experiments/2022-10-19-9028ad3c32f5c9871417ab3c5582aa3f4a9f9bf0a44f1de700e544523ab59718/output.log

nohup: ignoring input
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
No config specified, defaulting to: apps/all
Found cached dataset apps (/home/user/.cache/huggingface/datasets/codeparrot___apps/all/0.0.0/04ac807715d07d6e5cc580f59cdc8213cd7dc4529d0bb819cca72c9f8e8c1aa5)
PyTorch: setting up devices
The default value for the training argument `--report_to` will change in v5 (from all installed integrations to none). In v5, you will need to use `--report_to all` to get the same behavior as now. You should start updating your code and make this info disappear :-).
Max length: 2048
GPU memory occupied: 2667 MB.

  0%|          | 0/235 [00:00<?, ?it/s]
  0%|          | 1/235 [00:02<10:49,  2.78s/it]
                                               

  0%|          | 1/235 [00:02<10:49,  2.78s/it]
  1%|          | 2/235 [00:04<09:30,  2.45s/it]
  1%|▏         | 3/235 [00:07<09:03,  2.34s/it]
  2%|▏         | 4/235 [00:09<08:50,  2.30s/it]
  2%|▏         | 5/235 [00:11<08:42,  2.27s/it]
                                               

  2%|▏         | 5/235 [00:11<08:42,  2.27s/it]
  3%|▎         | 6/235 [00:13<08:37,  2.26s/it]
  3%|▎         | 7/235 [00:16<08:32,  2.25s/it]
  3%|▎         | 8/235 [00:18<08:29,  2.24s/it]
  4%|▍         | 9/235 [00:20<08:26,  2.24s/it]
  4%|▍         | 10/235 [00:22<08:23,  2.24s/it]
                                                

  4%|▍         | 10/235 [00:22<08:23,  2.24s/it]
  5%|▍         | 11/235 [00:25<08:21,  2.24s/it]
  5%|▌         | 12/235 [00:27<08:18,  2.24s/it]
  6%|▌         | 13/235 [00:29<08:16,  2.24s/it]
  6%|▌         | 14/235 [00:31<08:13,  2.24s/it]
  6%|▋         | 15/235 [00:33<08:11,  2.24s/it]
                                                

  6%|▋         | 15/235 [00:33<08:11,  2.24s/it]
  7%|▋         | 16/235 [00:36<08:09,  2.24s/it]
  7%|▋         | 17/235 [00:38<08:07,  2.24s/it]
  8%|▊         | 18/235 [00:40<08:05,  2.24s/it]
  8%|▊         | 19/235 [00:42<08:03,  2.24s/it]
  9%|▊         | 20/235 [00:45<08:01,  2.24s/it]
                                                

  9%|▊         | 20/235 [00:45<08:01,  2.24s/it]
  9%|▉         | 21/235 [00:47<07:58,  2.24s/it]
  9%|▉         | 22/235 [00:49<07:56,  2.24s/it]
 10%|▉         | 23/235 [00:51<07:54,  2.24s/it]
 10%|█         | 24/235 [00:54<07:52,  2.24s/it]
 11%|█         | 25/235 [00:56<07:50,  2.24s/it]
                                                

 11%|█         | 25/235 [00:56<07:50,  2.24s/it]
 11%|█         | 26/235 [00:58<07:48,  2.24s/it]
 11%|█▏        | 27/235 [01:00<07:45,  2.24s/it]
 12%|█▏        | 28/235 [01:03<07:43,  2.24s/it]
 12%|█▏        | 29/235 [01:05<07:41,  2.24s/it]
 13%|█▎        | 30/235 [01:07<07:39,  2.24s/it]
                                                

 13%|█▎        | 30/235 [01:07<07:39,  2.24s/it]
 13%|█▎        | 31/235 [01:09<07:37,  2.24s/it]
 14%|█▎        | 32/235 [01:12<07:35,  2.24s/it]
 14%|█▍        | 33/235 [01:14<07:32,  2.24s/it]
 14%|█▍        | 34/235 [01:16<07:30,  2.24s/it]
 15%|█▍        | 35/235 [01:18<07:28,  2.24s/it]
                                                

 15%|█▍        | 35/235 [01:18<07:28,  2.24s/it]
 15%|█▌        | 36/235 [01:21<07:26,  2.24s/it]
 16%|█▌        | 37/235 [01:23<07:24,  2.24s/it]
 16%|█▌        | 38/235 [01:25<07:21,  2.24s/it]
 17%|█▋        | 39/235 [01:27<07:19,  2.24s/it]
 17%|█▋        | 40/235 [01:30<07:17,  2.24s/it]
                                                

 17%|█▋        | 40/235 [01:30<07:17,  2.24s/it]
 17%|█▋        | 41/235 [01:32<07:15,  2.24s/it]
 18%|█▊        | 42/235 [01:34<07:12,  2.24s/it]
 18%|█▊        | 43/235 [01:36<07:10,  2.24s/it]
 19%|█▊        | 44/235 [01:38<07:08,  2.24s/it]
 19%|█▉        | 45/235 [01:41<07:06,  2.24s/it]
                                                

 19%|█▉        | 45/235 [01:41<07:06,  2.24s/it]
 20%|█▉        | 46/235 [01:43<07:03,  2.24s/it]
 20%|██        | 47/235 [01:45<07:01,  2.24s/it]
 20%|██        | 48/235 [01:49<08:33,  2.74s/it]
 21%|██        | 49/235 [01:51<08:02,  2.59s/it]
 21%|██▏       | 50/235 [01:54<07:40,  2.49s/it]
                                                

 21%|██▏       | 50/235 [01:54<07:40,  2.49s/it]
 22%|██▏       | 51/235 [01:56<07:24,  2.41s/it]
 22%|██▏       | 52/235 [01:58<07:12,  2.36s/it]
 23%|██▎       | 53/235 [02:00<07:03,  2.33s/it]
 23%|██▎       | 54/235 [02:03<06:56,  2.30s/it]
 23%|██▎       | 55/235 [02:05<06:51,  2.28s/it]
                                                

 23%|██▎       | 55/235 [02:05<06:51,  2.28s/it]
 24%|██▍       | 56/235 [02:07<06:46,  2.27s/it]
 24%|██▍       | 57/235 [02:09<06:42,  2.26s/it]
 25%|██▍       | 58/235 [02:12<06:39,  2.26s/it]
 25%|██▌       | 59/235 [02:14<06:36,  2.25s/it]
 26%|██▌       | 60/235 [02:16<06:33,  2.25s/it]
                                                

 26%|██▌       | 60/235 [02:16<06:33,  2.25s/it]
 26%|██▌       | 61/235 [02:18<06:31,  2.25s/it]
 26%|██▋       | 62/235 [02:21<06:28,  2.25s/it]
 27%|██▋       | 63/235 [02:23<06:26,  2.24s/it]
 27%|██▋       | 64/235 [02:25<06:23,  2.24s/it]
 28%|██▊       | 65/235 [02:27<06:21,  2.24s/it]
                                                

 28%|██▊       | 65/235 [02:27<06:21,  2.24s/it]
 28%|██▊       | 66/235 [02:29<06:19,  2.24s/it]
 29%|██▊       | 67/235 [02:32<06:16,  2.24s/it]
 29%|██▉       | 68/235 [02:34<06:14,  2.24s/it]
 29%|██▉       | 69/235 [02:36<06:12,  2.24s/it]
 30%|██▉       | 70/235 [02:38<06:09,  2.24s/it]
                                                

 30%|██▉       | 70/235 [02:38<06:09,  2.24s/it]
 30%|███       | 71/235 [02:41<06:07,  2.24s/it]
 31%|███       | 72/235 [02:43<06:05,  2.24s/it]
 31%|███       | 73/235 [02:45<06:03,  2.24s/it]
 31%|███▏      | 74/235 [02:47<06:01,  2.24s/it]
 32%|███▏      | 75/235 [02:50<05:58,  2.24s/it]
                                                

 32%|███▏      | 75/235 [02:50<05:58,  2.24s/it]
 32%|███▏      | 76/235 [02:52<05:56,  2.24s/it]
 33%|███▎      | 77/235 [02:54<05:54,  2.24s/it]
 33%|███▎      | 78/235 [02:56<05:52,  2.24s/it]
 34%|███▎      | 79/235 [02:59<05:49,  2.24s/it]
 34%|███▍      | 80/235 [03:01<05:47,  2.24s/it]
                                                

 34%|███▍      | 80/235 [03:01<05:47,  2.24s/it]
 34%|███▍      | 81/235 [03:03<05:45,  2.24s/it]
 35%|███▍      | 82/235 [03:05<05:43,  2.24s/it]
 35%|███▌      | 83/235 [03:08<05:40,  2.24s/it]
 36%|███▌      | 84/235 [03:10<05:38,  2.24s/it]
 36%|███▌      | 85/235 [03:12<05:36,  2.24s/it]
                                                

 36%|███▌      | 85/235 [03:12<05:36,  2.24s/it]
 37%|███▋      | 86/235 [03:14<05:34,  2.24s/it]
 37%|███▋      | 87/235 [03:17<05:31,  2.24s/it]
 37%|███▋      | 88/235 [03:19<05:29,  2.24s/it]
 38%|███▊      | 89/235 [03:21<05:27,  2.24s/it]
 38%|███▊      | 90/235 [03:23<05:24,  2.24s/it]
                                                

 38%|███▊      | 90/235 [03:23<05:24,  2.24s/it]
 39%|███▊      | 91/235 [03:26<05:22,  2.24s/it]
 39%|███▉      | 92/235 [03:28<05:20,  2.24s/it]
 40%|███▉      | 93/235 [03:30<05:18,  2.24s/it]
 40%|████      | 94/235 [03:32<05:16,  2.24s/it]
 40%|████      | 95/235 [03:36<06:23,  2.74s/it]
                                                

 40%|████      | 95/235 [03:36<06:23,  2.74s/it]
 41%|████      | 96/235 [03:38<06:00,  2.59s/it]
 41%|████▏     | 97/235 [03:41<05:43,  2.49s/it]
 42%|████▏     | 98/235 [03:43<05:30,  2.41s/it]
 42%|████▏     | 99/235 [03:45<05:21,  2.36s/it]
 43%|████▎     | 100/235 [03:47<05:13,  2.33s/it]
                                                 

 43%|████▎     | 100/235 [03:47<05:13,  2.33s/it]
 43%|████▎     | 101/235 [03:50<05:08,  2.30s/it]
 43%|████▎     | 102/235 [03:52<05:03,  2.28s/it]
 44%|████▍     | 103/235 [03:54<04:59,  2.27s/it]
 44%|████▍     | 104/235 [03:56<04:56,  2.26s/it]
 45%|████▍     | 105/235 [03:59<04:53,  2.25s/it]
                                                 

 45%|████▍     | 105/235 [03:59<04:53,  2.25s/it]
 45%|████▌     | 106/235 [04:01<04:50,  2.25s/it]
 46%|████▌     | 107/235 [04:03<04:47,  2.25s/it]
 46%|████▌     | 108/235 [04:05<04:45,  2.25s/it]
 46%|████▋     | 109/235 [04:08<04:42,  2.25s/it]
 47%|████▋     | 110/235 [04:10<04:40,  2.24s/it]
                                                 

 47%|████▋     | 110/235 [04:10<04:40,  2.24s/it]
 47%|████▋     | 111/235 [04:12<04:38,  2.24s/it]
 48%|████▊     | 112/235 [04:14<04:36,  2.24s/it]
 48%|████▊     | 113/235 [04:17<04:33,  2.24s/it]
 49%|████▊     | 114/235 [04:19<04:31,  2.24s/it]
 49%|████▉     | 115/235 [04:21<04:29,  2.24s/it]
                                                 

 49%|████▉     | 115/235 [04:21<04:29,  2.24s/it]
 49%|████▉     | 116/235 [04:23<04:26,  2.24s/it]
 50%|████▉     | 117/235 [04:25<04:24,  2.24s/it]
 50%|█████     | 118/235 [04:28<04:22,  2.24s/it]
 51%|█████     | 119/235 [04:30<04:20,  2.24s/it]
 51%|█████     | 120/235 [04:32<04:17,  2.24s/it]
                                                 

 51%|█████     | 120/235 [04:32<04:17,  2.24s/it]
 51%|█████▏    | 121/235 [04:34<04:15,  2.24s/it]
 52%|█████▏    | 122/235 [04:37<04:13,  2.24s/it]
 52%|█████▏    | 123/235 [04:39<04:11,  2.24s/it]
 53%|█████▎    | 124/235 [04:41<04:08,  2.24s/it]
 53%|█████▎    | 125/235 [04:43<04:06,  2.24s/it]
                                                 

 53%|█████▎    | 125/235 [04:43<04:06,  2.24s/it]
 54%|█████▎    | 126/235 [04:46<04:04,  2.24s/it]
 54%|█████▍    | 127/235 [04:48<04:01,  2.24s/it]
 54%|█████▍    | 128/235 [04:50<03:59,  2.24s/it]
 55%|█████▍    | 129/235 [04:52<03:57,  2.24s/it]
 55%|█████▌    | 130/235 [04:55<03:55,  2.24s/it]
                                                 

 55%|█████▌    | 130/235 [04:55<03:55,  2.24s/it]
 56%|█████▌    | 131/235 [04:57<03:53,  2.24s/it]
 56%|█████▌    | 132/235 [04:59<03:50,  2.24s/it]
 57%|█████▋    | 133/235 [05:01<03:48,  2.24s/it]
 57%|█████▋    | 134/235 [05:04<03:46,  2.24s/it]
 57%|█████▋    | 135/235 [05:06<03:44,  2.24s/it]
                                                 

 57%|█████▋    | 135/235 [05:06<03:44,  2.24s/it]
 58%|█████▊    | 136/235 [05:08<03:41,  2.24s/it]
 58%|█████▊    | 137/235 [05:10<03:39,  2.24s/it]
 59%|█████▊    | 138/235 [05:13<03:37,  2.24s/it]
 59%|█████▉    | 139/235 [05:15<03:35,  2.24s/it]
 60%|█████▉    | 140/235 [05:17<03:32,  2.24s/it]
                                                 

 60%|█████▉    | 140/235 [05:17<03:32,  2.24s/it]
 60%|██████    | 141/235 [05:19<03:30,  2.24s/it]
 60%|██████    | 142/235 [05:23<04:14,  2.74s/it]
 61%|██████    | 143/235 [05:25<03:58,  2.59s/it]
 61%|██████▏   | 144/235 [05:28<03:46,  2.49s/it]
 62%|██████▏   | 145/235 [05:30<03:37,  2.41s/it]
                                                 

 62%|██████▏   | 145/235 [05:30<03:37,  2.41s/it]
 62%|██████▏   | 146/235 [05:32<03:30,  2.36s/it]
 63%|██████▎   | 147/235 [05:34<03:24,  2.32s/it]
 63%|██████▎   | 148/235 [05:37<03:20,  2.30s/it]
 63%|██████▎   | 149/235 [05:39<03:16,  2.28s/it]
 64%|██████▍   | 150/235 [05:41<03:12,  2.27s/it]
                                                 

 64%|██████▍   | 150/235 [05:41<03:12,  2.27s/it]
 64%|██████▍   | 151/235 [05:43<03:09,  2.26s/it]
 65%|██████▍   | 152/235 [05:46<03:07,  2.26s/it]
 65%|██████▌   | 153/235 [05:48<03:04,  2.25s/it]
 66%|██████▌   | 154/235 [05:50<03:02,  2.25s/it]
 66%|██████▌   | 155/235 [05:52<02:59,  2.25s/it]
                                                 

 66%|██████▌   | 155/235 [05:52<02:59,  2.25s/it]
 66%|██████▋   | 156/235 [05:55<02:57,  2.24s/it]
 67%|██████▋   | 157/235 [05:57<02:55,  2.24s/it]
 67%|██████▋   | 158/235 [05:59<02:52,  2.24s/it]
 68%|██████▊   | 159/235 [06:01<02:50,  2.24s/it]
 68%|██████▊   | 160/235 [06:04<02:48,  2.24s/it]
                                                 

 68%|██████▊   | 160/235 [06:04<02:48,  2.24s/it]
 69%|██████▊   | 161/235 [06:06<02:45,  2.24s/it]
 69%|██████▉   | 162/235 [06:08<02:43,  2.24s/it]
 69%|██████▉   | 163/235 [06:10<02:41,  2.24s/it]
 70%|██████▉   | 164/235 [06:12<02:39,  2.24s/it]
 70%|███████   | 165/235 [06:15<02:36,  2.24s/it]
                                                 

 70%|███████   | 165/235 [06:15<02:36,  2.24s/it]
 71%|███████   | 166/235 [06:17<02:34,  2.24s/it]
 71%|███████   | 167/235 [06:19<02:32,  2.24s/it]
 71%|███████▏  | 168/235 [06:21<02:30,  2.24s/it]
 72%|███████▏  | 169/235 [06:24<02:27,  2.24s/it]
 72%|███████▏  | 170/235 [06:26<02:25,  2.24s/it]
                                                 

 72%|███████▏  | 170/235 [06:26<02:25,  2.24s/it]
 73%|███████▎  | 171/235 [06:28<02:23,  2.24s/it]
 73%|███████▎  | 172/235 [06:30<02:21,  2.24s/it]
 74%|███████▎  | 173/235 [06:33<02:18,  2.24s/it]
 74%|███████▍  | 174/235 [06:35<02:16,  2.24s/it]
 74%|███████▍  | 175/235 [06:37<02:14,  2.24s/it]
                                                 

 74%|███████▍  | 175/235 [06:37<02:14,  2.24s/it]
 75%|███████▍  | 176/235 [06:39<02:12,  2.24s/it]
 75%|███████▌  | 177/235 [06:42<02:10,  2.24s/it]
 76%|███████▌  | 178/235 [06:44<02:07,  2.24s/it]
 76%|███████▌  | 179/235 [06:46<02:05,  2.24s/it]
 77%|███████▋  | 180/235 [06:48<02:03,  2.24s/it]
                                                 

 77%|███████▋  | 180/235 [06:48<02:03,  2.24s/it]
 77%|███████▋  | 181/235 [06:51<02:01,  2.24s/it]
 77%|███████▋  | 182/235 [06:53<01:58,  2.24s/it]
 78%|███████▊  | 183/235 [06:55<01:56,  2.24s/it]
 78%|███████▊  | 184/235 [06:57<01:54,  2.24s/it]
 79%|███████▊  | 185/235 [07:00<01:52,  2.24s/it]
                                                 

 79%|███████▊  | 185/235 [07:00<01:52,  2.24s/it]
 79%|███████▉  | 186/235 [07:02<01:49,  2.24s/it]
 80%|███████▉  | 187/235 [07:04<01:47,  2.24s/it]
 80%|████████  | 188/235 [07:06<01:45,  2.24s/it]
 80%|████████  | 189/235 [07:10<02:06,  2.74s/it]
 81%|████████  | 190/235 [07:12<01:56,  2.59s/it]
                                                 

 81%|████████  | 190/235 [07:12<01:56,  2.59s/it]
 81%|████████▏ | 191/235 [07:15<01:49,  2.48s/it]
 82%|████████▏ | 192/235 [07:17<01:43,  2.41s/it]
 82%|████████▏ | 193/235 [07:19<01:39,  2.36s/it]
 83%|████████▎ | 194/235 [07:21<01:35,  2.32s/it]
 83%|████████▎ | 195/235 [07:24<01:31,  2.30s/it]
                                                 

 83%|████████▎ | 195/235 [07:24<01:31,  2.30s/it]
 83%|████████▎ | 196/235 [07:26<01:28,  2.28s/it]
 84%|████████▍ | 197/235 [07:28<01:26,  2.27s/it]
 84%|████████▍ | 198/235 [07:30<01:23,  2.26s/it]
 85%|████████▍ | 199/235 [07:33<01:21,  2.25s/it]
 85%|████████▌ | 200/235 [07:35<01:18,  2.25s/it]
                                                 

 85%|████████▌ | 200/235 [07:35<01:18,  2.25s/it]
 86%|████████▌ | 201/235 [07:41<01:53,  3.34s/it]
 86%|████████▌ | 202/235 [07:43<01:39,  3.01s/it]
 86%|████████▋ | 203/235 [07:45<01:28,  2.78s/it]
 87%|████████▋ | 204/235 [07:47<01:21,  2.62s/it]
 87%|████████▋ | 205/235 [07:50<01:15,  2.50s/it]
                                                 

 87%|████████▋ | 205/235 [07:50<01:15,  2.50s/it]
 88%|████████▊ | 206/235 [07:52<01:10,  2.42s/it]
 88%|████████▊ | 207/235 [07:54<01:06,  2.37s/it]
 89%|████████▊ | 208/235 [07:56<01:02,  2.33s/it]
 89%|████████▉ | 209/235 [07:59<00:59,  2.30s/it]
 89%|████████▉ | 210/235 [08:01<00:57,  2.29s/it]
                                                 

 89%|████████▉ | 210/235 [08:01<00:57,  2.29s/it]
 90%|████████▉ | 211/235 [08:03<00:54,  2.27s/it]
 90%|█████████ | 212/235 [08:05<00:52,  2.26s/it]
 91%|█████████ | 213/235 [08:08<00:49,  2.26s/it]
 91%|█████████ | 214/235 [08:10<00:47,  2.25s/it]
 91%|█████████▏| 215/235 [08:12<00:44,  2.25s/it]
                                                 

 91%|█████████▏| 215/235 [08:12<00:44,  2.25s/it]
 92%|█████████▏| 216/235 [08:14<00:42,  2.25s/it]
 92%|█████████▏| 217/235 [08:17<00:40,  2.24s/it]
 93%|█████████▎| 218/235 [08:19<00:38,  2.24s/it]
 93%|█████████▎| 219/235 [08:21<00:35,  2.24s/it]
 94%|█████████▎| 220/235 [08:23<00:33,  2.24s/it]
                                                 

 94%|█████████▎| 220/235 [08:23<00:33,  2.24s/it]
 94%|█████████▍| 221/235 [08:26<00:31,  2.24s/it]
 94%|█████████▍| 222/235 [08:28<00:29,  2.24s/it]
 95%|█████████▍| 223/235 [08:30<00:26,  2.24s/it]
 95%|█████████▌| 224/235 [08:32<00:24,  2.24s/it]
 96%|█████████▌| 225/235 [08:34<00:22,  2.24s/it]
                                                 

 96%|█████████▌| 225/235 [08:34<00:22,  2.24s/it]
 96%|█████████▌| 226/235 [08:37<00:20,  2.24s/it]
 97%|█████████▋| 227/235 [08:39<00:17,  2.24s/it]
 97%|█████████▋| 228/235 [08:41<00:15,  2.24s/it]
 97%|█████████▋| 229/235 [08:43<00:13,  2.24s/it]
 98%|█████████▊| 230/235 [08:46<00:11,  2.24s/it]
                                                 

 98%|█████████▊| 230/235 [08:46<00:11,  2.24s/it]
 98%|█████████▊| 231/235 [08:48<00:08,  2.24s/it]
 99%|█████████▊| 232/235 [08:50<00:06,  2.24s/it]
 99%|█████████▉| 233/235 [08:52<00:04,  2.24s/it]
100%|█████████▉| 234/235 [08:55<00:02,  2.24s/it]
100%|██████████| 235/235 [08:57<00:00,  2.24s/it]
                                                 

100%|██████████| 235/235 [08:57<00:00,  2.24s/it]
                                                 

100%|██████████| 235/235 [08:57<00:00,  2.24s/it]
100%|██████████| 235/235 [08:57<00:00,  2.29s/it]