End of training

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.1,
+    "eval_loss": 0.10796044021844864,
+    "eval_runtime": 2073.5744,
+    "eval_samples_per_second": 7.654,
+    "eval_steps_per_second": 0.239,
+    "eval_wer": 12.206885082321635,
+    "train_loss": 0.17721048017342886,
+    "train_runtime": 61737.3829,
+    "train_samples_per_second": 6.22,
+    "train_steps_per_second": 0.097
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.1,
+    "eval_loss": 0.10796044021844864,
+    "eval_runtime": 2073.5744,
+    "eval_samples_per_second": 7.654,
+    "eval_steps_per_second": 0.239,
+    "eval_wer": 12.206885082321635
+}

runs/Dec17_00-49-12_129-213-88-66/events.out.tfevents.1671302027.129-213-88-66.1326738.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f58508fb05ada573f3a57972a24b5a612a0fe93a9a8935c2036990e6dc02ed
+size 358

train_20221217-004912.log

@@ -138,3 +138,7 @@ remote: LFS file scan complete.
 To https://huggingface.co/ales/whisper-base-belarusian
    4074dad..52d55ef  main -> main
 
+12/17/2022 17:59:11 - WARNING - huggingface_hub.repository - To https://huggingface.co/ales/whisper-base-belarusian
+   52d55ef..4aae45b  main -> main
+
+12/17/2022 17:59:14 - INFO - __main__ - *** Evaluate ***

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.1,
+    "train_loss": 0.17721048017342886,
+    "train_runtime": 61737.3829,
+    "train_samples_per_second": 6.22,
+    "train_steps_per_second": 0.097
+}

train_run_1.log

@@ -36388,4 +36388,29 @@ remote: LFS file scan complete.
 To https://huggingface.co/ales/whisper-base-belarusian
    4074dad..52d55ef  main -> main
 
-
+
+To https://huggingface.co/ales/whisper-base-belarusian
+   52d55ef..4aae45b  main -> main
+
+12/17/2022 17:59:11 - WARNING - huggingface_hub.repository - To https://huggingface.co/ales/whisper-base-belarusian
+   52d55ef..4aae45b  main -> main
+
+***** train metrics *****
+  epoch                    =         1.1
+  train_loss               =      0.1772
+  train_runtime            = 17:08:57.38
+  train_samples_per_second =        6.22
+  train_steps_per_second   =       0.097
+12/17/2022 17:59:14 - INFO - __main__ - *** Evaluate ***
+[INFO|trainer.py:710] 2022-12-17 17:59:14,350 >> The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: sentence, labels_truncated, input_length, labels_length, audio. If sentence, labels_truncated, input_length, labels_length, audio are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.
+[INFO|trainer.py:2955] 2022-12-17 17:59:14,353 >> ***** Running Evaluation *****
+[INFO|trainer.py:2957] 2022-12-17 17:59:14,353 >>   Num examples = 15872
+[INFO|trainer.py:2960] 2022-12-17 17:59:14,353 >>   Batch size = 32
+
  0%|          | 0/496 [00:00<?, ?it/s]
  0%|          | 2/496 [00:02<12:12,  1.48s/it]
  1%|          | 3/496 [00:06<18:24,  2.24s/it]
  1%|          | 4/496 [00:09<21:51,  2.67s/it]
  1%|          | 5/496 [00:12<23:42,  2.90s/it]
  1%|          | 6/496 [00:16<24:19,  2.98s/it]
  1%|▏         | 7/496 [00:20<27:04,  3.32s/it]
  2%|▏         | 8/496 [00:23<27:39,  3.40s/it]
  2%|▏         | 9/496 [00:26<25:56,  3.20s/it]
  2%|▏         | 10/496 [00:29<25:11,  3.11s/it]
  2%|▏         | 11/496 [00:32<24:23,  3.02s/it]
  2%|▏         | 12/496 [00:35<25:18,  3.14s/it]
  3%|▎         | 13/496 [00:38<25:26,  3.16s/it]
  3%|▎         | 14/496 [00:41<24:15,  3.02s/it]
  3%|▎         | 15/496 [00:45<25:47,  3.22s/it]
  3%|▎         | 16/496 [00:48<25:38,  3.21s/it]
  3%|▎         | 17/496 [00:51<25:22,  3.18s/it]
  4%|▎         | 18/496 [00:54<24:15,  3.05s/it]
  4%|▍         | 19/496 [00:57<24:07,  3.03s/it]
  4%|▍         | 20/496 [01:00<24:16,  3.06s/it]
  4%|▍         | 21/496 [01:03<24:03,  3.04s/it]
  4%|▍         | 22/496 [01:06<23:17,  2.95s/it]
  5%|▍         | 23/496 [01:09<24:46,  3.14s/it]
  5%|▍         | 24/496 [01:12<23:55,  3.04s/it]
  5%|▌         | 25/496 [01:16<25:09,  3.20s/it]
  5%|▌         | 26/496 [01:19<25:19,  3.23s/it]
  5%|▌         | 27/496 [01:22<24:26,  3.13s/it]
  6%|▌         | 28/496 [01:25<23:56,  3.07s/it]
  6%|▌         | 29/496 [01:28<24:39,  3.17s/it]
  6%|▌         | 30/496 [01:31<25:05,  3.23s/it]
  6%|▋         | 31/496 [01:34<23:58,  3.09s/it]
  6%|▋         | 32/496 [01:38<25:00,  3.23s/it]
  7%|▋         | 33/496 [01:42<27:41,  3.59s/it]
  7%|▋         | 34/496 [01:45<25:28,  3.31s/it]
  7%|▋         | 35/496 [01:48<25:38,  3.34s/it]
  7%|▋         | 36/496 [01:52<25:34,  3.34s/it]
  7%|▋         | 37/496 [01:54<24:04,  3.15s/it]
  8%|▊         | 38/496 [01:57<24:04,  3.16s/it]
  8%|▊         | 39/496 [02:01<23:59,  3.15s/it]
  8%|▊         | 40/496 [02:03<22:32,  2.97s/it]
  8%|▊         | 41/496 [02:06<22:10,  2.92s/it]
  8%|▊         | 42/496 [02:09<23:02,  3.05s/it]
  9%|▊         | 43/496 [02:13<23:49,  3.16s/it]
  9%|▉         | 44/496 [02:16<24:04,  3.20s/it]
  9%|▉         | 45/496 [02:19<22:39,  3.01s/it]
  9%|▉         | 46/496 [02:21<21:54,  2.92s/it]
  9%|▉         | 47/496 [02:24<20:50,  2.78s/it]
 10%|▉         | 48/496 [02:27<21:49,  2.92s/it]
 10%|▉         | 49/496 [02:30<21:10,  2.84s/it]
 10%|█         | 50/496 [02:32<20:34,  2.77s/it]
 10%|█         | 51/496 [02:35<21:04,  2.84s/it]
 10%|█         | 52/496 [02:38<21:39,  2.93s/it]
 11%|█         | 53/496 [02:41<20:54,  2.83s/it]
 11%|█         | 54/496 [02:44<20:25,  2.77s/it]
 11%|█         | 55/496 [02:46<20:03,  2.73s/it]
 11%|█▏        | 56/496 [02:49<21:03,  2.87s/it]
 11%|█▏        | 57/496 [02:52<21:03,  2.88s/it]
 12%|█▏        | 58/496 [02:55<20:26,  2.80s/it]
 12%|█▏        | 59/496 [02:58<20:13,  2.78s/it]
 12%|█▏        | 60/496 [03:01<20:47,  2.86s/it]
 12%|█▏        | 61/496 [03:03<20:19,  2.80s/it]
 12%|█▎        | 62/496 [03:06<20:46,  2.87s/it]
 13%|█▎        | 63/496 [03:09<20:45,  2.88s/it]
 13%|█▎        | 64/496 [03:12<20:54,  2.91s/it]
 13%|█▎        | 65/496 [03:16<21:28,  2.99s/it]
 13%|█▎        | 66/496 [03:19<21:31,  3.00s/it]
 14%|█▎        | 67/496 [03:21<20:14,  2.83s/it]
 14%|█▎        | 68/496 [03:23<19:18,  2.71s/it]
 14%|█▍        | 69/496 [03:26<19:26,  2.73s/it]
 14%|█▍        | 70/496 [03:29<19:42,  2.78s/it]
 14%|█▍        | 71/496 [03:32<20:16,  2.86s/it]
 15%|█▍        | 72/496 [03:35<20:12,  2.86s/it]
 15%|█▍        | 73/496 [03:38<20:02,  2.84s/it]
 15%|█▍        | 74/496 [03:40<19:41,  2.80s/it]
 15%|█▌        | 75/496 [03:43<19:55,  2.84s/it]
 15%|█▌        | 76/496 [03:47<20:28,  2.93s/it]
 16%|█▌        | 77/496 [03:50<21:00,  3.01s/it]
 16%|█▌        | 78/496 [03:53<20:37,  2.96s/it]
 16%|█▌        | 79/496 [03:56<21:21,  3.07s/it]
 16%|█▌        | 80/496 [03:59<21:38,  3.12s/it]
 16%|█▋        | 81/496 [04:03<22:28,  3.25s/it]
 17%|█▋        | 82/496 [04:06<22:22,  3.24s/it]
 17%|█▋        | 83/496 [04:09<21:24,  3.11s/it]
 17%|█▋        | 84/496 [04:12<22:08,  3.23s/it]
 17%|█▋        | 85/496 [04:15<22:00,  3.21s/it]
 17%|█▋        | 86/496 [04:19<22:39,  3.32s/it]
 18%|█▊        | 87/496 [04:22<22:18,  3.27s/it]
 18%|█▊        | 88/496 [04:25<21:10,  3.11s/it]
 18%|█▊        | 89/496 [04:28<20:45,  3.06s/it]
 18%|█▊        | 90/496 [04:31<20:32,  3.04s/it]
 18%|█▊        | 91/496 [04:34<21:21,  3.16s/it]
 19%|█▊        | 92/496 [04:37<21:17,  3.16s/it]
 19%|█▉        | 93/496 [04:41<21:41,  3.23s/it]
 19%|█▉        | 94/496 [04:44<21:48,  3.26s/it]
 19%|█▉        | 95/496 [04:48<21:58,  3.29s/it]
 19%|█▉        | 96/496 [04:50<20:33,  3.08s/it]
 20%|█▉        | 97/496 [04:53<20:22,  3.06s/it]
 20%|█▉        | 98/496 [04:56<20:15,  3.06s/it]
 20%|█▉        | 99/496 [04:59<20:11,  3.05s/it]
 20%|██        | 100/496 [05:02<19:38,  2.98s/it]
 20%|██        | 101/496 [05:05<19:09,  2.91s/it]
 21%|██        | 102/496 [05:08<18:50,  2.87s/it]
 21%|██        | 103/496 [05:10<18:56,  2.89s/it]
 21%|██        | 104/496 [05:13<18:31,  2.84s/it]
 21%|██        | 105/496 [05:16<19:08,  2.94s/it]
 21%|██▏       | 106/496 [05:19<19:21,  2.98s/it]
 22%|██▏       | 107/496 [05:23<19:42,  3.04s/it]
 22%|██▏       | 108/496 [05:25<19:19,  2.99s/it]
 22%|██▏       | 109/496 [05:28<19:15,  2.98s/it]
 22%|██▏       | 110/496 [05:31<18:53,  2.94s/it]
 22%|██▏       | 111/496 [05:34<18:13,  2.84s/it]
 23%|██▎       | 112/496 [05:37<18:49,  2.94s/it]
 23%|██▎       | 113/496 [05:39<17:44,  2.78s/it]
 23%|██▎       | 114/496 [05:42<17:41,  2.78s/it]
 23%|██▎       | 115/496 [05:45<17:20,  2.73s/it]
 23%|██▎       | 116/496 [05:48<18:26,  2.91s/it]
 24%|██▎       | 117/496 [05:51<18:20,  2.90s/it]
 24%|██▍       | 118/496 [05:54<17:44,  2.82s/it]
 24%|██▍       | 119/496 [05:56<17:24,  2.77s/it]
 24%|██▍       | 120/496 [05:59<17:57,  2.87s/it]
 24%|██▍       | 121/496 [06:02<17:45,  2.84s/it]
 25%|██▍       | 122/496 [06:05<18:00,  2.89s/it]
 25%|██▍       | 123/496 [06:08<18:31,  2.98s/it]
 25%|██▌       | 124/496 [06:11<17:33,  2.83s/it]
 25%|██▌       | 125/496 [06:14<17:35,  2.84s/it]
 25%|██▌       | 126/496 [06:17<17:50,  2.89s/it]
 26%|██▌       | 127/496 [06:20<18:29,  3.01s/it]
 26%|██▌       | 128/496 [06:23<18:19,  2.99s/it]
 26%|██▌       | 129/496 [06:26<17:38,  2.88s/it]
 26%|██▌       | 130/496 [06:29<17:56,  2.94s/it]
 26%|██▋       | 131/496 [06:32<17:49,  2.93s/it]
 27%|██▋       | 132/496 [06:34<17:03,  2.81s/it]
 27%|██▋       | 133/496 [06:37<16:22,  2.71s/it]
 27%|██▋       | 134/496 [06:40<16:39,  2.76s/it]
 27%|██▋       | 135/496 [06:43<17:11,  2.86s/it]
 27%|██▋       | 136/496 [06:46<17:18,  2.89s/it]
 28%|██▊       | 137/496 [06:48<16:54,  2.82s/it]
 28%|██▊       | 138/496 [06:51<17:06,  2.87s/it]
 28%|██▊       | 139/496 [06:54<17:28,  2.94s/it]
 28%|██▊       | 140/496 [06:58<18:10,  3.06s/it]
 28%|██▊       | 141/496 [07:01<17:53,  3.02s/it]
 29%|██▊       | 142/496 [07:04<18:21,  3.11s/it]
 29%|██▉       | 143/496 [07:07<17:51,  3.03s/it]
 29%|██▉       | 144/496 [07:09<17:06,  2.92s/it]
 29%|██▉       | 145/496 [07:12<17:13,  2.94s/it]
 29%|██▉       | 146/496 [07:16<17:28,  3.00s/it]
 30%|██▉       | 147/496 [07:19<18:15,  3.14s/it]
 30%|██▉       | 148/496 [07:22<17:54,  3.09s/it]
 30%|███       | 149/496 [07:25<17:31,  3.03s/it]
 30%|███       | 150/496 [07:28<17:50,  3.09s/it]
 30%|███       | 151/496 [07:31<16:52,  2.94s/it]
 31%|███       | 152/496 [07:35<18:21,  3.20s/it]
 31%|███       | 153/496 [07:38<18:37,  3.26s/it]
 31%|███       | 154/496 [07:40<17:17,  3.03s/it]
 31%|███▏      | 155/496 [07:43<16:31,  2.91s/it]
 31%|███▏      | 156/496 [07:46<16:33,  2.92s/it]
 32%|███▏      | 157/496 [07:49<16:31,  2.92s/it]
 32%|███▏      | 158/496 [07:51<15:11,  2.70s/it]
 32%|███▏      | 159/496 [07:54<14:47,  2.63s/it]
 32%|███▏      | 160/496 [07:56<14:20,  2.56s/it]
 32%|███▏      | 161/496 [07:59<14:47,  2.65s/it]
 33%|███▎      | 162/496 [08:02<15:13,  2.73s/it]
 33%|███▎      | 163/496 [08:05<15:25,  2.78s/it]
 33%|███▎      | 164/496 [08:08<16:01,  2.90s/it]
 33%|███▎      | 165/496 [08:11<16:58,  3.08s/it]
 33%|███▎      | 166/496 [08:15<17:12,  3.13s/it]
 34%|███▎      | 167/496 [08:17<16:00,  2.92s/it]
 34%|███▍      | 168/496 [08:20<15:34,  2.85s/it]
 34%|███▍      | 169/496 [08:23<15:40,  2.88s/it]
 34%|███▍      | 170/496 [08:25<15:37,  2.88s/it]
 34%|███▍      | 171/496 [08:28<15:08,  2.79s/it]
 35%|███▍      | 172/496 [08:31<15:44,  2.92s/it]
 35%|███▍      | 173/496 [08:34<15:27,  2.87s/it]
 35%|███▌      | 174/496 [08:37<15:02,  2.80s/it]
 35%|███▌      | 175/496 [08:40<15:04,  2.82s/it]
 35%|███▌      | 176/496 [08:43<15:36,  2.93s/it]
 36%|███▌      | 177/496 [08:45<15:06,  2.84s/it]
 36%|███▌      | 178/496 [08:49<16:49,  3.17s/it]
 36%|███▌      | 179/496 [08:52<16:22,  3.10s/it]
 36%|███▋      | 180/496 [08:55<16:15,  3.09s/it]
 36%|███▋      | 181/496 [08:58<16:05,  3.07s/it]
 37%|███▋      | 182/496 [09:01<15:18,  2.92s/it]
 37%|███▋      | 183/496 [09:04<15:09,  2.91s/it]
 37%|███▋      | 184/496 [09:07<14:51,  2.86s/it]
 37%|███▋      | 185/496 [09:10<15:17,  2.95s/it]
 38%|███▊      | 186/496 [09:13<15:29,  3.00s/it]
 38%|███▊      | 187/496 [09:15<14:47,  2.87s/it]
 38%|███▊      | 188/496 [09:19<15:58,  3.11s/it]
 38%|███▊      | 189/496 [09:22<15:54,  3.11s/it]
 38%|███▊      | 190/496 [09:25<15:57,  3.13s/it]
 39%|███▊      | 191/496 [09:29<16:17,  3.21s/it]
 39%|███▊      | 192/496 [09:32<15:37,  3.09s/it]
 39%|███▉      | 193/496 [09:34<15:19,  3.03s/it]
 39%|███▉      | 194/496 [09:37<14:05,  2.80s/it]
 39%|███▉      | 195/496 [09:39<13:51,  2.76s/it]
 40%|███▉      | 196/496 [09:42<14:08,  2.83s/it]
 40%|███▉      | 197/496 [09:45<14:07,  2.83s/it]
 40%|███▉      | 198/496 [09:48<14:31,  2.93s/it]
 40%|████      | 199/496 [09:51<14:41,  2.97s/it]
 40%|████      | 200/496 [09:54<14:37,  2.97s/it]
 41%|████      | 201/496 [09:57<14:49,  3.02s/it]
 41%|████      | 202/496 [10:01<15:28,  3.16s/it]
 41%|████      | 203/496 [10:03<14:24,  2.95s/it]
 41%|████      | 204/496 [10:06<14:04,  2.89s/it]
 41%|████▏     | 205/496 [10:09<13:46,  2.84s/it]
 42%|████▏     | 206/496 [10:12<13:34,  2.81s/it]
 42%|████▏     | 207/496 [10:14<13:27,  2.79s/it]
 42%|████▏     | 208/496 [10:17<13:22,  2.79s/it]
 42%|████▏     | 209/496 [10:20<14:04,  2.94s/it]
 42%|████▏     | 210/496 [10:23<14:05,  2.96s/it]
 43%|████▎     | 211/496 [10:26<14:08,  2.98s/it]
 43%|████▎     | 212/496 [10:30<14:26,  3.05s/it]
 43%|████▎     | 213/496 [10:33<14:15,  3.02s/it]
 43%|████▎     | 214/496 [10:36<14:18,  3.05s/it]
 43%|████▎     | 215/496 [10:39<14:00,  2.99s/it]
 44%|████▎     | 216/496 [10:42<14:33,  3.12s/it]
 44%|████▍     | 217/496 [10:46<15:38,  3.36s/it]
 44%|████▍     | 218/496 [10:49<14:29,  3.13s/it]
 44%|████▍     | 219/496 [10:51<13:49,  2.99s/it]
 44%|████▍     | 220/496 [10:54<13:28,  2.93s/it]
 45%|████▍     | 221/496 [10:57<13:45,  3.00s/it]
 45%|████▍     | 222/496 [11:00<13:46,  3.02s/it]
 45%|████▍     | 223/496 [11:03<13:38,  3.00s/it]
 45%|████▌     | 224/496 [11:07<14:38,  3.23s/it]
 45%|████▌     | 225/496 [11:11<15:20,  3.40s/it]
 46%|████▌     | 226/496 [11:14<14:45,  3.28s/it]
 46%|████▌     | 227/496 [11:17<14:04,  3.14s/it]
 46%|████▌     | 228/496 [11:20<14:05,  3.16s/it]
 46%|████▌     | 229/496 [11:23<13:34,  3.05s/it]
 46%|████▋     | 230/496 [11:26<13:29,  3.04s/it]
 47%|████▋     | 231/496 [11:29<13:37,  3.08s/it]
 47%|████▋     | 232/496 [11:32<13:34,  3.08s/it]
 47%|████▋     | 233/496 [11:35<13:48,  3.15s/it]
 47%|████▋     | 234/496 [11:38<13:23,  3.07s/it]
 47%|████▋     | 235/496 [11:41<13:19,  3.06s/it]
 48%|████▊     | 236/496 [11:44<13:16,  3.06s/it]
 48%|████▊     | 237/496 [11:47<12:48,  2.97s/it]
 48%|████▊     | 238/496 [11:50<12:54,  3.00s/it]
 48%|████▊     | 239/496 [11:53<13:25,  3.14s/it]
 48%|████▊     | 240/496 [11:56<12:47,  3.00s/it]
 49%|████▊     | 241/496 [11:59<12:53,  3.03s/it]
 49%|████▉     | 242/496 [12:02<12:46,  3.02s/it]
 49%|████▉     | 243/496 [12:05<12:26,  2.95s/it]
 49%|████▉     | 244/496 [12:08<12:30,  2.98s/it]
 49%|████▉     | 245/496 [12:12<13:17,  3.18s/it]
 50%|████▉     | 246/496 [12:15<12:56,  3.11s/it]
 50%|████▉     | 247/496 [12:18<12:59,  3.13s/it]
 50%|█████     | 248/496 [12:21<12:23,  3.00s/it]
 50%|█████     | 249/496 [12:23<12:17,  2.98s/it]
 50%|█████     | 250/496 [12:26<12:03,  2.94s/it]
 51%|█████     | 251/496 [12:29<11:18,  2.77s/it]
 51%|█████     | 252/496 [12:32<12:00,  2.95s/it]
 51%|█████     | 253/496 [12:35<12:21,  3.05s/it]
 51%|█████     | 254/496 [12:39<12:57,  3.21s/it]
 51%|█████▏    | 255/496 [12:41<11:52,  2.96s/it]
 52%|█████▏    | 256/496 [12:45<13:06,  3.28s/it]
 52%|█████▏    | 257/496 [12:48<12:45,  3.20s/it]
 52%|█████▏    | 258/496 [12:51<11:50,  2.98s/it]
 52%|█████▏    | 259/496 [12:54<11:58,  3.03s/it]
 52%|█████▏    | 260/496 [12:57<12:10,  3.09s/it]
 53%|█████▎    | 261/496 [13:00<11:42,  2.99s/it]
 53%|█████▎    | 262/496 [13:03<11:26,  2.93s/it]
 53%|█████▎    | 263/496 [13:06<11:14,  2.90s/it]
 53%|█████▎    | 264/496 [13:08<10:56,  2.83s/it]
 53%|█████▎    | 265/496 [13:12<11:29,  2.98s/it]
 54%|█████▎    | 266/496 [13:15<11:55,  3.11s/it]
 54%|█████▍    | 267/496 [13:19<12:29,  3.27s/it]
 54%|█████▍    | 268/496 [13:22<12:20,  3.25s/it]
 54%|█████▍    | 269/496 [13:25<12:22,  3.27s/it]
 54%|█████▍    | 270/496 [13:28<12:15,  3.25s/it]
 55%|█████▍    | 271/496 [13:31<12:00,  3.20s/it]
 55%|█████▍    | 272/496 [13:34<11:27,  3.07s/it]
 55%|█████▌    | 273/496 [13:37<11:03,  2.98s/it]
 55%|█████▌    | 274/496 [13:40<11:16,  3.05s/it]
 55%|█████▌    | 275/496 [13:44<11:45,  3.19s/it]
 56%|█████▌    | 276/496 [13:47<11:27,  3.12s/it]
 56%|█████▌    | 277/496 [13:49<11:01,  3.02s/it]
 56%|█████▌    | 278/496 [13:53<11:31,  3.17s/it]
 56%|█████▋    | 279/496 [13:56<11:23,  3.15s/it]
 56%|█████▋    | 280/496 [14:00<11:40,  3.24s/it]
 57%|█████▋    | 281/496 [14:03<11:21,  3.17s/it]
 57%|█████▋    | 282/496 [14:05<11:03,  3.10s/it]
 57%|█████▋    | 283/496 [14:11<13:06,  3.69s/it]
 57%|█████▋    | 284/496 [14:13<11:46,  3.33s/it]
 57%|█████▋    | 285/496 [14:16<10:51,  3.09s/it]
 58%|█████▊    | 286/496 [14:19<11:13,  3.21s/it]
 58%|█████▊    | 287/496 [14:22<10:49,  3.11s/it]
 58%|█████▊    | 288/496 [14:26<11:41,  3.37s/it]
 58%|█████▊    | 289/496 [14:29<11:08,  3.23s/it]
 58%|█████▊    | 290/496 [14:32<10:46,  3.14s/it]
 59%|█████▊    | 291/496 [14:35<10:25,  3.05s/it]
 59%|█████▉    | 292/496 [14:37<10:12,  3.00s/it]
 59%|█████▉    | 293/496 [14:40<09:17,  2.75s/it]
 59%|█████▉    | 294/496 [14:42<09:16,  2.76s/it]
 59%|█████▉    | 295/496 [14:46<10:04,  3.01s/it]
 60%|█████▉    | 296/496 [14:49<09:48,  2.94s/it]
 60%|█████▉    | 297/496 [14:51<09:13,  2.78s/it]
 60%|██████    | 298/496 [14:54<08:45,  2.65s/it]
 60%|██████    | 299/496 [14:56<08:37,  2.63s/it]
 60%|██████    | 300/496 [14:59<09:02,  2.77s/it]
 61%|██████    | 301/496 [15:02<08:58,  2.76s/it]
 61%|██████    | 302/496 [15:06<10:03,  3.11s/it]
 61%|██████    | 303/496 [15:09<10:05,  3.14s/it]
 61%|██████▏   | 304/496 [15:12<10:06,  3.16s/it]
 61%|██████▏   | 305/496 [15:15<09:26,  2.97s/it]
 62%|██████▏   | 306/496 [15:17<09:09,  2.89s/it]
 62%|██████▏   | 307/496 [15:20<08:48,  2.80s/it]
 62%|██████▏   | 308/496 [15:23<08:41,  2.77s/it]
 62%|██████▏   | 309/496 [15:26<08:40,  2.78s/it]
 62%|██████▎   | 310/496 [15:29<09:10,  2.96s/it]
 63%|██████▎   | 311/496 [15:32<09:38,  3.13s/it]
 63%|██████▎   | 312/496 [15:36<09:44,  3.18s/it]
 63%|██████▎   | 313/496 [15:38<08:43,  2.86s/it]
 63%|██████▎   | 314/496 [15:41<08:28,  2.79s/it]
 64%|██████▎   | 315/496 [15:44<08:42,  2.89s/it]
 64%|██████▎   | 316/496 [15:47<08:39,  2.88s/it]
 64%|██████▍   | 317/496 [15:49<08:37,  2.89s/it]
 64%|██████▍   | 318/496 [15:52<08:38,  2.91s/it]
 64%|██████��   | 319/496 [15:56<09:25,  3.19s/it]
 65%|██████▍   | 320/496 [15:59<08:56,  3.05s/it]
 65%|██████▍   | 321/496 [16:02<08:32,  2.93s/it]
 65%|██████▍   | 322/496 [16:04<08:17,  2.86s/it]
 65%|██████▌   | 323/496 [16:08<08:36,  2.98s/it]
 65%|██████▌   | 324/496 [16:11<08:33,  2.99s/it]
 66%|██████▌   | 325/496 [16:13<08:05,  2.84s/it]
 66%|██████▌   | 326/496 [16:16<08:22,  2.96s/it]
 66%|██████▌   | 327/496 [16:19<07:59,  2.83s/it]
 66%|██████▌   | 328/496 [16:21<07:46,  2.77s/it]
 66%|██████▋   | 329/496 [16:25<08:04,  2.90s/it]
 67%|██████▋   | 330/496 [16:27<07:52,  2.85s/it]
 67%|██████▋   | 331/496 [16:31<08:08,  2.96s/it]
 67%|██████▋   | 332/496 [16:34<08:15,  3.02s/it]
 67%|██████▋   | 333/496 [16:37<08:10,  3.01s/it]
 67%|██████▋   | 334/496 [16:40<07:54,  2.93s/it]
 68%|██████▊   | 335/496 [16:43<08:04,  3.01s/it]
 68%|██████▊   | 336/496 [16:46<08:23,  3.15s/it]
 68%|██████▊   | 337/496 [16:49<08:15,  3.11s/it]
 68%|██████▊   | 338/496 [16:52<07:48,  2.96s/it]
 68%|██████▊   | 339/496 [16:54<07:26,  2.84s/it]
 69%|██████▊   | 340/496 [16:58<07:36,  2.93s/it]
 69%|██████▉   | 341/496 [17:01<07:49,  3.03s/it]
 69%|██████▉   | 342/496 [17:04<08:04,  3.14s/it]
 69%|██████▉   | 343/496 [17:07<08:00,  3.14s/it]
 69%|██████▉   | 344/496 [17:10<07:49,  3.09s/it]
 70%|██████▉   | 345/496 [17:13<07:27,  2.97s/it]
 70%|██████▉   | 346/496 [17:15<07:05,  2.84s/it]
 70%|██████▉   | 347/496 [17:19<07:14,  2.92s/it]
 70%|███████   | 348/496 [17:22<07:13,  2.93s/it]
 70%|███████   | 349/496 [17:26<08:25,  3.44s/it]
 71%|███████   | 350/496 [17:29<08:12,  3.38s/it]
 71%|███████   | 351/496 [17:32<07:51,  3.25s/it]
 71%|███████   | 352/496 [17:35<07:31,  3.13s/it]
 71%|███████   | 353/496 [17:38<07:24,  3.11s/it]
 71%|███████▏  | 354/496 [17:41<07:23,  3.12s/it]
 72%|███████▏  | 355/496 [17:45<07:33,  3.21s/it]
 72%|███████▏  | 356/496 [17:48<07:27,  3.20s/it]
 72%|███████▏  | 357/496 [17:51<07:14,  3.13s/it]
 72%|███████▏  | 358/496 [17:53<06:41,  2.91s/it]
 72%|███████▏  | 359/496 [17:57<06:47,  2.97s/it]
 73%|███████▎  | 360/496 [18:00<06:47,  3.00s/it]
 73%|███████▎  | 361/496 [18:02<06:37,  2.94s/it]
 73%|███████▎  | 362/496 [18:06<06:55,  3.10s/it]
 73%|███████▎  | 363/496 [18:09<06:44,  3.04s/it]
 73%|███████▎  | 364/496 [18:11<06:21,  2.89s/it]
 74%|███████▎  | 365/496 [18:14<06:14,  2.86s/it]
 74%|███████▍  | 366/496 [18:17<06:06,  2.82s/it]
 74%|███████▍  | 367/496 [18:19<05:56,  2.76s/it]
 74%|███████▍  | 368/496 [18:23<06:24,  3.00s/it]
 74%|███████▍  | 369/496 [18:26<06:17,  2.97s/it]
 75%|███████▍  | 370/496 [18:29<06:24,  3.05s/it]
 75%|███████▍  | 371/496 [18:32<06:29,  3.12s/it]
 75%|███████▌  | 372/496 [18:35<06:12,  3.01s/it]
 75%|███████▌  | 373/496 [18:38<06:07,  2.99s/it]
 75%|███████▌  | 374/496 [18:41<06:02,  2.97s/it]
 76%|███████▌  | 375/496 [18:44<06:11,  3.07s/it]
 76%|███████▌  | 376/496 [18:47<05:57,  2.98s/it]
 76%|███████▌  | 377/496 [18:50<05:56,  3.00s/it]
 76%|███████▌  | 378/496 [18:53<05:44,  2.92s/it]
 76%|███████▋  | 379/496 [18:55<05:22,  2.75s/it]
 77%|███████▋  | 380/496 [18:58<05:30,  2.85s/it]
 77%|███████▋  | 381/496 [19:01<05:15,  2.74s/it]
 77%|███████▋  | 382/496 [19:04<05:25,  2.86s/it]
 77%|███████▋  | 383/496 [19:07<05:37,  2.99s/it]
 77%|███████▋  | 384/496 [19:10<05:12,  2.79s/it]
 78%|███████▊  | 385/496 [19:13<05:26,  2.94s/it]
 78%|███████▊  | 386/496 [19:16<05:28,  2.98s/it]
 78%|███████▊  | 387/496 [19:19<05:29,  3.03s/it]
 78%|███████▊  | 388/496 [19:22<05:28,  3.04s/it]
 78%|███████▊  | 389/496 [19:25<05:30,  3.09s/it]
 79%|███████▊  | 390/496 [19:28<05:22,  3.05s/it]
 79%|███████▉  | 391/496 [19:31<05:18,  3.04s/it]
 79%|███████▉  | 392/496 [19:34<05:09,  2.98s/it]
 79%|███████▉  | 393/496 [19:37<04:59,  2.91s/it]
 79%|███████▉  | 394/496 [19:40<05:02,  2.96s/it]
 80%|███████▉  | 395/496 [19:42<04:42,  2.80s/it]
 80%|███████▉  | 396/496 [19:46<04:57,  2.98s/it]
 80%|████████  | 397/496 [19:49<05:02,  3.06s/it]
 80%|████████  | 398/496 [19:52<05:09,  3.16s/it]
 80%|████████  | 399/496 [19:55<04:43,  2.92s/it]
 81%|████████  | 400/496 [19:57<04:30,  2.81s/it]
 81%|████████  | 401/496 [20:01<04:50,  3.06s/it]
 81%|████████  | 402/496 [20:04<04:43,  3.02s/it]
 81%|████████▏ | 403/496 [20:08<05:19,  3.43s/it]
 81%|████████▏ | 404/496 [20:11<04:55,  3.21s/it]
 82%|████████▏ | 405/496 [20:14<04:48,  3.17s/it]
 82%|████████▏ | 406/496 [20:16<04:22,  2.92s/it]
 82%|████████▏ | 407/496 [20:19<04:15,  2.87s/it]
 82%|████████▏ | 408/496 [20:22<04:14,  2.89s/it]
 82%|████████▏ | 409/496 [20:25<04:05,  2.82s/it]
 83%|████████▎ | 410/496 [20:27<03:58,  2.78s/it]
 83%|████████▎ | 411/496 [20:31<04:08,  2.92s/it]
 83%|████████▎ | 412/496 [20:34<04:13,  3.01s/it]
 83%|████████▎ | 413/496 [20:37<04:20,  3.14s/it]
 83%|████████▎ | 414/496 [20:40<04:17,  3.14s/it]
 84%|████████▎ | 415/496 [20:44<04:27,  3.30s/it]
 84%|████████▍ | 416/496 [20:47<04:13,  3.17s/it]
 84%|████████▍ | 417/496 [20:50<04:05,  3.11s/it]
 84%|████████▍ | 418/496 [20:53<03:54,  3.01s/it]
 84%|████████▍ | 419/496 [20:55<03:40,  2.86s/it]
 85%|████████▍ | 420/496 [20:58<03:25,  2.70s/it]
 85%|████████▍ | 421/496 [21:00<03:18,  2.65s/it]
 85%|████████▌ | 422/496 [21:03<03:18,  2.69s/it]
 85%|████████▌ | 423/496 [21:05<03:08,  2.58s/it]
 85%|████████▌ | 424/496 [21:08<03:17,  2.74s/it]
 86%|████████▌ | 425/496 [21:11<03:16,  2.77s/it]
 86%|████████▌ | 426/496 [21:15<03:25,  2.94s/it]
 86%|████████▌ | 427/496 [21:17<03:22,  2.93s/it]
 86%|████████▋ | 428/496 [21:21<03:24,  3.01s/it]
 86%|████████▋ | 429/496 [21:23<03:14,  2.90s/it]
 87%|████████▋ | 430/496 [21:26<03:06,  2.83s/it]
 87%|████████▋ | 431/496 [21:29<03:09,  2.92s/it]
 87%|████████▋ | 432/496 [21:32<03:10,  2.98s/it]
 87%|████████▋ | 433/496 [21:35<02:57,  2.82s/it]
 88%|████████▊ | 434/496 [21:38<02:58,  2.88s/it]
 88%|████████▊ | 435/496 [21:41<02:55,  2.87s/it]
 88%|████████▊ | 436/496 [21:44<02:57,  2.95s/it]
 88%|████████▊ | 437/496 [21:47<03:09,  3.20s/it]
 88%|████████▊ | 438/496 [21:50<02:58,  3.07s/it]
 89%|████████▊ | 439/496 [21:53<02:57,  3.11s/it]
 89%|████████▊ | 440/496 [21:56<02:50,  3.04s/it]
 89%|████████▉ | 441/496 [22:00<02:50,  3.10s/it]
 89%|████████▉ | 442/496 [22:02<02:45,  3.06s/it]
 89%|████████▉ | 443/496 [22:06<02:51,  3.24s/it]
 90%|████████▉ | 444/496 [22:09<02:41,  3.11s/it]
 90%|████████▉ | 445/496 [22:12<02:34,  3.02s/it]
 90%|████████▉ | 446/496 [22:15<02:27,  2.95s/it]
 90%|█████████ | 447/496 [22:18<02:25,  2.97s/it]
 90%|█████████ | 448/496 [22:21<02:24,  3.00s/it]
 91%|█████████ | 449/496 [22:24<02:27,  3.14s/it]
 91%|█████████ | 450/496 [22:27<02:17,  2.99s/it]
 91%|█████████ | 451/496 [22:29<02:04,  2.76s/it]
 91%|█████████ | 452/496 [22:32<01:59,  2.71s/it]
 91%|█████████▏| 453/496 [22:35<02:06,  2.95s/it]
 92%|█████████▏| 454/496 [22:39<02:15,  3.22s/it]
 92%|█████████▏| 455/496 [22:41<02:02,  2.99s/it]
 92%|█████████▏| 456/496 [22:44<01:59,  2.99s/it]
 92%|█████████▏| 457/496 [22:48<02:03,  3.18s/it]
 92%|█████████▏| 458/496 [22:50<01:51,  2.94s/it]
 93%|█████████▎| 459/496 [22:54<01:59,  3.23s/it]
 93%|█████████▎| 460/496 [22:57<01:53,  3.16s/it]
 93%|█████████▎| 461/496 [23:00<01:47,  3.07s/it]
 93%|█████████▎| 462/496 [23:03<01:41,  2.98s/it]
 93%|█████████▎| 463/496 [23:06<01:37,  2.96s/it]
 94%|█████████▎| 464/496 [23:09<01:39,  3.10s/it]
 94%|█████████▍| 465/496 [23:12<01:32,  2.97s/it]
 94%|█████████▍| 466/496 [23:15<01:26,  2.87s/it]
 94%|█████████▍| 467/496 [23:17<01:19,  2.76s/it]
 94%|█████████▍| 468/496 [23:20<01:17,  2.78s/it]
 95%|█████████▍| 469/496 [23:23<01:17,  2.87s/it]
 95%|█████████▍| 470/496 [23:26<01:15,  2.89s/it]
 95%|█████████▍| 471/496 [23:29<01:11,  2.86s/it]
 95%|█████████▌| 472/496 [23:32<01:09,  2.91s/it]
 95%|█████████▌| 473/496 [23:34<01:04,  2.79s/it]
 96%|█████████▌| 474/496 [23:37<01:02,  2.85s/it]
 96%|█████████▌| 475/496 [23:40<00:59,  2.84s/it]
 96%|█████████▌| 476/496 [23:43<00:55,  2.80s/it]
 96%|█████████▌| 477/496 [23:46<00:53,  2.82s/it]
 96%|█████████▋| 478/496 [23:49<00:51,  2.86s/it]
 97%|█████████▋| 479/496 [23:51<00:47,  2.79s/it]
 97%|█████████▋| 480/496 [23:54<00:46,  2.88s/it]
 97%|█████████▋| 481/496 [23:57<00:44,  2.95s/it]
 97%|█████████▋| 482/496 [24:00<00:41,  2.95s/it]
 97%|█████████▋| 483/496 [24:03<00:38,  2.93s/it]
 98%|█████████▊| 484/496 [24:07<00:36,  3.07s/it]
 98%|█████████▊| 485/496 [24:09<00:33,  3.00s/it]
 98%|█████████▊| 486/496 [24:12<00:29,  2.94s/it]
 98%|█████████▊| 487/496 [24:15<00:27,  3.02s/it]
 98%|█████████▊| 488/496 [24:18<00:23,  3.00s/it]
 99%|█████████▊| 489/496 [24:21<00:20,  2.96s/it]
 99%|█████████▉| 490/496 [24:24<00:17,  2.91s/it]
 99%|█████████▉| 491/496 [24:27<00:14,  3.00s/it]
 99%|█████████▉| 492/496 [24:30<00:11,  2.98s/it]
 99%|█████████▉| 493/496 [24:33<00:09,  3.06s/it]
+[INFO|trainer.py:2700] 2022-12-17 18:33:47,930 >> Saving model checkpoint to ./
+[INFO|configuration_utils.py:447] 2022-12-17 18:33:47,931 >> Configuration saved in ./config.json
+[INFO|modeling_utils.py:1680] 2022-12-17 18:33:48,292 >> Model weights saved in ./pytorch_model.bin
+[INFO|feature_extraction_utils.py:368] 2022-12-17 18:33:48,308 >> Feature extractor saved in ./preprocessor_config.json
+[INFO|tokenization_utils_base.py:2157] 2022-12-17 18:33:48,308 >> tokenizer config file saved in ./tokenizer_config.json
+[INFO|tokenization_utils_base.py:2164] 2022-12-17 18:33:48,309 >> Special tokens file saved in ./special_tokens_map.json
+[INFO|tokenization_utils_base.py:2210] 2022-12-17 18:33:48,309 >> added tokens file saved in ./added_tokens.json

trainer_state.json

@@ -0,0 +1,805 @@
+{
+  "best_metric": 12.206885082321635,
+  "best_model_checkpoint": "./checkpoint-6000",
+  "epoch": 1.0958333333333334,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 2.996,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.4e-06,
+      "loss": 1.9547,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.94e-05,
+      "loss": 0.7554,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.94e-05,
+      "loss": 0.5206,
+      "step": 150
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.94e-05,
+      "loss": 0.4737,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.94e-05,
+      "loss": 0.3952,
+      "step": 250
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.94e-05,
+      "loss": 0.3662,
+      "step": 300
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 6.939999999999999e-05,
+      "loss": 0.3557,
+      "step": 350
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 7.94e-05,
+      "loss": 0.3687,
+      "step": 400
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.94e-05,
+      "loss": 0.3288,
+      "step": 450
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.94e-05,
+      "loss": 0.2986,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.914545454545455e-05,
+      "loss": 0.3076,
+      "step": 550
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.823636363636364e-05,
+      "loss": 0.2977,
+      "step": 600
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.732727272727273e-05,
+      "loss": 0.3167,
+      "step": 650
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.641818181818182e-05,
+      "loss": 0.2799,
+      "step": 700
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.550909090909092e-05,
+      "loss": 0.2079,
+      "step": 750
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.46e-05,
+      "loss": 0.2246,
+      "step": 800
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.36909090909091e-05,
+      "loss": 0.2568,
+      "step": 850
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.278181818181819e-05,
+      "loss": 0.2734,
+      "step": 900
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.187272727272727e-05,
+      "loss": 0.183,
+      "step": 950
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.096363636363638e-05,
+      "loss": 0.2445,
+      "step": 1000
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.3058685064315796,
+      "eval_runtime": 2133.1044,
+      "eval_samples_per_second": 7.441,
+      "eval_steps_per_second": 0.233,
+      "eval_wer": 32.41627267903669,
+      "step": 1000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.005454545454545e-05,
+      "loss": 0.1608,
+      "step": 1050
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 8.914545454545455e-05,
+      "loss": 0.1718,
+      "step": 1100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.823636363636364e-05,
+      "loss": 0.1721,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 8.732727272727273e-05,
+      "loss": 0.1762,
+      "step": 1200
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 8.641818181818182e-05,
+      "loss": 0.1587,
+      "step": 1250
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 8.550909090909092e-05,
+      "loss": 0.2133,
+      "step": 1300
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 8.46e-05,
+      "loss": 0.2291,
+      "step": 1350
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 8.36909090909091e-05,
+      "loss": 0.1172,
+      "step": 1400
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 8.278181818181819e-05,
+      "loss": 0.1034,
+      "step": 1450
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 8.187272727272728e-05,
+      "loss": 0.1746,
+      "step": 1500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 8.096363636363636e-05,
+      "loss": 0.1649,
+      "step": 1550
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 8.005454545454547e-05,
+      "loss": 0.1153,
+      "step": 1600
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 7.914545454545454e-05,
+      "loss": 0.1521,
+      "step": 1650
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 7.823636363636364e-05,
+      "loss": 0.1684,
+      "step": 1700
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 7.732727272727273e-05,
+      "loss": 0.2243,
+      "step": 1750
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 7.641818181818182e-05,
+      "loss": 0.2149,
+      "step": 1800
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 7.550909090909092e-05,
+      "loss": 0.1927,
+      "step": 1850
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 7.46e-05,
+      "loss": 0.2019,
+      "step": 1900
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.36909090909091e-05,
+      "loss": 0.2003,
+      "step": 1950
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.278181818181819e-05,
+      "loss": 0.1823,
+      "step": 2000
+    },
+    {
+      "epoch": 0.33,
+      "eval_loss": 0.20035691559314728,
+      "eval_runtime": 2105.4622,
+      "eval_samples_per_second": 7.538,
+      "eval_steps_per_second": 0.236,
+      "eval_wer": 22.12587013850942,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.187272727272728e-05,
+      "loss": 0.1707,
+      "step": 2050
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.096363636363636e-05,
+      "loss": 0.1659,
+      "step": 2100
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 7.005454545454547e-05,
+      "loss": 0.193,
+      "step": 2150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 6.914545454545454e-05,
+      "loss": 0.1882,
+      "step": 2200
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 6.823636363636364e-05,
+      "loss": 0.163,
+      "step": 2250
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 6.732727272727273e-05,
+      "loss": 0.1689,
+      "step": 2300
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 6.641818181818182e-05,
+      "loss": 0.1585,
+      "step": 2350
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 6.550909090909091e-05,
+      "loss": 0.1643,
+      "step": 2400
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 6.460000000000001e-05,
+      "loss": 0.1634,
+      "step": 2450
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.369090909090909e-05,
+      "loss": 0.1362,
+      "step": 2500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.278181818181819e-05,
+      "loss": 0.1446,
+      "step": 2550
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 6.187272727272728e-05,
+      "loss": 0.1439,
+      "step": 2600
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 6.0963636363636366e-05,
+      "loss": 0.1534,
+      "step": 2650
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 6.0054545454545454e-05,
+      "loss": 0.1264,
+      "step": 2700
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 5.914545454545455e-05,
+      "loss": 0.1373,
+      "step": 2750
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.8236363636363645e-05,
+      "loss": 0.1406,
+      "step": 2800
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5.732727272727273e-05,
+      "loss": 0.1393,
+      "step": 2850
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.641818181818183e-05,
+      "loss": 0.1377,
+      "step": 2900
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5.550909090909091e-05,
+      "loss": 0.1467,
+      "step": 2950
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5.4600000000000006e-05,
+      "loss": 0.1412,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.17524316906929016,
+      "eval_runtime": 2121.3824,
+      "eval_samples_per_second": 7.482,
+      "eval_steps_per_second": 0.234,
+      "eval_wer": 20.070007048220916,
+      "step": 3000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 5.3690909090909094e-05,
+      "loss": 0.1186,
+      "step": 3050
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 5.278181818181819e-05,
+      "loss": 0.1437,
+      "step": 3100
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 5.187272727272727e-05,
+      "loss": 0.1287,
+      "step": 3150
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 5.096363636363637e-05,
+      "loss": 0.1242,
+      "step": 3200
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5.0054545454545455e-05,
+      "loss": 0.1431,
+      "step": 3250
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.914545454545455e-05,
+      "loss": 0.1316,
+      "step": 3300
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.823636363636364e-05,
+      "loss": 0.1119,
+      "step": 3350
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.7327272727272734e-05,
+      "loss": 0.1286,
+      "step": 3400
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.641818181818182e-05,
+      "loss": 0.1479,
+      "step": 3450
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.550909090909091e-05,
+      "loss": 0.1144,
+      "step": 3500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.46e-05,
+      "loss": 0.1071,
+      "step": 3550
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.3690909090909095e-05,
+      "loss": 0.1525,
+      "step": 3600
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.2781818181818184e-05,
+      "loss": 0.1158,
+      "step": 3650
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.187272727272727e-05,
+      "loss": 0.1111,
+      "step": 3700
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.096363636363637e-05,
+      "loss": 0.1237,
+      "step": 3750
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.0054545454545456e-05,
+      "loss": 0.154,
+      "step": 3800
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.9145454545454545e-05,
+      "loss": 0.1298,
+      "step": 3850
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.823636363636364e-05,
+      "loss": 0.1273,
+      "step": 3900
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.732727272727273e-05,
+      "loss": 0.121,
+      "step": 3950
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.641818181818182e-05,
+      "loss": 0.1093,
+      "step": 4000
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 0.14134088158607483,
+      "eval_runtime": 2102.7704,
+      "eval_samples_per_second": 7.548,
+      "eval_steps_per_second": 0.236,
+      "eval_wer": 16.053313059799006,
+      "step": 4000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.5509090909090905e-05,
+      "loss": 0.1054,
+      "step": 4050
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.46e-05,
+      "loss": 0.1305,
+      "step": 4100
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.3690909090909096e-05,
+      "loss": 0.1138,
+      "step": 4150
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.2781818181818185e-05,
+      "loss": 0.1275,
+      "step": 4200
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.187272727272727e-05,
+      "loss": 0.0885,
+      "step": 4250
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.096363636363637e-05,
+      "loss": 0.1089,
+      "step": 4300
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.0054545454545457e-05,
+      "loss": 0.0838,
+      "step": 4350
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.914545454545455e-05,
+      "loss": 0.0833,
+      "step": 4400
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.8236363636363637e-05,
+      "loss": 0.0968,
+      "step": 4450
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.732727272727273e-05,
+      "loss": 0.0962,
+      "step": 4500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.641818181818182e-05,
+      "loss": 0.0779,
+      "step": 4550
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.550909090909091e-05,
+      "loss": 0.1033,
+      "step": 4600
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.46e-05,
+      "loss": 0.0762,
+      "step": 4650
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.369090909090909e-05,
+      "loss": 0.1111,
+      "step": 4700
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.2781818181818182e-05,
+      "loss": 0.0875,
+      "step": 4750
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.1872727272727274e-05,
+      "loss": 0.1337,
+      "step": 4800
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.0963636363636366e-05,
+      "loss": 0.1232,
+      "step": 4850
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.0054545454545458e-05,
+      "loss": 0.1153,
+      "step": 4900
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.9145454545454546e-05,
+      "loss": 0.1189,
+      "step": 4950
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.8236363636363638e-05,
+      "loss": 0.1137,
+      "step": 5000
+    },
+    {
+      "epoch": 0.83,
+      "eval_loss": 0.11552777886390686,
+      "eval_runtime": 2104.6449,
+      "eval_samples_per_second": 7.541,
+      "eval_steps_per_second": 0.236,
+      "eval_wer": 13.31084238118996,
+      "step": 5000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.7327272727272727e-05,
+      "loss": 0.1159,
+      "step": 5050
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.641818181818182e-05,
+      "loss": 0.1152,
+      "step": 5100
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.550909090909091e-05,
+      "loss": 0.1051,
+      "step": 5150
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.4599999999999999e-05,
+      "loss": 0.1196,
+      "step": 5200
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.3690909090909091e-05,
+      "loss": 0.117,
+      "step": 5250
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2781818181818183e-05,
+      "loss": 0.0972,
+      "step": 5300
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.1872727272727273e-05,
+      "loss": 0.0965,
+      "step": 5350
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.0963636363636365e-05,
+      "loss": 0.1008,
+      "step": 5400
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0054545454545455e-05,
+      "loss": 0.0843,
+      "step": 5450
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 9.145454545454546e-06,
+      "loss": 0.0583,
+      "step": 5500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 8.236363636363636e-06,
+      "loss": 0.06,
+      "step": 5550
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 7.327272727272727e-06,
+      "loss": 0.0601,
+      "step": 5600
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 6.418181818181819e-06,
+      "loss": 0.0591,
+      "step": 5650
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 5.50909090909091e-06,
+      "loss": 0.0608,
+      "step": 5700
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 4.6e-06,
+      "loss": 0.0628,
+      "step": 5750
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.6909090909090915e-06,
+      "loss": 0.0636,
+      "step": 5800
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.781818181818182e-06,
+      "loss": 0.0654,
+      "step": 5850
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.8727272727272728e-06,
+      "loss": 0.061,
+      "step": 5900
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.636363636363636e-07,
+      "loss": 0.0559,
+      "step": 5950
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 5.454545454545455e-08,
+      "loss": 0.0585,
+      "step": 6000
+    },
+    {
+      "epoch": 1.1,
+      "eval_loss": 0.10796044021844864,
+      "eval_runtime": 2137.698,
+      "eval_samples_per_second": 7.425,
+      "eval_steps_per_second": 0.232,
+      "eval_wer": 12.206885082321635,
+      "step": 6000
+    },
+    {
+      "epoch": 1.1,
+      "step": 6000,
+      "total_flos": 2.490351440560128e+19,
+      "train_loss": 0.17721048017342886,
+      "train_runtime": 61737.3829,
+      "train_samples_per_second": 6.22,
+      "train_steps_per_second": 0.097
+    }
+  ],
+  "max_steps": 6000,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 2.490351440560128e+19,
+  "trial_name": null,
+  "trial_params": null
+}