0%|                                                                                          | 0/3567 [00:00<?, ?it/s][WARNING|modeling_utils.py:388] 2022-03-02 09:41:39,040 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
{'loss': 10.579, 'learning_rate': 2e-08, 'epoch': 0.0}
[WARNING|modeling_utils.py:388] 2022-03-02 09:41:40,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
  0%|                                                                                | 1/3567 [00:02<2:48:28,  2.83s/it]
  0%|                                                                                | 1/3567 [00:02<2:48:28,  2.83s/it][WARNING|modeling_utils.py:388] 2022-03-02 09:41:41,519 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
[WARNING|modeling_utils.py:388] 2022-03-02 09:41:42,571 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
  0%|                                                                                | 2/3567 [00:05<2:28:00,  2.49s/it]
  0%|                                                                                | 2/3567 [00:05<2:28:00,  2.49s/it][WARNING|modeling_utils.py:388] 2022-03-02 09:41:43,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
[WARNING|modeling_utils.py:388] 2022-03-02 09:41:44,870 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
  0%|                                                                                | 3/3567 [00:07<2:22:42,  2.40s/it]
  0%|                                                                                | 3/3567 [00:07<2:22:42,  2.40s/it][WARNING|modeling_utils.py:388] 2022-03-02 09:41:46,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
[WARNING|modeling_utils.py:388] 2022-03-02 09:41:47,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed

  0%|                                                                                | 4/3567 [00:09<2:18:43,  2.34s/it][WARNING|modeling_utils.py:388] 2022-03-02 09:41:48,306 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
{'loss': 10.4912, 'learning_rate': 1.0000000000000001e-07, 'epoch': 0.0}
[WARNING|modeling_utils.py:388] 2022-03-02 09:41:49,365 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
  0%|                                                                                | 5/3567 [00:11<2:17:02,  2.31s/it][WARNING|modeling_utils.py:388] 2022-03-02 09:41:50,580 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
[WARNING|modeling_utils.py:388] 2022-03-02 09:41:51,633 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
  0%|▏                                                                               | 6/3567 [00:14<2:16:12,  2.30s/it][WARNING|modeling_utils.py:388] 2022-03-02 09:41:52,779 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
{'loss': 10.5017, 'learning_rate': 1.2000000000000002e-07, 'epoch': 0.0}
[WARNING|modeling_utils.py:388] 2022-03-02 09:41:53,836 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed
  0%|▏                                                                               | 7/3567 [00:16<2:14:23,  2.27s/it][WARNING|modeling_utils.py:388] 2022-03-02 09:41:54,973 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed