, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.6114, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.9359, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5215, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.6319, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.2486, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4777, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1273, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3742, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0937, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2066, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0391, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8095, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1030, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.3667, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7630, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3822, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.5481, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1493, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.5742, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0682, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0222, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2346, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.9199, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7022, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.8941, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2483, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0275, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0141, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0229, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7532, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0169, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1179, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.83it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.84it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:50,  1.84it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.83it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.82it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.83it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.84it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:48,  1.85it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.86it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:46,  1.86it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.84it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.83it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:46,  1.81it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:46,  1.80it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:45,  1.80it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.81it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.83it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.83it/s][A
Iteration:  22%|██▏       | 22/100 [00:12<00:42,  1.84it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:41,  1.84it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.83it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:41,  1.83it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.83it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.84it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:38,  1.85it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.84it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.83it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.82it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.81it/s][A
Iteration:  33%|███▎      | 33/100 [00:18<00:36,  1.82it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.82it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.82it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:35,  1.82it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.82it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:34,  1.82it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.82it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.82it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.80it/s][A
Iteration:  42%|████▏     | 42/100 [00:23<00:32,  1.80it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.80it/s][A
Iteration:  44%|████▍     | 44/100 [00:24<00:30,  1.81it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.82it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:29,  1.82it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:29,  1.82it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.82it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:28,  1.82it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.82it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.82it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.82it/s][A
Iteration:  53%|█████▎    | 53/100 [00:29<00:25,  1.83it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.83it/s][A
Iteration:  55%|█████▌    | 55/100 [00:30<00:24,  1.84it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:23,  1.84it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.84it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.84it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.83it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.82it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.83it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.84it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.85it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.85it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.83it/s][A
Iteration:  66%|██████▌   | 66/100 [00:36<00:18,  1.81it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.81it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.82it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.82it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.83it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.83it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.86it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.89it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:13,  1.90it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.92it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:12,  1.93it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.91it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.88it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.85it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.84it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.84it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.85it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.85it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.84it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.84it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.84it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.85it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.86it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.86it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.84it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.82it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.81it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.79it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.78it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.78it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.80it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.80it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.80it/s][A
Iteration:  99%|█████████▉| 99/100 [00:54<00:00,  1.81it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.89it/s][A
[AEpoch:  27%|██▋       | 8/30 [07:19<20:06, 54.85s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:54,  1.80it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:54,  1.81it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:53,  1.81it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.83it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.83it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:50,  1.85it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.85it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:49,  1.85it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.84it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.84it/s][A
Iteration:  11%|█         | 11/100 [00:06<00:49,  1.81it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:48,  1.83it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.85it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.87it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:44,  1.89it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:44,  1.91it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:43,  1.90it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.86it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.84it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.83it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:42,  1.85it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.85it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:41,  1.85it/s][A
Iteration:  24%|██▍       | 24/100 [00:12<00:40,  1.86it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:40,  1.84it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.84it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.83it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.83it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.84it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.83it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:38,  1.81it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.81it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.81it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.82it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.83it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.83it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.84it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.84it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.83it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.82it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.82it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.82it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.82it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.81it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.81it/s][A tensor(0.1441, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1497, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9167, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1851, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8080, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.9862, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0317, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0425, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1542, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0861, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0225, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0574, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2105, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3675, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4448, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.4845, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3738, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8085, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5127, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6588, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4577, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9319, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4344, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1920, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0266, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5289, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2385, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2580, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5123, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9435, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3350, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1632, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8856, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3756, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6524, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4251, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9508, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1952, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1232, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1657, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8077, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0481, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.8182, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0821, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4515, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3619, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9553, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4308, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5923, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.6533, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.8023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4351, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9200, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6540, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.4698, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0301, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3490, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0802, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2242, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3890, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0521, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0418, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1429, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0895, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5439, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2903, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1201, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3739, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2464, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0344, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3257, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5080, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6775, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.8394, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.2206, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2421, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0650, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.5008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.8323, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3994, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2641, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4107, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7043, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2151, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6050, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1040, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3156, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5811, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8203, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2720, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3273, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.4406, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1958, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9906, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0668, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1414, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.7456, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0483, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.5880, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2942, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1597, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0977, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2877, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2098, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1108, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7298, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.5583, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4492, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2240, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0434, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0773, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2337, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4881, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1105, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0712, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1268, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9801, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0778, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0115, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0174, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3667, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0037, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2425, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1389, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5085, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2370, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0373, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2490, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6200, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5539, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1891, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4070, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5485, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0907, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9299, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2755, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9592, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2240, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0988, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1550, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  46%|████▌     | 46/100 [00:25<00:30,  1.79it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:29,  1.79it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:29,  1.79it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:28,  1.80it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.81it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:27,  1.81it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.83it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.83it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.82it/s][A
Iteration:  55%|█████▌    | 55/100 [00:30<00:24,  1.82it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.82it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.84it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.85it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.84it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.85it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.85it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.84it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.84it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.84it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.84it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.83it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.83it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.81it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:17,  1.81it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.83it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.84it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.84it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.83it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.83it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.82it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.82it/s][A
Iteration:  77%|███████▋  | 77/100 [00:42<00:12,  1.81it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:12,  1.81it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.81it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:11,  1.79it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.79it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:10,  1.79it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.79it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.80it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.80it/s][A
Iteration:  86%|████████▌ | 86/100 [00:47<00:07,  1.81it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.81it/s][A
Iteration:  88%|████████▊ | 88/100 [00:48<00:06,  1.80it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:06,  1.80it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.80it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.81it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.82it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.83it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.83it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.84it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.85it/s][A
Iteration:  97%|█████████▋| 97/100 [00:53<00:01,  1.85it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.86it/s][A
Iteration:  99%|█████████▉| 99/100 [00:54<00:00,  1.84it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.93it/s][A
[AEpoch:  30%|███       | 9/30 [08:14<19:10, 54.77s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:54,  1.83it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.83it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.84it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:51,  1.85it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.84it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.84it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.84it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:49,  1.84it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.85it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.85it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:48,  1.84it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:48,  1.82it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.83it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.83it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.84it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.83it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.83it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.82it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.82it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.83it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.83it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.85it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:41,  1.88it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:40,  1.85it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:40,  1.86it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:39,  1.87it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.85it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.83it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.84it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.84it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.84it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.84it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.84it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:35,  1.85it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.85it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.83it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.83it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:34,  1.81it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.81it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:33,  1.81it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.82it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.83it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.82it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.82it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.79it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:30,  1.78it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:29,  1.79it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.80it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:28,  1.80it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.80it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:27,  1.80it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.80it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:26,  1.79it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.80it/s][A
Iteration:  55%|█████▌    | 55/100 [00:30<00:24,  1.80it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.81it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.82it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:23,  1.82it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.82it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.83it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.82it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.82it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.82it/s][A
Iteration:  64%|██████▍   | 64/100 [00:35<00:19,  1.82it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.80it/s][A
Iteration:  66%|██████▌   | 66/100 [00:36<00:18,  1.81it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.81it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.82it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.83it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.84it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.85it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.85it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.85it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:13,  1.86it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.86it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:12,  1.85it/s][A
Iteration:  77%|███████▋  | 77/100 [00:42<00:12,  1.83it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:12,  1.83it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.82it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.83it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.83it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.84it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.83it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.83it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.82it/s][A
Iteration:  86%|████████▌ | 86/100 [00:47<00:07,  1.82it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.83it/s][A tensor(0.1120, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4683, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3890, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0108, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.5335, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1493, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.3523, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3436, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.5808, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3501, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6867, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6987, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2788, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4265, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2938, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4635, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2723, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2568, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1121, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3103, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4129, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1472, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3346, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0304, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0083, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0956, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1676, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.6658, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9224, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5128, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6765, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.6642, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2286, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5280, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0086, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3612, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.5225, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1710, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0626, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4229, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2582, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6099, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3129, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0341, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0217, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1885, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1939, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0183, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0542, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3884, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1390, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5624, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.5872, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0975, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1485, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5562, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0086, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4725, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3359, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0150, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0102, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1827, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2871, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2151, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0336, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2309, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0060, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1672, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6629, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7035, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0119, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2945, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6634, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0740, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7468, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0856, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3803, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8540, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5177, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2357, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0370, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1588, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0981, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2634, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0187, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1532, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2830, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0458, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0150, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0163, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0169, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2619, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0180, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1952, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4970, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1534, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0181, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9398, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0636, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3900, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5144, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1075, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0779, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1689, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0191, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0299, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3990, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1461, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0374, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0215, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.3935, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5762, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1301, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1150, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1244, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1736, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0936, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1069, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1549, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2872, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1375, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0318, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0225, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3436, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0065, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2053, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5732, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0108, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0043, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3627, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4626, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0188, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0050, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2626, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0085, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0331, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1817, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1357, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1731, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0377, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0973, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0273, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  88%|████████▊ | 88/100 [00:48<00:06,  1.84it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.84it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.84it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.83it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.83it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.83it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.82it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.82it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.82it/s][A
Iteration:  97%|█████████▋| 97/100 [00:53<00:01,  1.82it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.80it/s][A
Iteration:  99%|█████████▉| 99/100 [00:54<00:00,  1.79it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.89it/s][A
[AEpoch:  33%|███▎      | 10/30 [09:09<18:14, 54.74s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:55,  1.80it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:54,  1.81it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:53,  1.81it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.82it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.83it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.83it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.82it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.83it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.84it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.85it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:47,  1.86it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:48,  1.83it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:48,  1.81it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:47,  1.81it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:47,  1.80it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:46,  1.81it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.83it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.84it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:43,  1.85it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.86it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.83it/s][A
Iteration:  22%|██▏       | 22/100 [00:12<00:42,  1.83it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:41,  1.84it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.84it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:40,  1.85it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.84it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.85it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.84it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.84it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.83it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:38,  1.81it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.84it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.86it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:34,  1.89it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:34,  1.89it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.87it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:33,  1.86it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.85it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:32,  1.85it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.85it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.84it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.83it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.83it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.81it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.81it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:30,  1.80it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:29,  1.81it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.82it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.83it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.84it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.83it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.83it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.83it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.83it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.82it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.83it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.83it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.83it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.84it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.85it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.86it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.85it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:19,  1.86it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.85it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.82it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.81it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.81it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.81it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:17,  1.82it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.82it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.83it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.84it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.86it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:13,  1.86it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.86it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:12,  1.88it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.87it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.86it/s][A
Iteration:  79%|███████▉  | 79/100 [00:42<00:11,  1.85it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.85it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.85it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.86it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.87it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.85it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.85it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.86it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:06,  1.87it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.87it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.86it/s][A
Iteration:  90%|█████████ | 90/100 [00:48<00:05,  1.83it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.83it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.82it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.83it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.84it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.84it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.83it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.84it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.83it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.82it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.90it/s][A
[AEpoch:  37%|███▋      | 11/30 [10:03<17:17, 54.62s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:54,  1.81it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.83it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.84it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:51,  1.85it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.86it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:50,  1.85it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.84it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.84it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.84it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:49,  1.83it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:48,  1.83it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.86it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:46,  1.89it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:45,  1.90it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:44,  1.92it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:43,  1.93it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:43,  1.90it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:43,  1.87it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:43,  1.86it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.86it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:42,  1.85it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.85it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:41,  1.86it/s][A
Iteration:  24%|██▍       | 24/100 [00:12<00:41,  1.85it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:41,  1.82it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.82it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:40,  1.82it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.82it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:39,  1.81it/s][A tensor(0.6180, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8826, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2088, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4553, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.5405, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.6650, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3898, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0084, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9400, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0626, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0764, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5104, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0603, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3138, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0743, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1588, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0183, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0516, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0249, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7409, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2759, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1602, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0285, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7572, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0561, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0303, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0630, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4430, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5277, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1709, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0759, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2049, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3808, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4231, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8751, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2461, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0419, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2320, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0105, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1588, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1210, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0725, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0690, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1264, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3947, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0327, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0297, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0028, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1555, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0070, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0063, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0733, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1160, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1191, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0449, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0275, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0407, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1844, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.3682, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0031, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.3859, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0962, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0423, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0553, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5667, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0054, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1487, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2934, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0143, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0294, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0869, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0386, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0222, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9533, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0177, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0326, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1266, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1355, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0241, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0050, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0194, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1199, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0737, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2342, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0082, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0129, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0505, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0147, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.3724, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1554, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9519, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2867, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0035, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0732, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9776, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0371, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0594, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0478, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4834, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0711, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0751, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0130, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0154, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0263, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0686, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1558, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1322, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0091, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2471, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0151, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3275, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0214, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0080, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0929, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1288, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2520, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0167, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0026, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0654, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0671, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0038, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0107, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0749, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0801, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0084, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0571, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1732, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0408, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0286, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0042, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0507, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.81it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:38,  1.80it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.81it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:37,  1.79it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.81it/s][A
Iteration:  35%|███▌      | 35/100 [00:18<00:35,  1.83it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.84it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.85it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.84it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.84it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:33,  1.82it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.81it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:32,  1.80it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.82it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.82it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.82it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:29,  1.82it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.83it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.83it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.84it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.84it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.87it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:25,  1.89it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:24,  1.90it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:24,  1.91it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:23,  1.92it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:22,  1.92it/s][A
Iteration:  57%|█████▋    | 57/100 [00:30<00:22,  1.88it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.84it/s][A
Iteration:  59%|█████▉    | 59/100 [00:31<00:22,  1.83it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.82it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.82it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.82it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.83it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.82it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.82it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.83it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.83it/s][A
Iteration:  68%|██████▊   | 68/100 [00:36<00:17,  1.82it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.82it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.82it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.82it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.82it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.81it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.78it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.79it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.80it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.81it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:12,  1.82it/s][A
Iteration:  79%|███████▉  | 79/100 [00:42<00:11,  1.84it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.85it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.85it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.83it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.85it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.83it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.83it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.84it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.83it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.82it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:06,  1.80it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.79it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:05,  1.75it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.75it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.75it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.75it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.77it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.78it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.80it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.81it/s][A
Iteration:  99%|█████████▉| 99/100 [00:54<00:00,  1.80it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.87it/s][A
[AEpoch:  40%|████      | 12/30 [10:58<16:22, 54.60s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:54,  1.83it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.83it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.84it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:51,  1.85it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.83it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.82it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:51,  1.81it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.81it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:50,  1.81it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:49,  1.81it/s][A
Iteration:  11%|█         | 11/100 [00:06<00:48,  1.82it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:48,  1.83it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.83it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.84it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:45,  1.85it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.86it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:44,  1.87it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:43,  1.87it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:43,  1.86it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.83it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.81it/s][A
Iteration:  22%|██▏       | 22/100 [00:12<00:43,  1.80it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:42,  1.81it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.82it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:41,  1.82it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:39,  1.86it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:38,  1.88it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:37,  1.90it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:37,  1.91it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:36,  1.93it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:36,  1.89it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:36,  1.87it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.86it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:35,  1.85it/s][A
Iteration:  35%|███▌      | 35/100 [00:18<00:35,  1.85it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.84it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.83it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:34,  1.82it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.81it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:33,  1.82it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.82it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.82it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.82it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.82it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.83it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:29,  1.81it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:29,  1.80it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.81it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.82it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.84it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.85it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:25,  1.85it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.85it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:24,  1.86it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.86it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:23,  1.86it/s][A
Iteration:  57%|█████▋    | 57/100 [00:30<00:23,  1.85it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.85it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.85it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.86it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.85it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.85it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.84it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.83it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.83it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.87it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:17,  1.89it/s][A
Iteration:  68%|██████▊   | 68/100 [00:36<00:16,  1.89it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.89it/s][A
Iteration:  70%|███████   | 70/100 [00:37<00:15,  1.90it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.88it/s][A tensor(0.0249, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0945, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3050, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2334, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0038, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0286, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0245, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0368, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0073, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2458, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0199, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2240, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0057, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0861, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0309, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0893, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0089, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0068, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0024, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1763, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2834, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0061, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1472, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0538, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3434, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5932, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1195, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1186, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0601, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0689, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0593, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0256, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0026, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1100, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3382, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0336, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3618, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0092, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0744, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0070, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0543, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0173, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0398, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0271, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0414, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0395, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0795, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2337, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0037, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0394, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5879, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2382, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0081, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1813, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3840, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2029, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0464, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1303, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0269, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0281, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0026, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3683, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5496, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0277, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.2976, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2620, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0754, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0112, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0029, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0316, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1279, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1231, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0173, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0201, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0039, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0040, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5087, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0071, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0089, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4563, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0880, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2519, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3360, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0067, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0092, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2536, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1685, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0382, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0321, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2217, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0361, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1142, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.1816, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1381, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0596, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0031, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1441, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0129, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2248, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0055, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0072, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0056, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1146, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0031, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1117, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0208, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9741, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0692, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1503, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0184, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0077, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0478, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0124, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1700, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0794, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0082, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0108, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0022, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0064, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3145, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1316, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0204, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0836, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1723, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0065, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0127, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0368, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3367, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8793, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0038, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.86it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.85it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.84it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.84it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.83it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.84it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:12,  1.81it/s][A
Iteration:  79%|███████▉  | 79/100 [00:42<00:11,  1.82it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:11,  1.81it/s][A
Iteration:  81%|████████  | 81/100 [00:43<00:10,  1.80it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:10,  1.78it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.77it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:09,  1.76it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.77it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.78it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.78it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.79it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:06,  1.81it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.82it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.80it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.79it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.79it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.80it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.82it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.83it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.83it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.83it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.82it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.91it/s][A
[AEpoch:  43%|████▎     | 13/30 [11:52<15:27, 54.56s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:55,  1.80it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:54,  1.80it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:53,  1.81it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:53,  1.81it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:52,  1.81it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.82it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.84it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:49,  1.85it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.85it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.87it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:47,  1.87it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.87it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:46,  1.86it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.86it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:45,  1.87it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.85it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.82it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:45,  1.82it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.82it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.82it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.82it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.83it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:41,  1.84it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.83it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:41,  1.81it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.82it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.83it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.84it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.84it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.84it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.85it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:36,  1.84it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.83it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.83it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.83it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.83it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.83it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:34,  1.81it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:34,  1.79it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:33,  1.79it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.83it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.86it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:30,  1.89it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:29,  1.90it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:28,  1.91it/s][A
Iteration:  46%|████▌     | 46/100 [00:24<00:28,  1.90it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.89it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.85it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.83it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.81it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.83it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.84it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.84it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:24,  1.86it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.85it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:23,  1.84it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.82it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:23,  1.81it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.82it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.83it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.83it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.84it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.84it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.83it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.83it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.83it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:17,  1.84it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.84it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:17,  1.81it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.80it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:16,  1.80it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.81it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.83it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.84it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.85it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:12,  1.85it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.84it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.84it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.84it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.84it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.87it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.89it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:08,  1.91it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.92it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:07,  1.93it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.91it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:06,  1.88it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.83it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:06,  1.81it/s][A
Iteration:  90%|█████████ | 90/100 [00:48<00:05,  1.81it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.82it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.82it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.82it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.83it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.84it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.83it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.84it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.84it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.83it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.92it/s][A
[AEpoch:  47%|████▋     | 14/30 [12:46<14:31, 54.48s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:54,  1.82it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.82it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.83it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.83it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.84it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.84it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.85it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.83it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:50,  1.81it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:49,  1.80it/s][A
Iteration:  11%|█         | 11/100 [00:06<00:49,  1.82it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:48,  1.81it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.83it/s][A tensor(0.0049, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0084, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0254, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0366, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1527, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7202, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0867, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0237, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0631, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3672, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0178, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0960, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0407, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3251, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8042, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6408, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0203, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3598, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0112, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2897, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0502, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0040, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0640, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0075, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0149, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0236, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0264, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1930, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0091, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0505, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0077, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1610, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1200, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0350, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0787, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0122, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3086, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0629, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2251, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0338, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0358, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0064, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0045, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0390, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0278, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0102, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0121, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1923, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0039, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0333, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0224, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0914, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0022, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0066, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0099, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0085, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0225, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0126, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0034, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2147, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0935, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3077, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0628, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4270, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4859, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5369, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0048, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0063, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0445, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2259, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0810, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0113, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0758, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0083, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0063, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1462, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2919, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0605, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0127, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1740, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0110, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0099, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0095, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0178, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0246, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0186, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1486, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1275, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2250, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0180, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0213, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0281, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0024, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0044, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0056, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0027, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0189, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0180, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0802, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1815, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0923, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2128, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0084, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2197, device='cuda:0', grad_fn=<MeanBackward1>) tensor(3.1063, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0067, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1111, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0142, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2415, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4474, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0082, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0196, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0078, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0817, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0266, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0653, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0042, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1780, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0016, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.83it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.84it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.84it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.84it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.84it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.84it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.84it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:42,  1.87it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:41,  1.89it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:40,  1.91it/s][A
Iteration:  24%|██▍       | 24/100 [00:12<00:39,  1.92it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:38,  1.93it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:38,  1.93it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.87it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.84it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.83it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.83it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.82it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.83it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.82it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.83it/s][A
Iteration:  35%|███▌      | 35/100 [00:18<00:35,  1.85it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.86it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:33,  1.86it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.85it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.84it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.84it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:31,  1.85it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.85it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:30,  1.85it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.85it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:29,  1.84it/s][A
Iteration:  46%|████▌     | 46/100 [00:24<00:29,  1.84it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.84it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.84it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.84it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.84it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.84it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.84it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.84it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.82it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.82it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.82it/s][A
Iteration:  57%|█████▋    | 57/100 [00:30<00:23,  1.82it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:23,  1.82it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.82it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:22,  1.82it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.86it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.88it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:19,  1.90it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:18,  1.91it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:18,  1.92it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:17,  1.89it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:17,  1.87it/s][A
Iteration:  68%|██████▊   | 68/100 [00:36<00:17,  1.85it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.85it/s][A
Iteration:  70%|███████   | 70/100 [00:37<00:16,  1.86it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.86it/s][A
Iteration:  72%|███████▏  | 72/100 [00:38<00:15,  1.86it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.87it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.85it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.82it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.80it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.81it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:12,  1.82it/s][A
Iteration:  79%|███████▉  | 79/100 [00:42<00:11,  1.83it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.83it/s][A
Iteration:  81%|████████  | 81/100 [00:43<00:10,  1.83it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.83it/s][A
Iteration:  83%|████████▎ | 83/100 [00:44<00:09,  1.84it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.85it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.86it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.86it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.84it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.84it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.84it/s][A
Iteration:  90%|█████████ | 90/100 [00:48<00:05,  1.83it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.82it/s][A
Iteration:  92%|█████████▏| 92/100 [00:49<00:04,  1.83it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.81it/s][A
Iteration:  94%|█████████▍| 94/100 [00:50<00:03,  1.82it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.82it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.81it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.81it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.82it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.82it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.91it/s][A
[AEpoch:  50%|█████     | 15/30 [13:41<13:35, 54.40s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:54,  1.83it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.84it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.84it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.85it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.85it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:50,  1.86it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:49,  1.87it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:49,  1.85it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:48,  1.87it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.86it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:48,  1.85it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.84it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.83it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.83it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.83it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.83it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.82it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.83it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.84it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.83it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.83it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:43,  1.81it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:42,  1.81it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.82it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:41,  1.83it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.84it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.85it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:38,  1.86it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.86it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:37,  1.86it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.85it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:36,  1.84it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.82it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.82it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.81it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:35,  1.82it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.84it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.87it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:32,  1.89it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:31,  1.91it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:30,  1.92it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:30,  1.90it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:30,  1.86it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.85it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:29,  1.85it/s][A
Iteration:  46%|████▌     | 46/100 [00:24<00:29,  1.86it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.86it/s][A
Iteration:  48%|████▊     | 48/100 [00:25<00:27,  1.86it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.84it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.82it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.82it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.83it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.84it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.84it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.83it/s][A tensor(0.0390, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0980, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0162, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.3219, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0695, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0055, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0132, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0030, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0090, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0142, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0098, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0022, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0071, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0091, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1411, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0031, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0771, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.3330, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0588, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0411, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0037, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0027, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0016, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0055, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0042, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.9203, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0144, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0027, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0280, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0445, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0734, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0578, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0149, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1239, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0111, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0079, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5793, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0108, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1548, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0054, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0136, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0228, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0039, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0091, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0280, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0223, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0066, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0972, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0040, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0029, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1492, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0068, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0411, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0134, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0258, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2160, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0047, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1033, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1153, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1604, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0094, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0024, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0257, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0166, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1387, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.2446, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0508, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0145, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1437, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0034, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0066, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2611, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0043, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0028, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0209, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0460, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0045, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0042, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0053, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0049, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0369, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0044, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0693, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0067, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0052, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.8951, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0254, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0024, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0185, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0118, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1948, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0073, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0212, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0112, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0094, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0149, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.1219, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0941, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0483, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0187, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0518, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0047, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0092, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0034, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0189, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0183, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0539, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.81it/s][A
Iteration:  57%|█████▋    | 57/100 [00:30<00:23,  1.80it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:23,  1.80it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.82it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.83it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.81it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:21,  1.79it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.78it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:20,  1.78it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.79it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:19,  1.77it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.76it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:18,  1.77it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:17,  1.78it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.78it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:16,  1.79it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.80it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:15,  1.79it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.77it/s][A
Iteration:  75%|███████▌  | 75/100 [00:41<00:14,  1.77it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.79it/s][A
Iteration:  77%|███████▋  | 77/100 [00:42<00:12,  1.83it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.87it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.89it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.91it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.88it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.83it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.80it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.80it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.80it/s][A
Iteration:  86%|████████▌ | 86/100 [00:47<00:07,  1.81it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.83it/s][A
Iteration:  88%|████████▊ | 88/100 [00:48<00:06,  1.84it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.85it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.84it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.84it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.85it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.84it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.83it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.82it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.82it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.82it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.84it/s][A
Iteration:  99%|█████████▉| 99/100 [00:54<00:00,  1.84it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.91it/s][A
[AEpoch:  53%|█████▎    | 16/30 [14:35<12:42, 54.44s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:53,  1.86it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.84it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.84it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.84it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.84it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.83it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.84it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.83it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.83it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:49,  1.83it/s][A
Iteration:  11%|█         | 11/100 [00:06<00:48,  1.83it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.83it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.83it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:47,  1.82it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.82it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:46,  1.82it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.84it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.84it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.83it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.83it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:42,  1.84it/s][A
Iteration:  22%|██▏       | 22/100 [00:12<00:42,  1.84it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:41,  1.83it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.82it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:40,  1.83it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.84it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.84it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.84it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:39,  1.82it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.82it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.82it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.81it/s][A
Iteration:  33%|███▎      | 33/100 [00:18<00:36,  1.82it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.82it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.83it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.84it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.85it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.85it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.83it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.83it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.83it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.83it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.83it/s][A
Iteration:  44%|████▍     | 44/100 [00:24<00:30,  1.83it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:29,  1.84it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:29,  1.84it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:29,  1.83it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.83it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.83it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.82it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:27,  1.79it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.81it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.83it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:24,  1.87it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:23,  1.89it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:23,  1.91it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:22,  1.89it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.85it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.85it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.85it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.85it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.84it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.83it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.81it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.82it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.83it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.81it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.81it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:17,  1.81it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.81it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.83it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.84it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.85it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.85it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.84it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.83it/s][A
Iteration:  77%|███████▋  | 77/100 [00:42<00:12,  1.83it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:12,  1.83it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.84it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.85it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.86it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.86it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.86it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.82it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.82it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.80it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.80it/s][A
Iteration:  88%|████████▊ | 88/100 [00:48<00:06,  1.81it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:06,  1.82it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.82it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.83it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.84it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.85it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.85it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.85it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.85it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.84it/s][A tensor(0.0258, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0127, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0260, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0058, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0028, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0368, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1322, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0317, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0293, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4366, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0021, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0045, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2388, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0024, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0239, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2335, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1587, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1735, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0066, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0016, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0907, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0067, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0154, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3278, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0163, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1147, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0054, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0083, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0099, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0048, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0054, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2221, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2294, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0189, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5288, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3107, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0060, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0212, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0062, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0022, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2905, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0082, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0064, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0684, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0773, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2548, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0127, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0942, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0081, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0654, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0646, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1752, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0208, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0121, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0584, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0237, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0036, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0027, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0137, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0546, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0316, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0257, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0305, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0026, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0339, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7322, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0042, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1713, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0137, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0034, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0033, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0034, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0455, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2684, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0087, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0894, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0726, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4287, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6537, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0036, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0037, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1093, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3447, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0552, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0368, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0031, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0666, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0098, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0027, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1663, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0104, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0119, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0056, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0426, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1553, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0037, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.84it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.83it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.90it/s][A
[AEpoch:  57%|█████▋    | 17/30 [15:30<11:47, 54.45s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:53,  1.85it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.85it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.84it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.83it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:52,  1.82it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.83it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.84it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.84it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.85it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.84it/s][A
Iteration:  11%|█         | 11/100 [00:06<00:48,  1.82it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:48,  1.83it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.83it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:47,  1.82it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.82it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:46,  1.82it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.83it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.84it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:43,  1.85it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.85it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.83it/s][A
Iteration:  22%|██▏       | 22/100 [00:12<00:42,  1.84it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:42,  1.82it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.83it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:41,  1.82it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.82it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.83it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.84it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.83it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.83it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.83it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.83it/s][A
Iteration:  33%|███▎      | 33/100 [00:18<00:36,  1.83it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.83it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.83it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.83it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.84it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.83it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.84it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.84it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.83it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.81it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.81it/s][A
Iteration:  44%|████▍     | 44/100 [00:24<00:31,  1.81it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.82it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:29,  1.83it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.84it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.85it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.85it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.83it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:27,  1.81it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.82it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:26,  1.80it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.80it/s][A
Iteration:  55%|█████▌    | 55/100 [00:30<00:24,  1.81it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.83it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.83it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.84it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.83it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:22,  1.80it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.79it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:21,  1.79it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.79it/s][A
Iteration:  64%|██████▍   | 64/100 [00:35<00:20,  1.79it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.79it/s][A
Iteration:  66%|██████▌   | 66/100 [00:36<00:18,  1.80it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.80it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.81it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:17,  1.82it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.82it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.82it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.82it/s][A
Iteration:  73%|███████▎  | 73/100 [00:40<00:14,  1.82it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.82it/s][A
Iteration:  75%|███████▌  | 75/100 [00:41<00:13,  1.83it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.83it/s][A
Iteration:  77%|███████▋  | 77/100 [00:42<00:12,  1.82it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:12,  1.82it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.81it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:11,  1.81it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.82it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.82it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.83it/s][A
Iteration:  84%|████████▍ | 84/100 [00:46<00:08,  1.83it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.83it/s][A
Iteration:  86%|████████▌ | 86/100 [00:47<00:07,  1.81it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.81it/s][A
Iteration:  88%|████████▊ | 88/100 [00:48<00:06,  1.81it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:06,  1.83it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.84it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.84it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.83it/s][A
Iteration:  93%|█████████▎| 93/100 [00:51<00:03,  1.82it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.83it/s][A
Iteration:  95%|█████████▌| 95/100 [00:52<00:02,  1.83it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.82it/s][A
Iteration:  97%|█████████▋| 97/100 [00:53<00:01,  1.85it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.87it/s][A
Iteration:  99%|█████████▉| 99/100 [00:54<00:00,  1.87it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.98it/s][A
[AEpoch:  60%|██████    | 18/30 [16:24<10:54, 54.52s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:50,  1.95it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:50,  1.94it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:50,  1.91it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:51,  1.87it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.85it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.83it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.84it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.84it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.84it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:49,  1.83it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:48,  1.84it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.83it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.84it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:47,  1.82it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.82it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:46,  1.81it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:46,  1.79it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:45,  1.79it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:45,  1.79it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:44,  1.80it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.80it/s][A
Iteration:  22%|██▏       | 22/100 [00:12<00:43,  1.80it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:42,  1.81it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:42,  1.80it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:41,  1.80it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:41,  1.80it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:40,  1.80it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.80it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:39,  1.79it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:39,  1.79it/s][A
Iteration:  31%|███       | 31/100 [00:17<00:38,  1.79it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:38,  1.79it/s][A
Iteration:  33%|███▎      | 33/100 [00:18<00:37,  1.80it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.81it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.83it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:35,  1.82it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.82it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:34,  1.81it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.82it/s][A tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0101, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0391, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0024, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0671, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9835, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9370, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0028, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0052, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9687, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0164, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0444, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0525, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0038, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0025, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0280, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0081, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2452, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0035, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0796, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1372, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0132, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0021, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0054, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0029, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0179, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0119, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7821, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0480, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1126, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0236, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3295, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1674, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0043, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0031, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7936, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0092, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0025, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0885, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1166, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0029, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1806, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0100, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0031, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0139, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0285, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0028, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0114, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1739, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0041, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0523, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0867, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1412, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0180, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2871, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1797, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0130, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0034, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0886, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0082, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0636, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1108, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0535, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8704, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0431, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0074, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0058, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0462, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0066, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1690, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0823, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0026, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0079, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0037, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2303, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0290, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0193, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0034, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0034, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0171, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0037, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  40%|████      | 40/100 [00:22<00:32,  1.82it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.82it/s][A
Iteration:  42%|████▏     | 42/100 [00:23<00:31,  1.82it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.81it/s][A
Iteration:  44%|████▍     | 44/100 [00:24<00:31,  1.78it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.78it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:30,  1.78it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:29,  1.80it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.81it/s][A
Iteration:  49%|████▉     | 49/100 [00:27<00:27,  1.83it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.84it/s][A
Iteration:  51%|█████     | 51/100 [00:28<00:26,  1.82it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.83it/s][A
Iteration:  53%|█████▎    | 53/100 [00:29<00:25,  1.82it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.83it/s][A
Iteration:  55%|█████▌    | 55/100 [00:30<00:24,  1.83it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.83it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.82it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:23,  1.82it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.84it/s][A
Iteration:  60%|██████    | 60/100 [00:33<00:21,  1.84it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.86it/s][A
Iteration:  62%|██████▏   | 62/100 [00:34<00:20,  1.85it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.84it/s][A
Iteration:  64%|██████▍   | 64/100 [00:35<00:19,  1.83it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.83it/s][A
Iteration:  66%|██████▌   | 66/100 [00:36<00:18,  1.84it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:17,  1.83it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.83it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.83it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.83it/s][A
Iteration:  71%|███████   | 71/100 [00:39<00:15,  1.84it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.82it/s][A
Iteration:  73%|███████▎  | 73/100 [00:40<00:14,  1.82it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.83it/s][A
Iteration:  75%|███████▌  | 75/100 [00:41<00:13,  1.81it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.81it/s][A
Iteration:  77%|███████▋  | 77/100 [00:42<00:12,  1.80it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:12,  1.79it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.79it/s][A
Iteration:  80%|████████  | 80/100 [00:44<00:11,  1.79it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.80it/s][A
Iteration:  82%|████████▏ | 82/100 [00:45<00:10,  1.78it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.79it/s][A
Iteration:  84%|████████▍ | 84/100 [00:46<00:08,  1.80it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.80it/s][A
Iteration:  86%|████████▌ | 86/100 [00:47<00:07,  1.80it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.81it/s][A
Iteration:  88%|████████▊ | 88/100 [00:48<00:06,  1.82it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:06,  1.82it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.81it/s][A
Iteration:  91%|█████████ | 91/100 [00:50<00:04,  1.81it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.81it/s][A
Iteration:  93%|█████████▎| 93/100 [00:51<00:03,  1.82it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.82it/s][A
Iteration:  95%|█████████▌| 95/100 [00:52<00:02,  1.83it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.83it/s][A
Iteration:  97%|█████████▋| 97/100 [00:53<00:01,  1.85it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.82it/s][A
Iteration:  99%|█████████▉| 99/100 [00:54<00:00,  1.82it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.90it/s][A
[AEpoch:  63%|██████▎   | 19/30 [17:19<10:01, 54.65s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:53,  1.86it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:52,  1.87it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.86it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:51,  1.85it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.85it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:50,  1.85it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.84it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:49,  1.85it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.85it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.85it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:48,  1.84it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.84it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.84it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:47,  1.83it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.81it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:46,  1.83it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.84it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.84it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.84it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.83it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.83it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.83it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:42,  1.83it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.82it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:41,  1.83it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.83it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.83it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.83it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.84it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:37,  1.85it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.85it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:36,  1.85it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.86it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:35,  1.86it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.85it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.84it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.83it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.84it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.84it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.84it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.84it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.84it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.83it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.82it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.83it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:29,  1.85it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.86it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.85it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:28,  1.81it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.82it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.84it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:25,  1.85it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.86it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:24,  1.86it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.82it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.80it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.80it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:23,  1.81it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.82it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.83it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.83it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.85it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:19,  1.86it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.85it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:18,  1.86it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.86it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:17,  1.84it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.81it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:17,  1.82it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.82it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:16,  1.81it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.81it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.82it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.83it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.83it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.84it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.83it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.84it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.84it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.85it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.86it/s][A tensor(0.0024, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1823, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0113, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0021, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0229, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2611, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2698, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0400, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0049, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0402, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0024, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0577, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3310, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5071, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0477, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0370, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0306, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0278, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0070, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0024, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0320, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0047, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0280, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1254, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0464, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5242, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0025, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0564, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0330, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7241, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0755, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0506, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0035, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4420, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0055, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0106, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1102, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0087, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0031, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0367, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0695, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0047, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0021, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1056, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0036, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0094, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0082, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0035, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0026, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0418, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0100, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0130, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0597, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0564, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0030, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0089, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1729, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0024, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0016, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0028, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1339, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0174, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0069, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0077, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0214, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0116, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0052, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0233, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.8512, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0038, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.84it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.81it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.81it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.82it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.82it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.84it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.84it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.84it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.84it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.83it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.82it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.83it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.85it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.84it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.83it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.82it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.84it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.83it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.90it/s][A
[AEpoch:  67%|██████▋   | 20/30 [18:14<09:05, 54.58s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:54,  1.82it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.82it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:53,  1.83it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.84it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.84it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.84it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.84it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.84it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.84it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:49,  1.83it/s][A
Iteration:  11%|█         | 11/100 [00:06<00:49,  1.81it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:48,  1.80it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:48,  1.81it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.84it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:45,  1.86it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:44,  1.89it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:43,  1.91it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:43,  1.89it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:43,  1.87it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.85it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:42,  1.85it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.84it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:42,  1.82it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.82it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:41,  1.82it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.81it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:40,  1.82it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.82it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:39,  1.82it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.82it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.82it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.82it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.81it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.81it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.81it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:35,  1.83it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.82it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:34,  1.82it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.82it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.83it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.82it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.84it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:30,  1.85it/s][A
Iteration:  44%|████▍     | 44/100 [00:24<00:30,  1.82it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.80it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:30,  1.80it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:29,  1.81it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.82it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:28,  1.82it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.82it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.82it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.82it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.81it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.81it/s][A
Iteration:  55%|█████▌    | 55/100 [00:30<00:24,  1.82it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.82it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.83it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.84it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.83it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:22,  1.81it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.82it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.84it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.82it/s][A
Iteration:  64%|██████▍   | 64/100 [00:35<00:19,  1.82it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.84it/s][A
Iteration:  66%|██████▌   | 66/100 [00:36<00:18,  1.85it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:17,  1.84it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.83it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:17,  1.82it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.83it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.83it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.83it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.82it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.83it/s][A
Iteration:  75%|███████▌  | 75/100 [00:41<00:13,  1.83it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.84it/s][A
Iteration:  77%|███████▋  | 77/100 [00:42<00:12,  1.83it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:12,  1.83it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.82it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.83it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.82it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.83it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.83it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.83it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.83it/s][A
Iteration:  86%|████████▌ | 86/100 [00:47<00:07,  1.84it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.83it/s][A
Iteration:  88%|████████▊ | 88/100 [00:48<00:06,  1.85it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.88it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.89it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.91it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.93it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.89it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.86it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.83it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.83it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.83it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.84it/s][A
Iteration:  99%|█████████▉| 99/100 [00:54<00:00,  1.84it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.93it/s][A
[AEpoch:  70%|███████   | 21/30 [19:08<08:10, 54.55s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:53,  1.83it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.84it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.85it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:51,  1.85it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.84it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.83it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.83it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.84it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.85it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.85it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:48,  1.85it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.84it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.84it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.84it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.85it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.85it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.84it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.84it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.83it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.84it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:42,  1.84it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.82it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:42,  1.82it/s][A tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0578, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0079, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1334, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0176, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1087, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2857, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0389, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0072, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0227, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1291, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0030, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5241, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0057, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0064, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0087, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0113, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0022, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0460, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3675, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0040, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1508, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0031, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0306, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0055, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0060, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0133, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0109, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0043, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0113, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0093, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0406, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0031, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0800, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0026, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0029, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0583, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1838, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0077, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0039, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0016, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0097, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2274, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0030, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2260, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1556, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0519, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1382, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0234, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.8130, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0150, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0341, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0767, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0391, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0099, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0224, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0073, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0025, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0021, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0988, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0043, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0461, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0363, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0022, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0865, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0036, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6113, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0173, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0379, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0029, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0064, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0098, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0021, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.82it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:40,  1.83it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.83it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.83it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:38,  1.87it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:37,  1.89it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:36,  1.91it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:35,  1.92it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:35,  1.90it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:35,  1.89it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:35,  1.88it/s][A
Iteration:  35%|███▌      | 35/100 [00:18<00:34,  1.86it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.85it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.84it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.83it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.84it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.84it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.83it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.82it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.82it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.82it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.82it/s][A
Iteration:  46%|████▌     | 46/100 [00:24<00:29,  1.82it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:29,  1.82it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.82it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.82it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.83it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.84it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.83it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.84it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.81it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:25,  1.78it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.79it/s][A
Iteration:  57%|█████▋    | 57/100 [00:30<00:23,  1.81it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.83it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.85it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.82it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.82it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:21,  1.81it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.81it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.82it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.82it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.83it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.83it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.84it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.83it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.81it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.81it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.82it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.82it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.82it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.82it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.83it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.84it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.85it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.86it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.86it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.81it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:10,  1.79it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.79it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.80it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.81it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.83it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.84it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.85it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.84it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.83it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.83it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.84it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.85it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.86it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.86it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.86it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.85it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.84it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.82it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.89it/s][A
[AEpoch:  73%|███████▎  | 22/30 [20:02<07:16, 54.51s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:54,  1.81it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.82it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.84it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.84it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.84it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.83it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.84it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:49,  1.84it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.83it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:49,  1.83it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:48,  1.84it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.84it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:48,  1.81it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:47,  1.80it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:47,  1.79it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:46,  1.80it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.82it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.83it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.83it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.84it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.83it/s][A
Iteration:  22%|██▏       | 22/100 [00:12<00:42,  1.83it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:42,  1.82it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.83it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:40,  1.85it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:39,  1.86it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.87it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:38,  1.85it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.83it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.84it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.82it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.80it/s][A
Iteration:  33%|███▎      | 33/100 [00:18<00:37,  1.78it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:37,  1.78it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:36,  1.77it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:36,  1.75it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:35,  1.77it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:34,  1.82it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:32,  1.86it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:31,  1.88it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:31,  1.88it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:30,  1.87it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:30,  1.84it/s][A
Iteration:  44%|████▍     | 44/100 [00:24<00:30,  1.83it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.81it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:29,  1.82it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:29,  1.82it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.83it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:28,  1.82it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.83it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.82it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.83it/s][A
Iteration:  53%|█████▎    | 53/100 [00:29<00:25,  1.82it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.83it/s][A
Iteration:  55%|█████▌    | 55/100 [00:30<00:24,  1.82it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.82it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.82it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.83it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.84it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.85it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.86it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.86it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:19,  1.87it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.87it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:18,  1.86it/s][A tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0808, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1307, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0138, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0043, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0525, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5825, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0559, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0054, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0026, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0344, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3818, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0284, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0045, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1320, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0439, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0033, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1468, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0720, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0049, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0297, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5752, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0072, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0139, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0111, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1488, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0074, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0136, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2486, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0064, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0065, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0118, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0989, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0068, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0504, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0054, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0129, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0030, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0177, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0041, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1021, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0049, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0268, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0074, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1547, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0047, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0280, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0031, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0063, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0075, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0061, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0350, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0022, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0786, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0220, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0033, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4354, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0385, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1088, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0096, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0292, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3566, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6342, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0029, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  66%|██████▌   | 66/100 [00:36<00:18,  1.87it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:17,  1.86it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.85it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.85it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.85it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.83it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.84it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.82it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.82it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.81it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.82it/s][A
Iteration:  77%|███████▋  | 77/100 [00:42<00:12,  1.83it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.86it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.89it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.91it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.88it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.89it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.87it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.86it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.86it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.86it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:06,  1.86it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.87it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.86it/s][A
Iteration:  90%|█████████ | 90/100 [00:48<00:05,  1.85it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.85it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.86it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.86it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.87it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.84it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.83it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.83it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.84it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.84it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.93it/s][A
[AEpoch:  77%|███████▋  | 23/30 [20:57<06:21, 54.46s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:54,  1.81it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.81it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:53,  1.82it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.83it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:52,  1.82it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:52,  1.81it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:51,  1.81it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.81it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:50,  1.81it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:49,  1.81it/s][A
Iteration:  11%|█         | 11/100 [00:06<00:48,  1.82it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:48,  1.82it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.82it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:47,  1.83it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.83it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.83it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.83it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.84it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:43,  1.87it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:42,  1.89it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:41,  1.91it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:40,  1.92it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:40,  1.92it/s][A
Iteration:  24%|██▍       | 24/100 [00:12<00:39,  1.91it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:39,  1.90it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:39,  1.89it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.86it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.82it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:39,  1.81it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.81it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.83it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.82it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.85it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:35,  1.84it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.83it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:35,  1.83it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.83it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.84it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.85it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.85it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:31,  1.85it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.82it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.80it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:31,  1.80it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.81it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:29,  1.80it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:29,  1.80it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.82it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:28,  1.81it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.81it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.83it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.84it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.83it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.84it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.82it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.82it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.82it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:23,  1.81it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.81it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.82it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.83it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.83it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.83it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.83it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.84it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.84it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.83it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.83it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.84it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.84it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.83it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.83it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.83it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.83it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.84it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.82it/s][A
Iteration:  77%|███████▋  | 77/100 [00:42<00:12,  1.81it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:12,  1.80it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.82it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.83it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.84it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.84it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.85it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.85it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.84it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.83it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.83it/s][A
Iteration:  88%|████████▊ | 88/100 [00:48<00:06,  1.83it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.84it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.84it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.85it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.85it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.84it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.85it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.85it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.86it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.88it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.90it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.89it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.96it/s][A
[AEpoch:  80%|████████  | 24/30 [21:51<05:26, 54.42s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:53,  1.85it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:52,  1.86it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.86it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:51,  1.86it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:50,  1.86it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:50,  1.86it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.85it/s][A tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0122, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3354, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0603, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0083, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0368, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1313, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4468, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0034, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0060, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0030, device='cuda:0', grad_fn=<MeanBackward1>) tensor(2.4603, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0068, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0421, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0783, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2286, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0085, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0060, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4605, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0039, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0915, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0058, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0024, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0044, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.6891, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0067, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0132, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0039, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1296, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0029, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2199, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0301, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0039, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0245, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2662, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1446, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0952, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0075, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0169, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0107, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0067, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.6980, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0021, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0027, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2964, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0324, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0141, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0036, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0053, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0057, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0061, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0073, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:   8%|▊         | 8/100 [00:04<00:49,  1.85it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.84it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.84it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:48,  1.85it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.85it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:46,  1.86it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.87it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:45,  1.86it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.85it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.84it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.83it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.84it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.84it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:42,  1.85it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.85it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:41,  1.85it/s][A
Iteration:  24%|██▍       | 24/100 [00:12<00:41,  1.84it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:40,  1.84it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.84it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.85it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.83it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:39,  1.81it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.81it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:38,  1.81it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.82it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.83it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:35,  1.84it/s][A
Iteration:  35%|███▌      | 35/100 [00:18<00:35,  1.85it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.85it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.84it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.84it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.84it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:33,  1.81it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.83it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.84it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.84it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.83it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.83it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:29,  1.83it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.84it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.85it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.84it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.83it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.83it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.83it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.85it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:24,  1.86it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.83it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:23,  1.83it/s][A
Iteration:  57%|█████▋    | 57/100 [00:30<00:23,  1.82it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:23,  1.82it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.81it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.83it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.84it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:21,  1.81it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.82it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.82it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.82it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.83it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.83it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.83it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.83it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.83it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.83it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.84it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.84it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.85it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.85it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.84it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.81it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:12,  1.80it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.81it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.82it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.83it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.84it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.85it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.87it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.84it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.82it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.83it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.84it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.85it/s][A
Iteration:  90%|█████████ | 90/100 [00:48<00:05,  1.85it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.86it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.86it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.87it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.87it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.88it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.88it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.88it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.87it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.86it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.93it/s][A
[AEpoch:  83%|████████▎ | 25/30 [22:45<04:31, 54.38s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:54,  1.83it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.83it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:53,  1.82it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.82it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.85it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:50,  1.87it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:49,  1.89it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:48,  1.90it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:48,  1.88it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.86it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:48,  1.85it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.84it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.83it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:47,  1.82it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:47,  1.80it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:46,  1.80it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.81it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.83it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:43,  1.84it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.83it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.83it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.83it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:42,  1.83it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.83it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:40,  1.84it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.84it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.84it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.83it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:39,  1.82it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.81it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:38,  1.80it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.81it/s][A
Iteration:  33%|███▎      | 33/100 [00:18<00:37,  1.80it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.81it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.81it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:35,  1.81it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.81it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:34,  1.81it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.82it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.82it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.83it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.83it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.83it/s][A
Iteration:  44%|████▍     | 44/100 [00:24<00:29,  1.87it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:29,  1.87it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:28,  1.87it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.88it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:27,  1.90it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:26,  1.89it/s][A tensor(0.0067, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0031, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0033, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.5648, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0183, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0381, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0227, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0044, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0147, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0130, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0021, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0027, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2578, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0041, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0049, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0532, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.2309, device='cuda:0', grad_fn=<MeanBackward1>) tensor(7.4373e-06, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0043, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0080, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0016, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0059, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0217, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0267, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1210, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0040, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0184, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0082, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0137, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0042, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1765, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0255, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2603, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1879, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.7262, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0044, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0022, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0144, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0704, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0147, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1327, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0302, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0026, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0027, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0037, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0046, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0076, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1496, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0471, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0030, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0050, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0147, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1993, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0139, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7419, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0059, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0393, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0064, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0083, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0204, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0111, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0034, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0163, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  50%|█████     | 50/100 [00:27<00:26,  1.87it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.86it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:25,  1.86it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.86it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:24,  1.87it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.86it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.82it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.83it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.84it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.84it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.83it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.82it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.82it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.81it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.81it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.82it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.81it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.82it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.82it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:17,  1.82it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.82it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:16,  1.81it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.81it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.83it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.84it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.85it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.85it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.86it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.85it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.85it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.84it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.84it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.84it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.84it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.85it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.84it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.84it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.85it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.84it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.84it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.85it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.85it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.86it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.85it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.85it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.85it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.83it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.83it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.84it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.83it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.90it/s][A
[AEpoch:  87%|████████▋ | 26/30 [23:40<03:37, 54.38s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:54,  1.82it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:53,  1.83it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.84it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:51,  1.85it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.85it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:50,  1.85it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.85it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:49,  1.86it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.86it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:49,  1.83it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:49,  1.81it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:48,  1.81it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.83it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.85it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.85it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.84it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.84it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.84it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:43,  1.87it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:42,  1.89it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:41,  1.89it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:41,  1.89it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:40,  1.90it/s][A
Iteration:  24%|██▍       | 24/100 [00:12<00:40,  1.88it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:40,  1.86it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.85it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.84it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:38,  1.86it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.85it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.82it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.83it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.83it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.83it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.83it/s][A
Iteration:  35%|███▌      | 35/100 [00:18<00:35,  1.82it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:35,  1.81it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.82it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.83it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:33,  1.84it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.84it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:32,  1.82it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.82it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.81it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.82it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.82it/s][A
Iteration:  46%|████▌     | 46/100 [00:24<00:29,  1.83it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.84it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.85it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.85it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.85it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.84it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:25,  1.85it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.85it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:24,  1.85it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.85it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:23,  1.84it/s][A
Iteration:  57%|█████▋    | 57/100 [00:30<00:23,  1.84it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.84it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.85it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.86it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.84it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.83it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.84it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.85it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:18,  1.85it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.84it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.82it/s][A
Iteration:  68%|██████▊   | 68/100 [00:36<00:17,  1.83it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:16,  1.83it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.83it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.83it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.83it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.82it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.82it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.82it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.83it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.84it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.85it/s][A
Iteration:  79%|███████▉  | 79/100 [00:42<00:11,  1.85it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.84it/s][A
Iteration:  81%|████████  | 81/100 [00:43<00:10,  1.83it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.84it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.82it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.83it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.84it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.83it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.83it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.83it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:06,  1.83it/s][A
Iteration:  90%|█████████ | 90/100 [00:48<00:05,  1.83it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.83it/s][A tensor(0.0021, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0231, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0114, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3828, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0022, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0034, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0354, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0081, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0036, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0040, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0533, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0578, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0196, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0157, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0025, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0053, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0084, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0062, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0021, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0033, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0112, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0016, device='cuda:0', grad_fn=<MeanBackward1>) tensor(4.7204e-06, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0504, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0088, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0036, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0299, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0025, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0085, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0078, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0139, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4026, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0036, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0568, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0057, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0030, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0016, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0047, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1580, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1076, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0068, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0213, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0303, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0062, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0030, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0060, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0051, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0071, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0026, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0174, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0220, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0066, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0022, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0064, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0724, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0204, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0885, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0138, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0639, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0481, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0088, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0080, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0458, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0103, device='cuda:0', grad_fn=<MeanBackward1>) tensor(5.5663e-06, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0276, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0022, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0045, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2771, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0145, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.84it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.84it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.84it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.86it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.88it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.90it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.92it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.92it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.99it/s][A
[AEpoch:  90%|█████████ | 27/30 [24:34<02:42, 54.30s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:53,  1.86it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:52,  1.86it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.86it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:51,  1.85it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:51,  1.83it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.82it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.83it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.83it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.82it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:49,  1.82it/s][A
Iteration:  11%|█         | 11/100 [00:06<00:48,  1.83it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:47,  1.84it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.85it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.84it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:45,  1.85it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.84it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:44,  1.85it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.83it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.84it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.84it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:42,  1.85it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:42,  1.85it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:41,  1.85it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:40,  1.86it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:40,  1.86it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:39,  1.87it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.87it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.84it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.83it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.81it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:38,  1.81it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.82it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.82it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.82it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:34,  1.86it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:33,  1.88it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:33,  1.90it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:32,  1.92it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:31,  1.92it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:31,  1.89it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:31,  1.88it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.87it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:30,  1.86it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.85it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.83it/s][A
Iteration:  46%|████▌     | 46/100 [00:24<00:29,  1.82it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.83it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.82it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:28,  1.81it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.82it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.82it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.82it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.83it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:24,  1.84it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.85it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:23,  1.85it/s][A
Iteration:  57%|█████▋    | 57/100 [00:30<00:23,  1.85it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:22,  1.85it/s][A
Iteration:  59%|█████▉    | 59/100 [00:31<00:22,  1.83it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.83it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.83it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.83it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.83it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.84it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.83it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.82it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.81it/s][A
Iteration:  68%|██████▊   | 68/100 [00:36<00:17,  1.81it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:17,  1.81it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.82it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.83it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.83it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.83it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.84it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.85it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.84it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.86it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.84it/s][A
Iteration:  79%|███████▉  | 79/100 [00:42<00:11,  1.84it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.83it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.82it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.82it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.83it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.84it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.85it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.83it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.81it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.82it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:06,  1.82it/s][A
Iteration:  90%|█████████ | 90/100 [00:48<00:05,  1.83it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.84it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.84it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.85it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.86it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.84it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.84it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.83it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.84it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.84it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.93it/s][A
[AEpoch:  93%|█████████▎| 28/30 [25:28<01:48, 54.30s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:53,  1.85it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:52,  1.86it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:52,  1.83it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:52,  1.82it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:52,  1.82it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.82it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:50,  1.83it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.83it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.83it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:48,  1.87it/s][A
Iteration:  11%|█         | 11/100 [00:05<00:47,  1.89it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:46,  1.91it/s][A
Iteration:  13%|█▎        | 13/100 [00:06<00:45,  1.90it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:44,  1.91it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:44,  1.90it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.86it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:44,  1.85it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.85it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.81it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:44,  1.80it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:44,  1.79it/s][A
Iteration:  22%|██▏       | 22/100 [00:11<00:43,  1.80it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:42,  1.81it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.82it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:40,  1.84it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.85it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:39,  1.84it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.84it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.84it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.83it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.84it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:37,  1.83it/s][A
Iteration:  33%|███▎      | 33/100 [00:17<00:36,  1.83it/s][A tensor(0.0036, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0364, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0093, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0076, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0060, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0022, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0918, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0056, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0024, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0252, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0139, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0057, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0041, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0052, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1689, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0818, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0016, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0028, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0046, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0028, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0479, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0021, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.7372, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0179, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0820, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3823, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0103, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0023, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0040, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2492, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1910, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0358, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0026, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0299, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1573, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0511, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0282, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0043, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0081, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0139, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0032, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0046, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0014, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0068, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0078, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0077, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0430, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0951, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0022, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0029, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0033, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0054, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0353, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0090, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0031, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0040, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0752, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  34%|███▍      | 34/100 [00:18<00:36,  1.83it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:35,  1.84it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.84it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:34,  1.85it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.86it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:32,  1.87it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.87it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:31,  1.87it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.87it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.84it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.83it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.83it/s][A
Iteration:  46%|████▌     | 46/100 [00:24<00:29,  1.83it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.83it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.84it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.83it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.84it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.82it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.82it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.83it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:24,  1.84it/s][A
Iteration:  55%|█████▌    | 55/100 [00:29<00:24,  1.85it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:23,  1.86it/s][A
Iteration:  57%|█████▋    | 57/100 [00:30<00:23,  1.82it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:23,  1.81it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.80it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:22,  1.79it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.79it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:21,  1.79it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.80it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.82it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.83it/s][A
Iteration:  66%|██████▌   | 66/100 [00:35<00:18,  1.83it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:18,  1.82it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.83it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:17,  1.82it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.82it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:16,  1.81it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.82it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.82it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.83it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.84it/s][A
Iteration:  76%|███████▌  | 76/100 [00:41<00:13,  1.84it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.84it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.84it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.83it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.83it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.83it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.84it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.84it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.84it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.87it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.89it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:06,  1.91it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.93it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:05,  1.93it/s][A
Iteration:  90%|█████████ | 90/100 [00:48<00:05,  1.91it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:04,  1.88it/s][A
Iteration:  92%|█████████▏| 92/100 [00:49<00:04,  1.86it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.85it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.83it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.81it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.82it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.81it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.80it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.80it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  1.89it/s][A
[AEpoch:  97%|█████████▋| 29/30 [26:23<00:54, 54.31s/it]
Iteration:   0%|          | 0/100 [00:00<?, ?it/s][A
Iteration:   1%|          | 1/100 [00:00<00:56,  1.74it/s][A
Iteration:   2%|▏         | 2/100 [00:01<00:55,  1.76it/s][A
Iteration:   3%|▎         | 3/100 [00:01<00:54,  1.77it/s][A
Iteration:   4%|▍         | 4/100 [00:02<00:53,  1.78it/s][A
Iteration:   5%|▌         | 5/100 [00:02<00:52,  1.80it/s][A
Iteration:   6%|▌         | 6/100 [00:03<00:51,  1.81it/s][A
Iteration:   7%|▋         | 7/100 [00:03<00:51,  1.82it/s][A
Iteration:   8%|▊         | 8/100 [00:04<00:50,  1.82it/s][A
Iteration:   9%|▉         | 9/100 [00:04<00:49,  1.82it/s][A
Iteration:  10%|█         | 10/100 [00:05<00:49,  1.83it/s][A
Iteration:  11%|█         | 11/100 [00:06<00:48,  1.83it/s][A
Iteration:  12%|█▏        | 12/100 [00:06<00:48,  1.83it/s][A
Iteration:  13%|█▎        | 13/100 [00:07<00:47,  1.83it/s][A
Iteration:  14%|█▍        | 14/100 [00:07<00:46,  1.83it/s][A
Iteration:  15%|█▌        | 15/100 [00:08<00:46,  1.84it/s][A
Iteration:  16%|█▌        | 16/100 [00:08<00:45,  1.84it/s][A
Iteration:  17%|█▋        | 17/100 [00:09<00:45,  1.84it/s][A
Iteration:  18%|█▊        | 18/100 [00:09<00:44,  1.84it/s][A
Iteration:  19%|█▉        | 19/100 [00:10<00:44,  1.83it/s][A
Iteration:  20%|██        | 20/100 [00:10<00:43,  1.83it/s][A
Iteration:  21%|██        | 21/100 [00:11<00:43,  1.83it/s][A
Iteration:  22%|██▏       | 22/100 [00:12<00:42,  1.83it/s][A
Iteration:  23%|██▎       | 23/100 [00:12<00:41,  1.84it/s][A
Iteration:  24%|██▍       | 24/100 [00:13<00:41,  1.82it/s][A
Iteration:  25%|██▌       | 25/100 [00:13<00:41,  1.82it/s][A
Iteration:  26%|██▌       | 26/100 [00:14<00:40,  1.82it/s][A
Iteration:  27%|██▋       | 27/100 [00:14<00:40,  1.82it/s][A
Iteration:  28%|██▊       | 28/100 [00:15<00:39,  1.82it/s][A
Iteration:  29%|██▉       | 29/100 [00:15<00:38,  1.83it/s][A
Iteration:  30%|███       | 30/100 [00:16<00:38,  1.83it/s][A
Iteration:  31%|███       | 31/100 [00:16<00:37,  1.83it/s][A
Iteration:  32%|███▏      | 32/100 [00:17<00:36,  1.85it/s][A
Iteration:  33%|███▎      | 33/100 [00:18<00:36,  1.85it/s][A
Iteration:  34%|███▍      | 34/100 [00:18<00:35,  1.86it/s][A
Iteration:  35%|███▌      | 35/100 [00:19<00:34,  1.86it/s][A
Iteration:  36%|███▌      | 36/100 [00:19<00:34,  1.87it/s][A
Iteration:  37%|███▋      | 37/100 [00:20<00:33,  1.87it/s][A
Iteration:  38%|███▊      | 38/100 [00:20<00:33,  1.87it/s][A
Iteration:  39%|███▉      | 39/100 [00:21<00:32,  1.86it/s][A
Iteration:  40%|████      | 40/100 [00:21<00:32,  1.87it/s][A
Iteration:  41%|████      | 41/100 [00:22<00:31,  1.87it/s][A
Iteration:  42%|████▏     | 42/100 [00:22<00:31,  1.85it/s][A
Iteration:  43%|████▎     | 43/100 [00:23<00:31,  1.84it/s][A
Iteration:  44%|████▍     | 44/100 [00:23<00:30,  1.84it/s][A
Iteration:  45%|████▌     | 45/100 [00:24<00:30,  1.83it/s][A
Iteration:  46%|████▌     | 46/100 [00:25<00:29,  1.84it/s][A
Iteration:  47%|████▋     | 47/100 [00:25<00:28,  1.84it/s][A
Iteration:  48%|████▊     | 48/100 [00:26<00:28,  1.81it/s][A
Iteration:  49%|████▉     | 49/100 [00:26<00:27,  1.83it/s][A
Iteration:  50%|█████     | 50/100 [00:27<00:27,  1.83it/s][A
Iteration:  51%|█████     | 51/100 [00:27<00:26,  1.83it/s][A
Iteration:  52%|█████▏    | 52/100 [00:28<00:26,  1.85it/s][A
Iteration:  53%|█████▎    | 53/100 [00:28<00:25,  1.85it/s][A
Iteration:  54%|█████▍    | 54/100 [00:29<00:25,  1.83it/s][A
Iteration:  55%|█████▌    | 55/100 [00:30<00:24,  1.81it/s][A
Iteration:  56%|█████▌    | 56/100 [00:30<00:24,  1.80it/s][A
Iteration:  57%|█████▋    | 57/100 [00:31<00:23,  1.81it/s][A
Iteration:  58%|█████▊    | 58/100 [00:31<00:23,  1.81it/s][A
Iteration:  59%|█████▉    | 59/100 [00:32<00:22,  1.82it/s][A
Iteration:  60%|██████    | 60/100 [00:32<00:21,  1.83it/s][A
Iteration:  61%|██████    | 61/100 [00:33<00:21,  1.84it/s][A
Iteration:  62%|██████▏   | 62/100 [00:33<00:20,  1.86it/s][A
Iteration:  63%|██████▎   | 63/100 [00:34<00:20,  1.84it/s][A
Iteration:  64%|██████▍   | 64/100 [00:34<00:19,  1.82it/s][A
Iteration:  65%|██████▌   | 65/100 [00:35<00:19,  1.83it/s][A
Iteration:  66%|██████▌   | 66/100 [00:36<00:18,  1.83it/s][A
Iteration:  67%|██████▋   | 67/100 [00:36<00:17,  1.83it/s][A
Iteration:  68%|██████▊   | 68/100 [00:37<00:17,  1.82it/s][A
Iteration:  69%|██████▉   | 69/100 [00:37<00:17,  1.82it/s][A
Iteration:  70%|███████   | 70/100 [00:38<00:16,  1.83it/s][A
Iteration:  71%|███████   | 71/100 [00:38<00:15,  1.83it/s][A
Iteration:  72%|███████▏  | 72/100 [00:39<00:15,  1.83it/s][A
Iteration:  73%|███████▎  | 73/100 [00:39<00:14,  1.84it/s][A
Iteration:  74%|███████▍  | 74/100 [00:40<00:14,  1.83it/s][A
Iteration:  75%|███████▌  | 75/100 [00:40<00:13,  1.83it/s][A tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0196, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0882, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0021, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4058, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0080, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0201, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0294, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1793, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0142, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0335, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0226, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2550, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0078, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.2434, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0353, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0064, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3876, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0016, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(1.0173, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0027, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0207, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0018, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0112, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.4862, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0020, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0181, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0015, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0066, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1531, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0178, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0097, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.1563e-06, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1826, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0769, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0116, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0043, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0016, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0025, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0058, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0009, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0030, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0084, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0269, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0007, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0128, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0016, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0039, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0102, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0072, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0017, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0330, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0028, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0071, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0074, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0067, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0079, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0019, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0040, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0034, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0002, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.9140, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0012, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0006, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0008, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0013, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0011, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0100, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0113, device='cuda:0', grad_fn=<MeanBackward1>)
Iteration:  76%|███████▌  | 76/100 [00:41<00:12,  1.85it/s][A
Iteration:  77%|███████▋  | 77/100 [00:41<00:12,  1.86it/s][A
Iteration:  78%|███████▊  | 78/100 [00:42<00:11,  1.86it/s][A
Iteration:  79%|███████▉  | 79/100 [00:43<00:11,  1.86it/s][A
Iteration:  80%|████████  | 80/100 [00:43<00:10,  1.85it/s][A
Iteration:  81%|████████  | 81/100 [00:44<00:10,  1.85it/s][A
Iteration:  82%|████████▏ | 82/100 [00:44<00:09,  1.86it/s][A
Iteration:  83%|████████▎ | 83/100 [00:45<00:09,  1.86it/s][A
Iteration:  84%|████████▍ | 84/100 [00:45<00:08,  1.84it/s][A
Iteration:  85%|████████▌ | 85/100 [00:46<00:08,  1.83it/s][A
Iteration:  86%|████████▌ | 86/100 [00:46<00:07,  1.82it/s][A
Iteration:  87%|████████▋ | 87/100 [00:47<00:07,  1.82it/s][A
Iteration:  88%|████████▊ | 88/100 [00:47<00:06,  1.82it/s][A
Iteration:  89%|████████▉ | 89/100 [00:48<00:06,  1.82it/s][A
Iteration:  90%|█████████ | 90/100 [00:49<00:05,  1.80it/s][A
Iteration:  91%|█████████ | 91/100 [00:49<00:05,  1.79it/s][A
Iteration:  92%|█████████▏| 92/100 [00:50<00:04,  1.80it/s][A
Iteration:  93%|█████████▎| 93/100 [00:50<00:03,  1.81it/s][A
Iteration:  94%|█████████▍| 94/100 [00:51<00:03,  1.81it/s][A
Iteration:  95%|█████████▌| 95/100 [00:51<00:02,  1.82it/s][A
Iteration:  96%|█████████▌| 96/100 [00:52<00:02,  1.85it/s][A
Iteration:  97%|█████████▋| 97/100 [00:52<00:01,  1.88it/s][A
Iteration:  98%|█████████▊| 98/100 [00:53<00:01,  1.90it/s][A
Iteration:  99%|█████████▉| 99/100 [00:53<00:00,  1.92it/s][A
Iteration: 100%|██████████| 100/100 [00:54<00:00,  2.01it/s][A
[AEpoch: 100%|██████████| 30/30 [27:17<00:00, 54.32s/it]
12/28/2018 21:28:11 - INFO - pytorch_pretrained_bert.modeling -   loading archive file /data/nfsdata/meijie/data/uncased_L-12_H-768_A-12
12/28/2018 21:28:11 - INFO - pytorch_pretrained_bert.modeling -   Model config {
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "max_position_embeddings": 512,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "type_vocab_size": 2,
  "vocab_size": 30522
}

12/28/2018 21:28:17 - INFO - __main__ -   *** Example ***
12/28/2018 21:28:17 - INFO - __main__ -   unique_id: 1000000000
12/28/2018 21:28:17 - INFO - __main__ -   example_index: 0
12/28/2018 21:28:17 - INFO - __main__ -   doc_span_index: 0
12/28/2018 21:28:17 - INFO - __main__ -   tokens: [CLS] to whom did the virgin mary allegedly appear in 1858 in lou ##rdes france ? [SEP] architectural ##ly , the school has a catholic character . atop the main building ' s gold dome is a golden statue of the virgin mary . immediately in front of the main building and facing it , is a copper statue of christ with arms up ##rai ##sed with the legend " ve ##ni ##te ad me om ##nes " . next to the main building is the basilica of the sacred heart . immediately behind the basilica is the gr ##otto , a marian place of prayer and reflection . it is a replica of the gr ##otto at lou ##rdes , france where the virgin mary reputed ##ly appeared to saint bern ##ade ##tte so ##ub ##iro ##us in 1858 . at the end of the main drive ( and in a direct line that connects through 3 statues and the gold dome ) , is a simple , modern stone statue of mary . [SEP]
12/28/2018 21:28:17 - INFO - __main__ -   token_to_orig_map: 17:0 18:0 19:0 20:1 21:2 22:3 23:4 24:5 25:6 26:6 27:7 28:8 29:9 30:10 31:10 32:10 33:11 34:12 35:13 36:14 37:15 38:16 39:17 40:18 41:19 42:20 43:20 44:21 45:22 46:23 47:24 48:25 49:26 50:27 51:28 52:29 53:30 54:30 55:31 56:32 57:33 58:34 59:35 60:36 61:37 62:38 63:39 64:39 65:39 66:40 67:41 68:42 69:43 70:43 71:43 72:43 73:44 74:45 75:46 76:46 77:46 78:46 79:47 80:48 81:49 82:50 83:51 84:52 85:53 86:54 87:55 88:56 89:57 90:58 91:58 92:59 93:60 94:61 95:62 96:63 97:64 98:65 99:65 100:65 101:66 102:67 103:68 104:69 105:70 106:71 107:72 108:72 109:73 110:74 111:75 112:76 113:77 114:78 115:79 116:79 117:80 118:81 119:81 120:81 121:82 122:83 123:84 124:85 125:86 126:87 127:87 128:88 129:89 130:90 131:91 132:91 133:91 134:92 135:92 136:92 137:92 138:93 139:94 140:94 141:95 142:96 143:97 144:98 145:99 146:100 147:101 148:102 149:102 150:103 151:104 152:105 153:106 154:107 155:108 156:109 157:110 158:111 159:112 160:113 161:114 162:115 163:115 164:115 165:116 166:117 167:118 168:118 169:119 170:120 171:121 172:122 173:123 174:123
12/28/2018 21:28:17 - INFO - __main__ -   token_is_max_context: 17:True 18:True 19:True 20:True 21:True 22:True 23:True 24:True 25:True 26:True 27:True 28:True 29:True 30:True 31:True 32:True 33:True 34:True 35:True 36:True 37:True 38:True 39:True 40:True 41:True 42:True 43:True 44:True 45:True 46:True 47:True 48:True 49:True 50:True 51:True 52:True 53:True 54:True 55:True 56:True 57:True 58:True 59:True 60:True 61:True 62:True 63:True 64:True 65:True 66:True 67:True 68:True 69:True 70:True 71:True 72:True 73:True 74:True 75:True 76:True 77:True 78:True 79:True 80:True 81:True 82:True 83:True 84:True 85:True 86:True 87:True 88:True 89:True 90:True 91:True 92:True 93:True 94:True 95:True 96:True 97:True 98:True 99:True 100:True 101:True 102:True 103:True 104:True 105:True 106:True 107:True 108:True 109:True 110:True 111:True 112:True 113:True 114:True 115:True 116:True 117:True 118:True 119:True 120:True 121:True 122:True 123:True 124:True 125:True 126:True 127:True 128:True 129:True 130:True 131:True 132:True 133:True 134:True 135:True 136:True 137:True 138:True 139:True 140:True 141:True 142:True 143:True 144:True 145:True 146:True 147:True 148:True 149:True 150:True 151:True 152:True 153:True 154:True 155:True 156:True 157:True 158:True 159:True 160:True 161:True 162:True 163:True 164:True 165:True 166:True 167:True 168:True 169:True 170:True 171:True 172:True 173:True 174:True
12/28/2018 21:28:17 - INFO - __main__ -   input_ids: 101 2000 3183 2106 1996 6261 2984 9382 3711 1999 8517 1999 10223 26371 2605 1029 102 6549 2135 1010 1996 2082 2038 1037 3234 2839 1012 10234 1996 2364 2311 1005 1055 2751 8514 2003 1037 3585 6231 1997 1996 6261 2984 1012 3202 1999 2392 1997 1996 2364 2311 1998 5307 2009 1010 2003 1037 6967 6231 1997 4828 2007 2608 2039 14995 6924 2007 1996 5722 1000 2310 3490 2618 4748 2033 18168 5267 1000 1012 2279 2000 1996 2364 2311 2003 1996 13546 1997 1996 6730 2540 1012 3202 2369 1996 13546 2003 1996 24665 23052 1010 1037 14042 2173 1997 7083 1998 9185 1012 2009 2003 1037 15059 1997 1996 24665 23052 2012 10223 26371 1010 2605 2073 1996 6261 2984 22353 2135 2596 2000 3002 16595 9648 4674 2061 12083 9711 2271 1999 8517 1012 2012 1996 2203 1997 1996 2364 3298 1006 1998 1999 1037 3622 2240 2008 8539 2083 1017 11342 1998 1996 2751 8514 1007 1010 2003 1037 3722 1010 2715 2962 6231 1997 2984 1012 102 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
12/28/2018 21:28:17 - INFO - __main__ -   input_mask: 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
12/28/2018 21:28:17 - INFO - __main__ -   segment_ids: 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
12/28/2018 21:28:17 - INFO - __main__ -   *** Example ***
12/28/2018 21:28:17 - INFO - __main__ -   unique_id: 1000000001
12/28/2018 21:28:17 - INFO - __main__ -   example_index: 1
12/28/2018 21:28:17 - INFO - __main__ -   doc_span_index: 0
12/28/2018 21:28:17 - INFO - __main__ -   tokens: [CLS] what is in front of the notre dame main building ? [SEP] architectural ##ly , the school has a catholic character . atop the main building ' s gold dome is a golden statue of the virgin mary . immediately in front of the main building and facing it , is a copper statue of christ with arms up ##rai ##sed with the legend " ve ##ni ##te ad me om ##nes " . next to the main building is the basilica of the sacred heart . immediately behind the basilica is the gr ##otto , a marian place of prayer and reflection . it is a replica of the gr ##otto at lou ##rdes , france where the virgin mary reputed ##ly appeared to saint bern ##ade ##tte so ##ub ##iro ##us in 1858 . at the end of the main drive ( and in a direct line that connects through 3 statues and the gold dome ) , is a simple , modern stone statue of mary . [SEP]
12/28/2018 21:28:17 - INFO - __main__ -   token_to_orig_map: 13:0 14:0 15:0 16:1 17:2 18:3 19:4 20:5 21:6 22:6 23:7 24:8 25:9 26:10 27:10 28:10 29:11 30:12 31:13 32:14 33:15 34:16 35:17 36:18 37:19 38:20 39:20 40:21 41:22 42:23 43:24 44:25 45:26 46:27 47:28 48:29 49:30 50:30 51:31 52:32 53:33 54:34 55:35 56:36 57:37 58:38 59:39 60:39 61:39 62:40 63:41 64:42 65:43 66:43 67:43 68:43 69:44 70:45 71:46 72:46 73:46 74:46 75:47 76:48 77:49 78:50 79:51 80:52 81:53 82:54 83:55 84:56 85:57 86:58 87:58 88:59 89:60 90:61 91:62 92:63 93:64 94:65 95:65 96:65 97:66 98:67 99:68 100:69 101:70 102:71 103:72 104:72 105:73 106:74 107:75 108:76 109:77 110:78 111:79 112:79 113:80 114:81 115:81 116:81 117:82 118:83 119:84 120:85 121:86 122:87 123:87 124:88 125:89 126:90 127:91 128:91 129:91 130:92 131:92 132:92 133:92 134:93 135:94 136:94 137:95 138:96 139:97 140:98 141:99 142:100 143:101 144:102 145:102 146:103 147:104 148:105 149:106 150:107 151:108 152:109 153:110 154:111 155:112 156:113 157:114 158:115 159:115 160:115 161:116 162:117 163:118 164:118 165:119 166:120 167:121 168:122 169:123 170:123
12/28/2018 21:28:17 - INFO - __main__ -   token_is_max_context: 13:True 14:True 15:True 16:True 17:True 18:True 19:True 20:True 21:True 22:True 23:True 24:True 25:True 26:True 27:True 28:True 29:True 30:True 31:True 32:True 33:True 34:True 35:True 36:True 37:True 38:True 39:True 40:True 41:True 42:True 43:True 44:True 45:True 46:True 47:True 48:True 49:True 50:True 51:True 52:True 53:True 54:True 55:True 56:True 57:True 58:True 59:True 60:True 61:True 62:True 63:True 64:True 65:True 66:True 67:True 68:True 69:True 70:True 71:True 72:True 73:True 74:True 75:True 76:True 77:True 78:True 79:True 80:True 81:True 82:True 83:True 84:True 85:True 86:True 87:True 88:True 89:True 90:True 91:True 92:True 93:True 94:True 95:True 96:True 97:True 98:True 99:True 100:True 101:True 102:True 103:True 104:True 105:True 106:True 107:True 108:True 109:True 110:True 111:True 112:True 113:True 114:True 115:True 116:True 117:True 118:True 119:True 120:True 121:True 122:True 123:True 124:True 125:True 126:True 127:True 128:True 129:True 130:True 131:True 132:True 133:True 134:True 135:True 136:True 137:True 138:True 139:True 140:True 141:True 142:True 143:True 144:True 145:True 146:True 147:True 148:True 149:True 150:True 151:True 152:True 153:True 154:True 155:True 156:True 157:True 158:True 159:True 160:True 161:True 162:True 163:True 164:True 165:True 166:True 167:True 168:True 169:True 170:True
12/28/2018 21:28:17 - INFO - __main__ -   input_ids: 101 2054 2003 1999 2392 1997 1996 10289 8214 2364 2311 1029 102 6549 2135 1010 1996 2082 2038 1037 3234 2839 1012 10234 1996 2364 2311 1005 1055 2751 8514 2003 1037 3585 6231 1997 1996 6261 2984 1012 3202 1999 2392 1997 1996 2364 2311 1998 5307 2009 1010 2003 1037 6967 6231 1997 4828 2007 2608 2039 14995 6924 2007 1996 5722 1000 2310 3490 2618 4748 2033 18168 5267 1000 1012 2279 2000 1996 2364 2311 2003 1996 13546 1997 1996 6730 2540 1012 3202 2369 1996 13546 2003 1996 24665 23052 1010 1037 14042 2173 1997 7083 1998 9185 1012 2009 2003 1037 15059 1997 1996 24665 23052 2012 10223 26371 1010 2605 2073 1996 6261 2984 22353 2135 2596 2000 3002 16595 9648 4674 2061 12083 9711 2271 1999 8517 1012 2012 1996 2203 1997 1996 2364 3298 1006 1998 1999 1037 3622 2240 2008 8539 2083 1017 11342 1998 1996 2751 8514 1007 1010 2003 1037 3722 1010 2715 2962 6231 1997 2984 1012 102 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
12/28/2018 21:28:17 - INFO - __main__ -   input_mask: 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
12/28/2018 21:28:17 - INFO - __main__ -   segment_ids: 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
12/28/2018 21:28:29 - INFO - __main__ -   ***** Running predictions *****
12/28/2018 21:28:29 - INFO - __main__ -     Num orig examples = 1177
12/28/2018 21:28:29 - INFO - __main__ -     Num split examples = 1218
12/28/2018 21:28:29 - INFO - __main__ -     Batch size = 8
12/28/2018 21:28:29 - INFO - __main__ -   Start evaluating
Evaluating:   0%|          | 0/153 [00:00<?, ?it/s]12/28/2018 21:28:29 - INFO - __main__ -   Processing example: 0
Evaluating:   1%|          | 1/153 [00:00<00:19,  7.93it/s]Evaluating:   1%|▏         | 2/153 [00:00<00:18,  8.03it/s]Evaluating:   2%|▏         | 3/153 [00:00<00:18,  8.21it/s]Evaluating:   3%|▎         | 4/153 [00:00<00:17,  8.43it/s]Evaluating:   3%|▎         | 5/153 [00:00<00:17,  8.60it/s]Evaluating:   4%|▍         | 6/153 [00:00<00:16,  8.70it/s]Evaluating:   5%|▍         | 7/153 [00:00<00:16,  8.82it/s]Evaluating:   5%|▌         | 8/153 [00:00<00:16,  8.90it/s]Evaluating:   6%|▌         | 9/153 [00:01<00:16,  8.95it/s]Evaluating:   7%|▋         | 10/153 [00:01<00:15,  8.97it/s]Evaluating:   7%|▋         | 11/153 [00:01<00:15,  8.99it/s]Evaluating:   8%|▊         | 12/153 [00:01<00:15,  8.95it/s]Evaluating:   8%|▊         | 13/153 [00:01<00:15,  8.97it/s]Evaluating:   9%|▉         | 14/153 [00:01<00:15,  8.97it/s]Evaluating:  10%|▉         | 15/153 [00:01<00:15,  8.99it/s]Evaluating:  10%|█         | 16/153 [00:01<00:15,  9.01it/s]Evaluating:  11%|█         | 17/153 [00:01<00:15,  9.00it/s]Evaluating:  12%|█▏        | 18/153 [00:02<00:14,  9.02it/s]Evaluating:  12%|█▏        | 19/153 [00:02<00:14,  9.02it/s]Evaluating:  13%|█▎        | 20/153 [00:02<00:14,  9.03it/s]Evaluating:  14%|█▎        | 21/153 [00:02<00:14,  9.02it/s]Evaluating:  14%|█▍        | 22/153 [00:02<00:14,  9.03it/s]Evaluating:  15%|█▌        | 23/153 [00:02<00:14,  9.03it/s]Evaluating:  16%|█▌        | 24/153 [00:02<00:14,  9.00it/s]Evaluating:  16%|█▋        | 25/153 [00:02<00:14,  8.99it/s]Evaluating:  17%|█▋        | 26/153 [00:02<00:14,  9.00it/s]Evaluating:  18%|█▊        | 27/153 [00:03<00:13,  9.01it/s]Evaluating:  18%|█▊        | 28/153 [00:03<00:13,  9.02it/s]Evaluating:  19%|█▉        | 29/153 [00:03<00:13,  9.03it/s]Evaluating:  20%|█▉        | 30/153 [00:03<00:13,  9.03it/s]Evaluating:  20%|██        | 31/153 [00:03<00:13,  9.00it/s]Evaluating:  21%|██        | 32/153 [00:03<00:13,  9.01it/s]Evaluating:  22%|██▏       | 33/153 [00:03<00:13,  8.97it/s]Evaluating:  22%|██▏       | 34/153 [00:03<00:13,  8.94it/s]Evaluating:  23%|██▎       | 35/153 [00:03<00:13,  8.92it/s]Evaluating:  24%|██▎       | 36/153 [00:04<00:13,  8.95it/s]Evaluating:  24%|██▍       | 37/153 [00:04<00:12,  8.97it/s]Evaluating:  25%|██▍       | 38/153 [00:04<00:12,  8.98it/s]Evaluating:  25%|██▌       | 39/153 [00:04<00:12,  8.98it/s]Evaluating:  26%|██▌       | 40/153 [00:04<00:12,  9.00it/s]Evaluating:  27%|██▋       | 41/153 [00:04<00:12,  9.01it/s]Evaluating:  27%|██▋       | 42/153 [00:04<00:12,  8.99it/s]Evaluating:  28%|██▊       | 43/153 [00:04<00:12,  8.99it/s]Evaluating:  29%|██▉       | 44/153 [00:04<00:12,  8.98it/s]Evaluating:  29%|██▉       | 45/153 [00:05<00:12,  8.96it/s]Evaluating:  30%|███       | 46/153 [00:05<00:11,  8.98it/s]Evaluating:  31%|███       | 47/153 [00:05<00:11,  8.98it/s]Evaluating:  31%|███▏      | 48/153 [00:05<00:11,  8.96it/s]Evaluating:  32%|███▏      | 49/153 [00:05<00:11,  8.98it/s]Evaluating:  33%|███▎      | 50/153 [00:05<00:11,  8.96it/s]Evaluating:  33%|███▎      | 51/153 [00:05<00:11,  8.95it/s]Evaluating:  34%|███▍      | 52/153 [00:05<00:11,  8.98it/s]Evaluating:  35%|███▍      | 53/153 [00:05<00:11,  8.99it/s]Evaluating:  35%|███▌      | 54/153 [00:06<00:11,  8.95it/s]Evaluating:  36%|███▌      | 55/153 [00:06<00:10,  8.98it/s]Evaluating:  37%|███▋      | 56/153 [00:06<00:10,  9.01it/s]Evaluating:  37%|███▋      | 57/153 [00:06<00:10,  9.00it/s]Evaluating:  38%|███▊      | 58/153 [00:06<00:10,  9.01it/s]Evaluating:  39%|███▊      | 59/153 [00:06<00:10,  9.02it/s]Evaluating:  39%|███▉      | 60/153 [00:06<00:10,  9.02it/s]Evaluating:  40%|███▉      | 61/153 [00:06<00:10,  9.01it/s]Evaluating:  41%|████      | 62/153 [00:06<00:10,  9.02it/s]Evaluating:  41%|████      | 63/153 [00:07<00:09,  9.02it/s]Evaluating:  42%|████▏     | 64/153 [00:07<00:09,  9.01it/s]Evaluating:  42%|████▏     | 65/153 [00:07<00:09,  9.01it/s]Evaluating:  43%|████▎     | 66/153 [00:07<00:09,  9.00it/s]Evaluating:  44%|████▍     | 67/153 [00:07<00:09,  9.00it/s]Evaluating:  44%|████▍     | 68/153 [00:07<00:09,  9.01it/s]Evaluating:  45%|████▌     | 69/153 [00:07<00:09,  8.99it/s]Evaluating:  46%|████▌     | 70/153 [00:07<00:09,  8.98it/s]Evaluating:  46%|████▋     | 71/153 [00:07<00:09,  9.01it/s]Evaluating:  47%|████▋     | 72/153 [00:08<00:08,  9.01it/s]Evaluating:  48%|████▊     | 73/153 [00:08<00:08,  9.02it/s]Evaluating:  48%|████▊     | 74/153 [00:08<00:08,  9.03it/s]Evaluating:  49%|████▉     | 75/153 [00:08<00:08,  8.98it/s]Evaluating:  50%|████▉     | 76/153 [00:08<00:08,  8.98it/s]Evaluating:  50%|█████     | 77/153 [00:08<00:08,  8.99it/s]Evaluating:  51%|█████     | 78/153 [00:08<00:08,  8.99it/s]Evaluating:  52%|█████▏    | 79/153 [00:08<00:08,  8.99it/s]Evaluating:  52%|█████▏    | 80/153 [00:08<00:08,  8.99it/s]Evaluating:  53%|█████▎    | 81/153 [00:09<00:08,  8.99it/s]Evaluating:  54%|█████▎    | 82/153 [00:09<00:07,  8.98it/s]Evaluating:  54%|█████▍    | 83/153 [00:09<00:07,  8.99it/s]Evaluating:  55%|█████▍    | 84/153 [00:09<00:07,  9.01it/s]Evaluating:  56%|█████▌    | 85/153 [00:09<00:07,  9.00it/s]Evaluating:  56%|█████▌    | 86/153 [00:09<00:07,  9.01it/s]Evaluating:  57%|█████▋    | 87/153 [00:09<00:07,  9.01it/s]Evaluating:  58%|█████▊    | 88/153 [00:09<00:07,  9.01it/s]Evaluating:  58%|█████▊    | 89/153 [00:09<00:07,  9.02it/s]Evaluating:  59%|█████▉    | 90/153 [00:10<00:06,  9.01it/s]Evaluating:  59%|█████▉    | 91/153 [00:10<00:06,  9.02it/s]Evaluating:  60%|██████    | 92/153 [00:10<00:06,  9.01it/s]Evaluating:  61%|██████    | 93/153 [00:10<00:06,  9.02it/s]Evaluating:  61%|██████▏   | 94/153 [00:10<00:06,  9.03it/s]Evaluating:  62%|██████▏   | 95/153 [00:10<00:06,  9.02it/s]Evaluating:  63%|██████▎   | 96/153 [00:10<00:06,  8.71it/s]Evaluating:  63%|██████▎   | 97/153 [00:10<00:06,  8.79it/s]Evaluating:  64%|██████▍   | 98/153 [00:10<00:06,  8.86it/s]Evaluating:  65%|██████▍   | 99/153 [00:11<00:06,  8.90it/s]Evaluating:  65%|██████▌   | 100/153 [00:11<00:05,  8.92it/s]Evaluating:  66%|██████▌   | 101/153 [00:11<00:05,  8.95it/s]Evaluating:  67%|██████▋   | 102/153 [00:11<00:05,  8.96it/s]Evaluating:  67%|██████▋   | 103/153 [00:11<00:05,  8.97it/s]Evaluating:  68%|██████▊   | 104/153 [00:11<00:05,  8.96it/s]Evaluating:  69%|██████▊   | 105/153 [00:11<00:05,  8.96it/s]Evaluating:  69%|██████▉   | 106/153 [00:11<00:05,  8.97it/s]Evaluating:  70%|██████▉   | 107/153 [00:11<00:05,  8.98it/s]Evaluating:  71%|███████   | 108/153 [00:12<00:05,  8.96it/s]Evaluating:  71%|███████   | 109/153 [00:12<00:04,  8.96it/s]Evaluating:  72%|███████▏  | 110/153 [00:12<00:04,  8.99it/s]Evaluating:  73%|███████▎  | 111/153 [00:12<00:04,  8.99it/s]Evaluating:  73%|███████▎  | 112/153 [00:12<00:04,  9.00it/s]Evaluating:  74%|███████▍  | 113/153 [00:12<00:04,  8.99it/s]Evaluating:  75%|███████▍  | 114/153 [00:12<00:04,  8.98it/s]Evaluating:  75%|███████▌  | 115/153 [00:12<00:04,  8.98it/s]Evaluating:  76%|███████▌  | 116/153 [00:12<00:04,  8.98it/s]Evaluating:  76%|███████▋  | 117/153 [00:13<00:04,  8.97it/s]Evaluating:  77%|███████▋  | 118/153 [00:13<00:03,  8.98it/s]Evaluating:  78%|███████▊  | 119/153 [00:13<00:03,  8.99it/s]Evaluating:  78%|███████▊  | 120/153 [00:13<00:03,  8.99it/s]Evaluating:  79%|███████▉  | 121/153 [00:13<00:03,  8.98it/s]Evaluating:  80%|███████▉  | 122/153 [00:13<00:03,  8.97it/s]Evaluating:  80%|████████  | 123/153 [00:13<00:03,  8.98it/s]Evaluating:  81%|████████  | 124/153 [00:13<00:03,  8.99it/s]Evaluating:  82%|████████▏ | 125/153 [00:13<00:03,  9.01it/s]12/28/2018 21:28:43 - INFO - __main__ -   Processing example: 1000
Evaluating:  82%|████████▏ | 126/153 [00:14<00:02,  9.00it/s]Evaluating:  83%|████████▎ | 127/153 [00:14<00:02,  9.01it/s]Evaluating:  84%|████████▎ | 128/153 [00:14<00:02,  8.99it/s]Evaluating:  84%|████████▍ | 129/153 [00:14<00:02,  8.99it/s]Evaluating:  85%|████████▍ | 130/153 [00:14<00:02,  8.99it/s]Evaluating:  86%|████████▌ | 131/153 [00:14<00:02,  8.99it/s]Evaluating:  86%|████████▋ | 132/153 [00:14<00:02,  9.00it/s]Evaluating:  87%|████████▋ | 133/153 [00:14<00:02,  8.98it/s]Evaluating:  88%|████████▊ | 134/153 [00:14<00:02,  8.97it/s]Evaluating:  88%|████████▊ | 135/153 [00:15<00:02,  8.98it/s]Evaluating:  89%|████████▉ | 136/153 [00:15<00:01,  8.97it/s]Evaluating:  90%|████████▉ | 137/153 [00:15<00:01,  8.98it/s]Evaluating:  90%|█████████ | 138/153 [00:15<00:01,  8.93it/s]Evaluating:  91%|█████████ | 139/153 [00:15<00:01,  8.95it/s]Evaluating:  92%|█████████▏| 140/153 [00:15<00:01,  8.96it/s]Evaluating:  92%|█████████▏| 141/153 [00:15<00:01,  8.96it/s]Evaluating:  93%|█████████▎| 142/153 [00:15<00:01,  8.97it/s]Evaluating:  93%|█████████▎| 143/153 [00:15<00:01,  8.96it/s]Evaluating:  94%|█████████▍| 144/153 [00:16<00:01,  8.94it/s]Evaluating:  95%|█████████▍| 145/153 [00:16<00:00,  8.92it/s]Evaluating:  95%|█████████▌| 146/153 [00:16<00:00,  8.94it/s]Evaluating:  96%|█████████▌| 147/153 [00:16<00:00,  8.93it/s]Evaluating:  97%|█████████▋| 148/153 [00:16<00:00,  8.94it/s]Evaluating:  97%|█████████▋| 149/153 [00:16<00:00,  8.89it/s]Evaluating:  98%|█████████▊| 150/153 [00:16<00:00,  8.84it/s]Evaluating:  99%|█████████▊| 151/153 [00:16<00:00,  8.85it/s]Evaluating:  99%|█████████▉| 152/153 [00:16<00:00,  8.86it/s]Evaluating: 100%|██████████| 153/153 [00:16<00:00,  9.00it/s]
12/28/2018 21:28:46 - INFO - __main__ -   Writing predictions to: /tmp/SQuAD_v1-12_3_2_384_128_newloss/predictions.json
12/28/2018 21:28:46 - INFO - __main__ -   Writing nbest to: /tmp/SQuAD_v1-12_3_2_384_128_newloss/nbest_predictions.json
 tensor(0.0035, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0158, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.3878, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0003, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0005, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1894, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0030, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0061, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0772, device='cuda:0', grad_fn=<MeanBackward1>) tensor(6.2011e-06, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0010, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0821, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0001, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0059, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.1173, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0043, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0004, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0000, device='cuda:0', grad_fn=<MeanBackward1>) tensor(0.0016, device='cuda:0', grad_fn=<MeanBackward1>) 