Training in progress, step 4000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:944c1d6b08a21304a7ef94644fa7d9a1b0339ac8db2840865316da5264c3850b
+oid sha256:38caf6d8a9c2b7c18aca76fa2d4a9f08a3ed0a3e45016695116c2fbd41ee2652
 size 3025686376

runs/Mar27_19-04-06_hf-dgx-01/events.out.tfevents.1711562657.hf-dgx-01.1893386.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84eb09edac34b6f730fc5972ebb7401f0b96a5e0db9c5c5ebbeb3ccdd9d2612a
-size 31639
+oid sha256:8396ee90e66bcd7c2aee0da8f2c08987080a79f3b01330943b772a7bcc9cb9d5
+size 40397

wandb/run-20240327_190418-lwtbcr8s/files/output.log

@@ -3484,3 +3484,1160 @@ Non-default generation parameters: {'max_length': 448, 'begin_suppress_tokens':
 
  60%|█████████████████████████████████████████████▍                             | 3025/5000 [5:10:36<1:29:13,  2.71s/it]
 
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 61%|█████████████████████████████████████████████▊                             | 3050/5000 [5:11:43<1:27:10,  2.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 62%|██████████████████████████████████████████████▏                            | 3075/5000 [5:12:51<1:26:00,  2.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 62%|██████████████████████████████████████████████▌                            | 3100/5000 [5:13:58<1:24:53,  2.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 62%|██████████████████████████████████████████████▉                            | 3125/5000 [5:15:16<1:23:58,  2.69s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 63%|███████████████████████████████████████████████▎                           | 3150/5000 [5:16:23<1:22:33,  2.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 64%|███████████████████████████████████████████████▋                           | 3175/5000 [5:17:30<1:21:31,  2.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 64%|████████████████████████████████████████████████                           | 3200/5000 [5:18:37<1:20:15,  2.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 64%|████████████████████████████████████████████████▍                          | 3225/5000 [5:19:44<1:19:14,  2.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 65%|████████████████████████████████████████████████▊                          | 3250/5000 [5:20:50<1:18:05,  2.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 66%|█████████████████████████████████████████████████▏                         | 3275/5000 [5:21:57<1:17:01,  2.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 66%|█████████████████████████████████████████████████▌                         | 3300/5000 [5:23:04<1:15:50,  2.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 66%|█████████████████████████████████████████████████▉                         | 3325/5000 [5:24:11<1:14:38,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 67%|██████████████████████████████████████████████████▎                        | 3350/5000 [5:25:29<1:13:32,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 68%|██████████████████████████████████████████████████▋                        | 3375/5000 [5:26:36<1:12:26,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 68%|███████████████████████████████████████████████████                        | 3400/5000 [5:27:43<1:11:22,  2.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 68%|███████████████████████████████████████████████████▍                       | 3425/5000 [5:28:50<1:10:19,  2.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 69%|███████████████████████████████████████████████████▋                       | 3449/5000 [5:29:54<1:09:04,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 69%|█████████████████████████████████████████████████��██                       | 3474/5000 [5:31:01<1:08:00,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 70%|████████████████████████████████████████████████████▍                      | 3499/5000 [5:32:08<1:06:52,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 70%|████████████████████████████████████████████████████▊                      | 3524/5000 [5:33:15<1:05:42,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 71%|█████████████████████████████████████████████████████▏                     | 3549/5000 [5:34:22<1:04:40,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 71%|█████████████████████████████████████████████████████▌                     | 3574/5000 [5:35:39<1:03:26,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 72%|█████████████████████████████████████████████████████▉                     | 3599/5000 [5:36:46<1:02:20,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 72%|██████████████████████████████████████████████████████▎                    | 3624/5000 [5:37:53<1:01:07,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 73%|██████████████████████████████████████████████████████▋                    | 3649/5000 [5:39:00<1:00:03,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 73%|████████████████████████████████████████████████████████▌                    | 3674/5000 [5:40:06<58:56,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 74%|████████████████████████████████████████████████████████▉                    | 3699/5000 [5:41:13<57:49,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 74%|█████████████████████████████████████████████████████████▎                   | 3724/5000 [5:42:20<56:51,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 75%|█████████████████████████████████████████████████████████▋                   | 3749/5000 [5:43:27<55:48,  2.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 75%|██████████████████████████████████████████████████████████                   | 3774/5000 [5:44:33<53:06,  2.60s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 76%|██████████████████████████████████████████████████████████▌                  | 3799/5000 [5:45:51<53:20,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 76%|██████████████████████████████████████████████████████████▉                  | 3824/5000 [5:46:58<52:11,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 77%|███████████████████████████████████████████████████████████▎                 | 3849/5000 [5:48:05<51:03,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 77%|███████████████████████████████████████████████████████████▋                 | 3874/5000 [5:49:11<49:58,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 78%|████████████████████████████████████████████████████████████                 | 3899/5000 [5:50:18<48:53,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 78%|████████████████████████████████████████████████████████████▍                | 3924/5000 [5:51:24<47:48,  2.67s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 79%|████████████████████████████████████████████████████████████▊                | 3949/5000 [5:52:31<46:38,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 79%|█████████████████████████████████████████████████████████████▏               | 3974/5000 [5:53:37<45:28,  2.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 80%|███████████████████████████████████████████████████████████▉               | 3999/5000 [5:54:55<1:11:54,  4.31s/it]
+ 80%|████████████████████████████████████████████████████████████               | 4000/5000 [5:54:58<1:03:34,  3.81s/it][INFO|trainer.py:768] 2024-03-28 00:59:17,414 >> The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.
+[INFO|trainer.py:3544] 2024-03-28 00:59:17,417 >> ***** Running Evaluation *****
+[INFO|trainer.py:3546] 2024-03-28 00:59:17,417 >>   Num examples = 3123
+[INFO|trainer.py:3549] 2024-03-28 00:59:17,417 >>   Batch size = 32
+[INFO|generation_whisper.py:1111] 2024-03-28 00:59:28,924 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+                                                                                                                        [INFO|generation_whisper.py:1111] 2024-03-28 00:59:34,506 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  0%|                                                                                            | 0/98 [00:00<?, ?it/s][INFO|generation_whisper.py:1111] 2024-03-28 00:59:40,103 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  2%|█▋                                                                                  | 2/98 [00:05<04:28,  2.80s/it][INFO|generation_whisper.py:1111] 2024-03-28 00:59:45,747 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  3%|██▌                                                                                 | 3/98 [00:11<06:18,  3.98s/it][INFO|generation_whisper.py:1111] 2024-03-28 00:59:51,326 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  4%|███▍                                                                                | 4/98 [00:16<07:10,  4.58s/it][INFO|generation_whisper.py:1111] 2024-03-28 00:59:56,998 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  5%|████▎                                                                               | 5/98 [00:22<07:41,  4.96s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:00:02,574 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  6%|█████▏                                                                              | 6/98 [00:28<07:55,  5.16s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:00:08,220 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  7%|██████                                                                              | 7/98 [00:33<08:04,  5.32s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:00:13,807 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  8%|██████▊                                                                             | 8/98 [00:39<08:06,  5.40s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:00:19,437 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+  9%|███████▋                                                                            | 9/98 [00:44<08:07,  5.47s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:00:25,057 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 10%|████████▍                                                                          | 10/98 [00:50<08:05,  5.52s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:00:30,692 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 11%|█████████▎                                                                         | 11/98 [00:56<08:03,  5.55s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:00:36,292 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 12%|██████████▏                                                                        | 12/98 [01:01<07:58,  5.57s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:00:41,856 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 13%|███████████                                                                        | 13/98 [01:07<07:53,  5.57s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:00:47,455 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 14%|███████████▊                                                                       | 14/98 [01:12<07:48,  5.58s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:00:53,129 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 15%|████████████▋                                                                      | 15/98 [01:18<07:45,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:00:58,713 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 16%|█████████████▌                                                                     | 16/98 [01:24<07:39,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:01:04,351 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 17%|██████████████▍                                                                    | 17/98 [01:29<07:34,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:01:09,943 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 18%|███████████████▏                                                                   | 18/98 [01:35<07:28,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:01:15,558 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 19%|████████████████                                                                   | 19/98 [01:41<07:23,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:01:21,175 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 20%|████████████████▉                                                                  | 20/98 [01:46<07:17,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:01:26,786 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 21%|██���██████████████▊                                                                 | 21/98 [01:52<07:12,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:01:32,439 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 22%|██████████████████▋                                                                | 22/98 [01:57<07:07,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:01:38,034 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 23%|███████████████████▍                                                               | 23/98 [02:03<07:01,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:01:43,641 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 24%|████████████████████▎                                                              | 24/98 [02:09<06:55,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:01:49,264 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 26%|█████████████████████▏                                                             | 25/98 [02:14<06:49,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:01:54,895 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 27%|██████████████████████                                                             | 26/98 [02:20<06:44,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:02:00,494 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 28%|██████████████████████▊                                                            | 27/98 [02:25<06:38,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:02:06,116 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 29%|███████████████████████▋                                                           | 28/98 [02:31<06:33,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:02:11,746 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 30%|████████████████████████▌                                                          | 29/98 [02:37<06:27,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:02:17,370 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 31%|█████████████████████████▍                                                         | 30/98 [02:42<06:22,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:02:22,949 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 32%|██████████████████████████▎                                                        | 31/98 [02:48<06:15,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:02:28,552 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 33%|███████████████████████████                                                        | 32/98 [02:54<06:10,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:02:34,249 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 34%|███████████████████████████▉                                                       | 33/98 [02:59<06:06,  5.63s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:02:39,768 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 35%|████████████████████████████▊                                                      | 34/98 [03:05<05:58,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:02:45,384 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 36%|█████████████████████████████▋                                                     | 35/98 [03:10<05:53,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:02:50,939 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 37%|██████████████████████████████▍                                                    | 36/98 [03:16<05:46,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:02:56,555 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 38%|███████████████████████████████▎                                                   | 37/98 [03:22<05:41,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:03:02,137 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 39%|████████████████████████████████▏                                                  | 38/98 [03:27<05:35,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:03:07,763 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 40%|█████████████████████████████████                                                  | 39/98 [03:33<05:30,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:03:13,324 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 41%|█████████████████████████████████▉                                                 | 40/98 [03:38<05:24,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:03:18,918 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 42%|██████████████████████████████████▋                                                | 41/98 [03:44<05:18,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:03:24,520 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 43%|███████████████████████████████████▌                                               | 42/98 [03:50<05:13,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:03:30,144 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 44%|████████████████████████████████████▍                                              | 43/98 [03:55<05:08,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:03:35,723 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 45%|█████████████████████████████████████▎                                             | 44/98 [04:01<05:02,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:03:41,333 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 46%|██████████████████████████████████████                                             | 45/98 [04:06<04:56,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:03:46,988 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 47%|██████████████████████████████████████▉                                            | 46/98 [04:12<04:52,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:03:52,689 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 48%|███████████████████████████████████████▊                                           | 47/98 [04:18<04:47,  5.64s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:03:58,282 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 49%|████████████████████████████████████████▋                                          | 48/98 [04:23<04:41,  5.63s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:04:03,949 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 50%|█████████████████████████████████████████▌                                         | 49/98 [04:29<04:36,  5.64s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:04:09,544 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 51%|██████████████████████████████████████████▎                                        | 50/98 [04:35<04:30,  5.63s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:04:15,107 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 52%|███████████████████████████████████████████▏                                       | 51/98 [04:40<04:23,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:04:20,697 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 53%|████████████████████████████████████████████                                       | 52/98 [04:46<04:17,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:04:26,347 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 54%|████████████████████████████████████████████▉                                      | 53/98 [04:51<04:12,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:04:32,010 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 55%|█████████████████████████████████████████████▋                                     | 54/98 [04:57<04:07,  5.63s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:04:37,618 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 56%|██████████████████████████████████████████████▌                                    | 55/98 [05:03<04:01,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:04:43,204 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 57%|███████████���███████████████████████████████████▍                                   | 56/98 [05:08<03:55,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:04:48,801 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 58%|████████████████████████████████████████████████▎                                  | 57/98 [05:14<03:49,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:04:54,404 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 59%|█████████████████████████████████████████████████                                  | 58/98 [05:19<03:44,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:05:00,017 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 60%|█████████████████████████████████████████████████▉                                 | 59/98 [05:25<03:38,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:05:05,607 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 61%|██████████████████████████████████████████████████▊                                | 60/98 [05:31<03:32,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:05:11,206 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 62%|███████████████████████████████████████████████████▋                               | 61/98 [05:36<03:27,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:05:16,781 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 63%|████████████████████████████████████████████████████▌                              | 62/98 [05:42<03:21,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:05:22,422 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 64%|█████████████████████████████████████████████████████▎                             | 63/98 [05:47<03:16,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:05:28,065 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 65%|██████████████████████████████████████████████████████▏                            | 64/98 [05:53<03:11,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:05:33,639 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 66%|███████████████████████████████████████████████████████                            | 65/98 [05:59<03:04,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:05:39,188 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 67%|███████████████████████████████████████████████████████▉                           | 66/98 [06:04<02:58,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:05:44,812 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 68%|████████████████████████████████████████████████████████▋                          | 67/98 [06:10<02:53,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:05:50,410 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 69%|█████████████████████████████████████████████████████████▌                         | 68/98 [06:15<02:47,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:05:56,040 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 70%|██████████████████████████████████████████████████████████▍                        | 69/98 [06:21<02:42,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:06:01,649 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 71%|███████████████████████████████████████████████████████████▎                       | 70/98 [06:27<02:37,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:06:07,248 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 72%|████████████████████████████████████████████████████████████▏                      | 71/98 [06:32<02:31,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:06:12,829 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 73%|████████████████████████████████████████████████████████████▉                      | 72/98 [06:38<02:25,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:06:18,397 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 74%|█████████████████████████████████████████████████████████████▊                     | 73/98 [06:43<02:19,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:06:24,028 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 76%|██████████████████████████████████████████████████████████████▋                    | 74/98 [06:49<02:14,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:06:29,696 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 77%|███████████████████████████████████████████████████████████████▌                   | 75/98 [06:55<02:09,  5.62s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:06:35,242 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 78%|████████████████████████████████████████████████████████████████▎                  | 76/98 [07:00<02:03,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:06:40,825 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 79%|█████████████████████████��███████████████████████████████████████▏                 | 77/98 [07:06<01:57,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:06:46,376 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 80%|██████████████████████████████████████████████████████████████████                 | 78/98 [07:11<01:51,  5.58s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:06:51,960 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 81%|██████████████████████████████████████████████████████████████████▉                | 79/98 [07:17<01:46,  5.58s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:06:57,546 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 82%|███████████████████████████████████████████████████████████████████▊               | 80/98 [07:23<01:40,  5.58s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:07:03,130 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 83%|████████████████████████████████████████████████████████████████████▌              | 81/98 [07:28<01:34,  5.58s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:07:08,771 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 84%|█████████████████████████████████████████████████████████████████████▍             | 82/98 [07:34<01:29,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:07:14,399 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 85%|██████████████████████████████████████████████████████████████████████▎            | 83/98 [07:39<01:24,  5.61s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:07:19,986 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 86%|███████████████████████████████████████████████████████████████████████▏           | 84/98 [07:45<01:18,  5.60s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:07:25,563 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 87%|███████████████████████████████████████████████████████████████████████▉           | 85/98 [07:51<01:12,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:07:31,086 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 88%|████████████████████████████████████████████████████████████████████████▊          | 86/98 [07:56<01:06,  5.57s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:07:36,689 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 89%|██████████████████████████���██████████████████████████████████████████████▋         | 87/98 [08:02<01:01,  5.58s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:07:42,264 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 90%|██████████████████████████████████████████████████████████████████████████▌        | 88/98 [08:07<00:55,  5.58s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:07:47,892 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 91%|███████████████████████████████████████████████████████████████████████████▍       | 89/98 [08:13<00:50,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:07:53,478 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 92%|████████████████████████████████████████████████████████████████████████████▏      | 90/98 [08:18<00:44,  5.59s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:07:59,038 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 93%|█████████████████████████████████████████████████████████████████████████████      | 91/98 [08:24<00:39,  5.58s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:08:04,609 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 94%|█████████████████████████████████████████████████████████████████████████████▉     | 92/98 [08:30<00:33,  5.58s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:08:10,183 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 95%|██████████████████████████████████████████████████████████████████████████████▊    | 93/98 [08:35<00:27,  5.58s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:08:15,714 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 96%|███████████████████████████████████████████████████████████████████████████████▌   | 94/98 [08:41<00:22,  5.56s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:08:21,298 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 97%|████████████████████████████████████████████████████████████████████████████████▍  | 95/98 [08:46<00:16,  5.57s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:08:26,878 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 98%|█████████████████████████████████████████████████████████████████████████████████▎ | 96/98 [08:52<00:11,  5.57s/it][INFO|generation_whisper.py:1111] 2024-03-28 01:08:32,616 >> You have passed task=transcribe, but also have set `forced_decoder_ids` to [[1, None], [2, 50360]] which creates a conflict. `forced_decoder_ids` will be ignored in favor of task=transcribe.
+ 99%|██████████████████████████████████████████████████████████████████████████████████▏| 97/98 [08:57<00:05,  5.59s/it]
+ 80%|████████████████████████████████████████████████████████████               | 4000/5000 [6:04:17<1:03:34,  3.81s/it][INFO|trainer.py:3235] 2024-03-28 01:08:36,699 >> Saving model checkpoint to ./checkpoint-4000
+[WARNING|configuration_utils.py:447] 2024-03-28 01:08:36,699 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
+Non-default generation parameters: {'max_length': 448, 'begin_suppress_tokens': [220, 50257]}
+[INFO|configuration_utils.py:471] 2024-03-28 01:08:36,700 >> Configuration saved in ./checkpoint-4000/config.json
+[INFO|configuration_utils.py:697] 2024-03-28 01:08:36,701 >> Configuration saved in ./checkpoint-4000/generation_config.json
+[INFO|modeling_utils.py:2475] 2024-03-28 01:08:44,304 >> Model weights saved in ./checkpoint-4000/model.safetensors
+[INFO|feature_extraction_utils.py:424] 2024-03-28 01:08:44,306 >> Feature extractor saved in ./checkpoint-4000/preprocessor_config.json
+[INFO|feature_extraction_utils.py:424] 2024-03-28 01:09:06,517 >> Feature extractor saved in ./preprocessor_config.json
+[INFO|trainer.py:3327] 2024-03-28 01:09:06,519 >> Deleting older checkpoint [checkpoint-3000] due to args.save_total_limit
+/home/sanchit/hf/lib/python3.8/site-packages/torch/utils/checkpoint.py:460: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
+  warnings.warn(
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 80%|█████████████████████████████████████████████████████████████▉               | 4025/5000 [6:05:54<43:45,  2.69s/it]
+
+
+
+
+
+

wandb/run-20240327_190418-lwtbcr8s/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 0.0063, "train/grad_norm": 0.51263427734375, "train/learning_rate": 4.4000000000000006e-05, "train/epoch": 13.63, "train/global_step": 3025, "_timestamp": 1711581296.0875716, "_runtime": 18637.522981643677, "_step": 123, "eval/loss": 0.5476499795913696, "eval/wer": 0.35351155064513634, "eval/runtime": 560.2614, "eval/samples_per_second": 5.574, "eval/steps_per_second": 0.175}
+{"train/loss": 0.0005, "train/grad_norm": 0.018902545794844627, "train/learning_rate": 2.177777777777778e-05, "train/epoch": 18.13, "train/global_step": 4025, "_timestamp": 1711584613.86865, "_runtime": 21955.3040599823, "_step": 164, "eval/loss": 0.5731213092803955, "eval/wer": 0.33979757397821214, "eval/runtime": 559.2789, "eval/samples_per_second": 5.584, "eval/steps_per_second": 0.175}

wandb/run-20240327_190418-lwtbcr8s/run-lwtbcr8s.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3ca7bfb8672fa56c8c9fef11a8b0a2abb579ac6859d19baf45b9a34bae8c78e
-size 4084243
+oid sha256:311c7a1ba8ad47da67a2e6ad4f3ceef30a17026ee75c8a4adda40a1fea48fef4
+size 5046509