diff --git "a/wandb/run-20220301_141622-dv1pefph/files/output.log" "b/wandb/run-20220301_141622-dv1pefph/files/output.log" new file mode 100644--- /dev/null +++ "b/wandb/run-20220301_141622-dv1pefph/files/output.log" @@ -0,0 +1,1620 @@ + + + 0%| | 0/1019 [00:00> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:16:30,387 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 0%| | 1/1019 [00:06<1:54:08, 6.73s/it] + + 0%| | 1/1019 [00:06<1:54:08, 6.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:16:33,381 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:16:36,312 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 0%|▏ | 2/1019 [00:12<1:46:01, 6.26s/it] + + 0%|▏ | 2/1019 [00:12<1:46:01, 6.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:16:39,256 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:16:42,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 0%|▏ | 3/1019 [00:18<1:44:34, 6.18s/it] + + 0%|▏ | 3/1019 [00:18<1:44:34, 6.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:16:45,436 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.86, 'learning_rate': 1.2000000000000002e-07, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-03-01 14:16:48,337 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 0%|▎ | 4/1019 [00:24<1:43:17, 6.11s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:16:51,291 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6573, 'learning_rate': 1.8e-07, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-03-01 14:16:54,112 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 0%|▍ | 5/1019 [00:30<1:41:10, 5.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:16:57,077 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:16:59,930 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▍ | 6/1019 [00:36<1:40:05, 5.93s/it] + + 1%|▍ | 6/1019 [00:36<1:40:05, 5.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:17:02,861 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7021, 'learning_rate': 3.0000000000000004e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-03-01 14:17:05,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▌ | 7/1019 [00:42<1:38:48, 5.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:17:08,494 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.837, 'learning_rate': 3.6e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-03-01 14:17:11,297 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▋ | 8/1019 [00:47<1:37:37, 5.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:17:14,153 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9707, 'learning_rate': 3.6e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-03-01 14:17:16,984 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▋ | 9/1019 [00:53<1:36:40, 5.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:17:19,821 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:17:22,581 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8212, 'learning_rate': 4.2e-07, 'epoch': 0.01} + + 1%|▊ | 10/1019 [00:58<1:36:06, 5.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:17:25,526 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8562, 'learning_rate': 4.800000000000001e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-03-01 14:17:28,262 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▊ | 11/1019 [01:04<1:35:50, 5.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:17:31,116 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8799, 'learning_rate': 5.4e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-03-01 14:17:33,863 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▉ | 12/1019 [01:10<1:35:11, 5.67s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:17:36,722 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8682, 'learning_rate': 6.000000000000001e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-03-01 14:17:39,416 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|█ | 13/1019 [01:15<1:34:30, 5.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:17:42,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.78, 'learning_rate': 6.599999999999999e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-03-01 14:17:44,956 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|█ | 14/1019 [01:21<1:33:55, 5.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:17:47,791 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7108, 'learning_rate': 7.2e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-03-01 14:17:50,461 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|█▏ | 15/1019 [01:26<1:33:18, 5.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:17:53,271 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9448, 'learning_rate': 7.799999999999999e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-03-01 14:17:55,867 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▏ | 16/1019 [01:32<1:32:21, 5.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:17:58,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7769, 'learning_rate': 8.4e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-03-01 14:18:01,232 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▎ | 17/1019 [01:37<1:31:27, 5.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:18:03,913 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.0294, 'learning_rate': 9e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-03-01 14:18:06,481 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▍ | 18/1019 [01:42<1:30:14, 5.41s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:18:09,185 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:18:11,763 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▍ | 19/1019 [01:48<1:29:30, 5.37s/it] + + 2%|█▍ | 19/1019 [01:48<1:29:30, 5.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:18:14,473 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8765, 'learning_rate': 1.0200000000000002e-06, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-03-01 14:18:17,018 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▌ | 20/1019 [01:53<1:28:51, 5.34s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:18:19,671 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:18:22,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▋ | 21/1019 [01:58<1:28:10, 5.30s/it] + + 2%|█▋ | 21/1019 [01:58<1:28:10, 5.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:18:24,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6939, 'learning_rate': 1.14e-06, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-03-01 14:18:27,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▋ | 22/1019 [02:03<1:27:39, 5.28s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:18:30,058 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:18:32,586 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▊ | 23/1019 [02:08<1:26:51, 5.23s/it] + + 2%|█▊ | 23/1019 [02:08<1:26:51, 5.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:18:35,179 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.001, 'learning_rate': 1.26e-06, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-03-01 14:18:37,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▊ | 24/1019 [02:14<1:26:07, 5.19s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:18:40,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:18:42,787 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▉ | 25/1019 [02:19<1:25:33, 5.16s/it] + + 2%|█▉ | 25/1019 [02:19<1:25:33, 5.16s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:18:45,408 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9024, 'learning_rate': 1.38e-06, 'epoch': 0.03} +[WARNING|modeling_utils.py:388] 2022-03-01 14:18:47,808 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 3%|██ | 26/1019 [02:24<1:24:45, 5.12s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:18:50,372 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:18:52,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██ | 27/1019 [02:29<1:23:53, 5.07s/it] + + 3%|██ | 27/1019 [02:29<1:23:53, 5.07s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:18:55,297 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:18:57,732 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▏ | 28/1019 [02:34<1:23:14, 5.04s/it] + + 3%|██▏ | 28/1019 [02:34<1:23:14, 5.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:19:00,279 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6461, 'learning_rate': 1.5599999999999999e-06, 'epoch': 0.03} +[WARNING|modeling_utils.py:388] 2022-03-01 14:19:02,697 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 3%|██▏ | 29/1019 [02:39<1:22:47, 5.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:19:05,192 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:19:07,576 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 30/1019 [02:43<1:22:01, 4.98s/it] + + 3%|██▎ | 30/1019 [02:43<1:22:01, 4.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:19:10,091 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:19:12,465 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7906, 'learning_rate': 1.68e-06, 'epoch': 0.03} + + 3%|██▍ | 31/1019 [02:48<1:21:30, 4.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:19:14,904 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:19:17,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▍ | 32/1019 [02:53<1:20:37, 4.90s/it] + + 3%|██▍ | 32/1019 [02:53<1:20:37, 4.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:19:19,649 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:19:21,898 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▌ | 33/1019 [02:58<1:19:16, 4.82s/it] + + 3%|██▌ | 33/1019 [02:58<1:19:16, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:19:24,285 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:19:26,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▋ | 34/1019 [03:02<1:18:16, 4.77s/it] + + 3%|██▋ | 34/1019 [03:02<1:18:16, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:19:28,876 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:19:31,067 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▋ | 35/1019 [03:07<1:17:02, 4.70s/it] + + 3%|██▋ | 35/1019 [03:07<1:17:02, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:19:33,351 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:19:35,557 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▊ | 36/1019 [03:11<1:15:56, 4.63s/it] + + 4%|██▊ | 36/1019 [03:11<1:15:56, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:19:37,826 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:19:39,951 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▊ | 37/1019 [03:16<1:14:40, 4.56s/it] + + 4%|██▊ | 37/1019 [03:16<1:14:40, 4.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:19:42,120 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:19:44,210 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|█��▉ | 38/1019 [03:20<1:13:06, 4.47s/it] + + 4%|██▉ | 38/1019 [03:20<1:13:06, 4.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:19:46,298 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:19:48,287 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███ | 39/1019 [03:24<1:11:06, 4.35s/it] + + 4%|███ | 39/1019 [03:24<1:11:06, 4.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:19:50,307 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:19:52,204 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███ | 40/1019 [03:28<1:08:53, 4.22s/it] + + 4%|███ | 40/1019 [03:28<1:08:53, 4.22s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:19:54,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:19:56,005 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▏ | 41/1019 [03:32<1:06:45, 4.10s/it] + + 4%|███▏ | 41/1019 [03:32<1:06:45, 4.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:19:57,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6884, 'learning_rate': 2.34e-06, 'epoch': 0.04} +[WARNING|modeling_utils.py:388] 2022-03-01 14:19:59,588 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▎ | 42/1019 [03:35<1:04:11, 3.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:01,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:20:02,854 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▎ | 43/1019 [03:39<1:00:49, 3.74s/it] + + 4%|███▎ | 43/1019 [03:39<1:00:49, 3.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:04,446 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:20:05,848 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 44/1019 [03:42<57:08, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:07,269 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7399, 'learning_rate': 2.46e-06, 'epoch': 0.04} +[WARNING|modeling_utils.py:388] 2022-03-01 14:20:08,476 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▌ | 45/1019 [03:44<52:44, 3.25s/it] + 4%|███▌ | 45/1019 [03:44<52:44, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:09,710 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:20:10,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 46/1019 [03:47<48:13, 2.97s/it] + 5%|███▋ | 46/1019 [03:47<48:13, 2.97s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:11,922 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:20:12,884 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 47/1019 [03:49<43:48, 2.70s/it] + 5%|███▋ | 47/1019 [03:49<43:48, 2.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:13,889 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:20:14,730 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 48/1019 [03:51<39:36, 2.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:15,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.1418, 'learning_rate': 2.7e-06, 'epoch': 0.05} +[WARNING|modeling_utils.py:388] 2022-03-01 14:20:16,317 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 49/1019 [03:52<35:22, 2.19s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:17,098 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.4682, 'learning_rate': 2.76e-06, 'epoch': 0.05} +[WARNING|modeling_utils.py:388] 2022-03-01 14:20:18,256 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 50/1019 [03:54<33:52, 2.10s/it] + 5%|███▉ | 50/1019 [03:54<33:52, 2.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:21,446 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 51/1019 [04:00<54:06, 3.35s/it]g-point operations will not be computed-01 14:20:21,446 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 51/1019 [04:00<54:06, 3.35s/it]g-point operations will not be computed-01 14:20:21,446 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 51/1019 [04:00<54:06, 3.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:27,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 51/1019 [04:00<54:06, 3.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:27,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 52/1019 [04:06<1:06:40, 4.14s/it]g-point operations will not be computed-01 14:20:27,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 52/1019 [04:06<1:06:40, 4.14s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:33,457 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 52/1019 [04:06<1:06:40, 4.14s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:33,457 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 53/1019 [04:12<1:15:14, 4.67s/it]g-point operations will not be computed-01 14:20:33,457 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 53/1019 [04:12<1:15:14, 4.67s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:39,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▏ | 54/1019 [04:18<1:21:09, 5.05s/it]g-point operations will not be computed-01 14:20:39,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▏ | 54/1019 [04:18<1:21:09, 5.05s/it]g-point operations will not be computed-01 14:20:39,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▏ | 54/1019 [04:18<1:21:09, 5.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:45,247 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▏ | 54/1019 [04:18<1:21:09, 5.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:45,247 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 55/1019 [04:24<1:24:33, 5.26s/it]g-point operations will not be computed-01 14:20:45,247 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 55/1019 [04:24<1:24:33, 5.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:51,008 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 55/1019 [04:24<1:24:33, 5.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:51,008 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 56/1019 [04:30<1:27:05, 5.43s/it]g-point operations will not be computed-01 14:20:51,008 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 56/1019 [04:30<1:27:05, 5.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:56,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 56/1019 [04:30<1:27:05, 5.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:20:56,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 57/1019 [04:36<1:29:05, 5.56s/it]g-point operations will not be computed-01 14:20:56,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 57/1019 [04:36<1:29:05, 5.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:02,656 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 57/1019 [04:36<1:29:05, 5.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:02,656 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 58/1019 [04:41<1:30:00, 5.62s/it]g-point operations will not be computed-01 14:21:02,656 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 58/1019 [04:41<1:30:00, 5.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:08,455 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 59/1019 [04:47<1:30:18, 5.64s/it]g-point operations will not be computed-01 14:21:08,455 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 59/1019 [04:47<1:30:18, 5.64s/it]g-point operations will not be computed-01 14:21:08,455 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 59/1019 [04:47<1:30:18, 5.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:14,061 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 59/1019 [04:47<1:30:18, 5.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:14,061 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 60/1019 [04:53<1:30:07, 5.64s/it]g-point operations will not be computed-01 14:21:14,061 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 60/1019 [04:53<1:30:07, 5.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:19,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 60/1019 [04:53<1:30:07, 5.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:19,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 61/1019 [04:58<1:29:23, 5.60s/it]g-point operations will not be computed-01 14:21:19,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 61/1019 [04:58<1:29:23, 5.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:25,128 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + g-point operations will not be computed-01 14:21:25,128 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + g-point operations will not be computed-01 14:21:25,128 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 62/1019 [05:04<1:29:06, 5.59s/it]g-point operations will not be computed-01 14:21:25,128 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 62/1019 [05:04<1:29:06, 5.59s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:30,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 63/1019 [05:09<1:28:31, 5.56s/it]g-point operations will not be computed-01 14:21:30,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 63/1019 [05:09<1:28:31, 5.56s/it]g-point operations will not be computed-01 14:21:30,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 63/1019 [05:09<1:28:31, 5.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:36,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 63/1019 [05:09<1:28:31, 5.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:36,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 64/1019 [05:15<1:27:54, 5.52s/it]g-point operations will not be computed-01 14:21:36,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 64/1019 [05:15<1:27:54, 5.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:41,568 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 65/1019 [05:20<1:27:22, 5.50s/it]g-point operations will not be computed-01 14:21:41,568 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 65/1019 [05:20<1:27:22, 5.50s/it]g-point operations will not be computed-01 14:21:41,568 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 65/1019 [05:20<1:27:22, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:46,965 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 65/1019 [05:20<1:27:22, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:46,965 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 66/1019 [05:25<1:26:25, 5.44s/it]g-point operations will not be computed-01 14:21:46,965 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 66/1019 [05:25<1:26:25, 5.44s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:52,320 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 66/1019 [05:25<1:26:25, 5.44s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:52,320 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 67/1019 [05:31<1:26:24, 5.45s/it]g-point operations will not be computed-01 14:21:52,320 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 67/1019 [05:31<1:26:24, 5.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:21:57,707 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 68/1019 [05:36<1:25:50, 5.42s/it]g-point operations will not be computed-01 14:21:57,707 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 68/1019 [05:36<1:25:50, 5.42s/it]g-point operations will not be computed-01 14:21:57,707 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 68/1019 [05:36<1:25:50, 5.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:22:03,059 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 68/1019 [05:36<1:25:50, 5.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:22:03,059 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 69/1019 [05:42<1:25:10, 5.38s/it]g-point operations will not be computed-01 14:22:03,059 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 69/1019 [05:42<1:25:10, 5.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:22:08,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 70/1019 [05:47<1:24:13, 5.33s/it]g-point operations will not be computed-01 14:22:08,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 70/1019 [05:47<1:24:13, 5.33s/it]g-point operations will not be computed-01 14:22:08,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 70/1019 [05:47<1:24:13, 5.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:22:13,525 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 70/1019 [05:47<1:24:13, 5.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:22:13,525 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 71/1019 [05:52<1:23:39, 5.29s/it]g-point operations will not be computed-01 14:22:13,525 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 71/1019 [05:52<1:23:39, 5.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:22:18,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 72/1019 [05:57<1:23:21, 5.28s/it]g-point operations will not be computed-01 14:22:18,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 72/1019 [05:57<1:23:21, 5.28s/it]g-point operations will not be computed-01 14:22:18,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 72/1019 [05:57<1:23:21, 5.28s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:22:23,962 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 73/1019 [06:02<1:22:20, 5.22s/it]g-point operations will not be computed-01 14:22:23,962 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 73/1019 [06:02<1:22:20, 5.22s/it]g-point operations will not be computed-01 14:22:23,962 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 73/1019 [06:02<1:22:20, 5.22s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:22:29,054 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 74/1019 [06:07<1:21:51, 5.20s/it]g-point operations will not be computed-01 14:22:29,054 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 74/1019 [06:07<1:21:51, 5.20s/it]g-point operations will not be computed-01 14:22:29,054 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 74/1019 [06:07<1:21:51, 5.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:22:34,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 75/1019 [06:13<1:21:22, 5.17s/it]g-point operations will not be computed-01 14:22:34,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 75/1019 [06:13<1:21:22, 5.17s/it]g-point operations will not be computed-01 14:22:34,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 75/1019 [06:13<1:21:22, 5.17s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:22:39,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▉ | 76/1019 [06:18<1:20:55, 5.15s/it]g-point operations will not be computed-01 14:22:39,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▉ | 76/1019 [06:18<1:20:55, 5.15s/it]g-point operations will not be computed-01 14:22:39,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▉ | 76/1019 [06:18<1:20:55, 5.15s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:22:44,272 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▉ | 77/1019 [06:23<1:19:45, 5.08s/it]g-point operations will not be computed-01 14:22:44,272 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▉ | 77/1019 [06:23<1:19:45, 5.08s/it]g-point operations will not be computed-01 14:22:44,272 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▉ | 77/1019 [06:23<1:19:45, 5.08s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:22:49,236 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 78/1019 [06:28<1:19:05, 5.04s/it]g-point operations will not be computed-01 14:22:49,236 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 78/1019 [06:28<1:19:05, 5.04s/it]g-point operations will not be computed-01 14:22:49,236 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 78/1019 [06:28<1:19:05, 5.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:22:54,166 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:22:56,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 14:22:54,166 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:22:56,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 14:22:54,166 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 79/1019 [06:32<1:18:37, 5.02s/it]g-point operations will not be computed-01 14:22:54,166 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 79/1019 [06:32<1:18:37, 5.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:22:59,134 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▏ | 80/1019 [06:37<1:17:57, 4.98s/it]g-point operations will not be computed-01 14:22:59,134 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▏ | 80/1019 [06:37<1:17:57, 4.98s/it]g-point operations will not be computed-01 14:22:59,134 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▏ | 80/1019 [06:37<1:17:57, 4.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:03,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▎ | 81/1019 [06:42<1:17:09, 4.94s/it]g-point operations will not be computed-01 14:23:03,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▎ | 81/1019 [06:42<1:17:09, 4.94s/it]g-point operations will not be computed-01 14:23:03,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▎ | 81/1019 [06:42<1:17:09, 4.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:08,769 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▎ | 82/1019 [06:47<1:16:17, 4.89s/it]g-point operations will not be computed-01 14:23:08,769 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▎ | 82/1019 [06:47<1:16:17, 4.89s/it]g-point operations will not be computed-01 14:23:08,769 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▎ | 82/1019 [06:47<1:16:17, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:13,540 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▎ | 82/1019 [06:47<1:16:17, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:13,540 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▍ | 83/1019 [06:52<1:15:23, 4.83s/it]g-point operations will not be computed-01 14:23:13,540 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▍ | 83/1019 [06:52<1:15:23, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:18,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 84/1019 [06:56<1:14:28, 4.78s/it]g-point operations will not be computed-01 14:23:18,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 84/1019 [06:56<1:14:28, 4.78s/it]g-point operations will not be computed-01 14:23:18,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 84/1019 [06:56<1:14:28, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:22,753 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 85/1019 [07:01<1:13:06, 4.70s/it]g-point operations will not be computed-01 14:23:22,753 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 85/1019 [07:01<1:13:06, 4.70s/it]g-point operations will not be computed-01 14:23:22,753 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 85/1019 [07:01<1:13:06, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:27,300 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:23:29,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 14:23:27,300 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:23:29,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 14:23:27,300 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 86/1019 [07:05<1:12:26, 4.66s/it]g-point operations will not be computed-01 14:23:27,300 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 86/1019 [07:05<1:12:26, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:31,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 86/1019 [07:05<1:12:26, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:31,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 87/1019 [07:10<1:10:54, 4.56s/it]g-point operations will not be computed-01 14:23:31,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 87/1019 [07:10<1:10:54, 4.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:36,047 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 87/1019 [07:10<1:10:54, 4.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:36,047 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 88/1019 [07:14<1:09:15, 4.46s/it]g-point operations will not be computed-01 14:23:36,047 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|█████��▊ | 88/1019 [07:14<1:09:15, 4.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:40,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 88/1019 [07:14<1:09:15, 4.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:40,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 89/1019 [07:18<1:07:10, 4.33s/it]g-point operations will not be computed-01 14:23:40,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 90/1019 [07:22<1:04:42, 4.18s/it]g-point operations will not be computed-01 14:23:44,127 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 90/1019 [07:22<1:04:42, 4.18s/it]g-point operations will not be computed-01 14:23:44,127 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 90/1019 [07:22<1:04:42, 4.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:47,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 90/1019 [07:22<1:04:42, 4.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:47,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 91/1019 [07:25<1:02:05, 4.01s/it]g-point operations will not be computed-01 14:23:47,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 91/1019 [07:25<1:02:05, 4.01s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:51,364 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 91/1019 [07:25<1:02:05, 4.01s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:51,364 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 92/1019 [07:29<59:22, 3.84s/it]g-point operations will not be computed-01 14:23:51,364 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:23:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 14:23:54,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:23:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 14:23:54,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▍ | 93/1019 [07:32<56:26, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:57,819 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▍ | 93/1019 [07:32<56:26, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:23:57,819 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▍ | 94/1019 [07:35<53:18, 3.46s/it]g-point operations will not be computed-01 14:23:57,819 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▌ | 95/1019 [07:38<50:00, 3.25s/it]g-point operations will not be computed-01 14:24:00,694 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▌ | 95/1019 [07:38<50:00, 3.25s/it]g-point operations will not be computed-01 14:24:00,694 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:24:04,475 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 14:24:03,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:24:04,475 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 14:24:03,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5139, 'learning_rate': 5.52e-06, 'epoch': 0.09} + 9%|███████▋ | 96/1019 [07:40<46:25, 3.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:24:05,648 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3959, 'learning_rate': 5.58e-06, 'epoch': 0.1} +[WARNING|modeling_utils.py:388] 2022-03-01 14:24:06,644 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▋ | 97/1019 [07:43<42:26, 2.76s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:24:07,693 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:24:08,581 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6472, 'learning_rate': 5.64e-06, 'epoch': 0.1} + 10%|███████▊ | 98/1019 [07:44<38:36, 2.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:24:09,508 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:24:10,262 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 99/1019 [07:46<34:43, 2.26s/it] + 10%|███████▊ | 99/1019 [07:46<34:43, 2.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:24:11,066 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:24:12,199 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 100/1019 [07:48<33:12, 2.17s/it] + + 10%|███████▊ | 100/1019 [07:48<33:12, 2.17s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:24:15,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:24:18,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▉ | 101/1019 [07:54<51:40, 3.38s/it] + + 10%|███████▉ | 101/1019 [07:54<51:40, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:24:21,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:24:24,307 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 102/1019 [08:00<1:03:12, 4.14s/it] + + 10%|███████▊ | 102/1019 [08:00<1:03:12, 4.14s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:24:27,319 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:24:30,218 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▉ | 103/1019 [08:06<1:11:15, 4.67s/it] + + 10%|███████▉ | 103/1019 [08:06<1:11:15, 4.67s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:24:33,076 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2759, 'learning_rate': 6e-06, 'epoch': 0.1} +[WARNING|modeling_utils.py:388] 2022-03-01 14:24:35,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 10%|███████▉ | 104/1019 [08:12<1:15:36, 4.96s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:24:38,780 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:24:41,611 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3552, 'learning_rate': 6.0600000000000004e-06, 'epoch': 0.1} + + 10%|████████ | 105/1019 [08:18<1:19:10, 5.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:24:44,536 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:24:47,335 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 106/1019 [08:23<1:21:29, 5.36s/it] + + 10%|████████ | 106/1019 [08:23<1:21:29, 5.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:24:50,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:24:52,997 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▏ | 107/1019 [08:29<1:22:48, 5.45s/it] + + 11%|████████▏ | 107/1019 [08:29<1:22:48, 5.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:24:55,901 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3795, 'learning_rate': 6.2399999999999995e-06, 'epoch': 0.11} +[WARNING|modeling_utils.py:388] 2022-03-01 14:24:58,718 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 11%|████████▎ | 108/1019 [08:35<1:23:58, 5.53s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:25:01,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1435, 'learning_rate': 6.3e-06, 'epoch': 0.11} +[WARNING|modeling_utils.py:388] 2022-03-01 14:25:04,364 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 11%|████████▎ | 109/1019 [08:40<1:24:23, 5.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:25:07,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:25:09,962 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 110/1019 [08:46<1:24:27, 5.57s/it] + + 11%|████████▍ | 110/1019 [08:46<1:24:27, 5.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:25:12,773 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:25:15,488 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 111/1019 [08:51<1:24:08, 5.56s/it] + + 11%|████████▍ | 111/1019 [08:51<1:24:08, 5.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:25:18,295 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:25:20,958 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2045, 'learning_rate': 6.48e-06, 'epoch': 0.11} + + 11%|████████▌ | 112/1019 [08:57<1:23:37, 5.53s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:25:23,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:25:26,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 113/1019 [09:02<1:23:08, 5.51s/it] + + 11%|████████▋ | 113/1019 [09:02<1:23:08, 5.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:25:29,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:25:31,825 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 114/1019 [09:08<1:22:41, 5.48s/it] + + 11%|████████▋ | 114/1019 [09:08<1:22:41, 5.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:25:34,601 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:25:37,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 115/1019 [09:13<1:22:28, 5.47s/it] + + 11%|████████▊ | 115/1019 [09:13<1:22:28, 5.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:25:39,979 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:25:42,656 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 116/1019 [09:19<1:21:56, 5.44s/it] + + 11%|████████▉ | 116/1019 [09:19<1:21:56, 5.44s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:25:45,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:25:48,026 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 117/1019 [09:24<1:21:30, 5.42s/it] + + 11%|████████▉ | 117/1019 [09:24<1:21:30, 5.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:25:50,744 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:25:53,297 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████ | 118/1019 [09:29<1:20:44, 5.38s/it] + + 12%|█████████ | 118/1019 [09:29<1:20:44, 5.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:25:55,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:25:58,500 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████ | 119/1019 [09:34<1:19:52, 5.32s/it] + + 12%|█████████ | 119/1019 [09:34<1:19:52, 5.32s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:26:01,173 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:26:03,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▏ | 120/1019 [09:40<1:19:26, 5.30s/it] + + 12%|█████████▏ | 120/1019 [09:40<1:19:26, 5.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:26:06,495 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:26:09,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▎ | 121/1019 [09:45<1:19:13, 5.29s/it] + + 12%|█████████▎ | 121/1019 [09:45<1:19:13, 5.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:26:11,687 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:26:14,207 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▎ | 122/1019 [09:50<1:18:39, 5.26s/it] + + 12%|█████████▎ | 122/1019 [09:50<1:18:39, 5.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:26:16,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2381, 'learning_rate': 7.14e-06, 'epoch': 0.12} +[WARNING|modeling_utils.py:388] 2022-03-01 14:26:19,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 12%|█████████▍ | 123/1019 [09:55<1:17:51, 5.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:26:21,913 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:26:24,365 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▍ | 124/1019 [10:00<1:17:02, 5.16s/it] + + 12%|█████████▍ | 124/1019 [10:00<1:17:02, 5.16s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:26:26,933 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2045, 'learning_rate': 7.26e-06, 'epoch': 0.12} +[WARNING|modeling_utils.py:388] 2022-03-01 14:26:29,370 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 12%|█████████▌ | 125/1019 [10:05<1:16:14, 5.12s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:26:31,901 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4064, 'learning_rate': 7.32e-06, 'epoch': 0.12} +[WARNING|modeling_utils.py:388] 2022-03-01 14:26:34,381 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 12%|█████████▋ | 126/1019 [10:10<1:15:41, 5.09s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:26:36,886 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3749, 'learning_rate': 7.3800000000000005e-06, 'epoch': 0.12} +[WARNING|modeling_utils.py:388] 2022-03-01 14:26:39,295 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 12%|█████████▋ | 127/1019 [10:15<1:14:50, 5.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:26:41,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3069, 'learning_rate': 7.44e-06, 'epoch': 0.13} +[WARNING|modeling_utils.py:388] 2022-03-01 14:26:44,178 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 13%|█████████▊ | 128/1019 [10:20<1:14:05, 4.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:26:46,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:26:49,101 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|█████████▊ | 129/1019 [10:25<1:13:42, 4.97s/it] + + 13%|█████████▊ | 129/1019 [10:25<1:13:42, 4.97s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:26:51,557 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3884, 'learning_rate': 7.5600000000000005e-06, 'epoch': 0.13} +[WARNING|modeling_utils.py:388] 2022-03-01 14:26:53,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 13%|█████████▉ | 130/1019 [10:30<1:12:38, 4.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:26:56,294 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2463, 'learning_rate': 7.62e-06, 'epoch': 0.13} +[WARNING|modeling_utils.py:388] 2022-03-01 14:26:58,637 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 13%|██████████ | 131/1019 [10:35<1:12:02, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:01,035 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:03,297 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 132/1019 [10:39<1:11:02, 4.81s/it] + + 13%|██████████ | 132/1019 [10:39<1:11:02, 4.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:05,654 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4135, 'learning_rate': 7.74e-06, 'epoch': 0.13} +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:07,930 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 133/1019 [10:44<1:10:12, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:10,312 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:12,514 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3817, 'learning_rate': 7.8e-06, 'epoch': 0.13} + + 13%|██████████▎ | 134/1019 [10:48<1:09:22, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:14,813 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3232, 'learning_rate': 7.860000000000001e-06, 'epoch': 0.13} +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:17,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 13%|██████████▎ | 135/1019 [10:53<1:08:21, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:19,262 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:21,460 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 136/1019 [10:57<1:07:27, 4.58s/it] + + 13%|██████████▍ | 136/1019 [10:57<1:07:27, 4.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:23,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:25,809 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 137/1019 [11:02<1:06:20, 4.51s/it] + + 13%|██████████▍ | 137/1019 [11:02<1:06:20, 4.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:27,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:29,956 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▌ | 138/1019 [11:06<1:04:39, 4.40s/it] + + 14%|██████████▌ | 138/1019 [11:06<1:04:39, 4.40s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:32,009 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:33,926 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▋ | 139/1019 [11:10<1:02:40, 4.27s/it] + + 14%|██████████▋ | 139/1019 [11:10<1:02:40, 4.27s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:35,995 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:37,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▋ | 140/1019 [11:14<1:01:00, 4.16s/it] + + 14%|██████████▋ | 140/1019 [11:14<1:01:00, 4.16s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:39,702 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:41,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 141/1019 [11:17<58:17, 3.98s/it] + 14%|███████████ | 141/1019 [11:17<58:17, 3.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:43,167 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:44,722 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 142/1019 [11:21<55:19, 3.79s/it] + + 14%|███████████▏ | 142/1019 [11:21<55:19, 3.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:46,354 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:47,801 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 143/1019 [11:24<52:10, 3.57s/it] + 14%|███████████▏ | 143/1019 [11:24<52:10, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:49,290 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:50,609 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5753, 'learning_rate': 8.400000000000001e-06, 'epoch': 0.14} + 14%|███████████▎ | 144/1019 [11:27<48:46, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:51,954 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5049, 'learning_rate': 8.459999999999999e-06, 'epoch': 0.14} +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:53,133 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▍ | 145/1019 [11:29<45:07, 3.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:54,361 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5994, 'learning_rate': 8.52e-06, 'epoch': 0.14} +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:55,427 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▍ | 146/1019 [11:31<41:33, 2.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:56,529 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5181, 'learning_rate': 8.58e-06, 'epoch': 0.14} +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:57,473 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▌ | 147/1019 [11:33<37:58, 2.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:27:58,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3057, 'learning_rate': 8.64e-06, 'epoch': 0.15} +[WARNING|modeling_utils.py:388] 2022-03-01 14:27:59,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▌ | 148/1019 [11:35<34:28, 2.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:28:00,176 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5382, 'learning_rate': 8.7e-06, 'epoch': 0.15} +[WARNING|modeling_utils.py:388] 2022-03-01 14:28:00,904 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▋ | 149/1019 [11:37<31:07, 2.15s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:28:01,652 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:28:02,783 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2405, 'learning_rate': 8.759999999999999e-06, 'epoch': 0.15} + + 15%|███████████▊ | 150/1019 [11:39<29:55, 2.07s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:28:06,047 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3383, 'learning_rate': 8.82e-06, 'epoch': 0.15} +[WARNING|modeling_utils.py:388] 2022-03-01 14:28:09,043 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 15%|███████████▊ | 151/1019 [11:45<48:06, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:28:12,078 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:28:14,954 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▉ | 152/1019 [11:51<59:14, 4.10s/it] + + 15%|███████████▉ | 152/1019 [11:51<59:14, 4.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:28:17,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:28:20,889 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▋ | 153/1019 [11:57<1:07:07, 4.65s/it] + + 15%|███████████▋ | 153/1019 [11:57<1:07:07, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:28:23,789 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:28:26,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▊ | 154/1019 [12:03<1:11:50, 4.98s/it] + + 15%|███████████▊ | 154/1019 [12:03<1:11:50, 4.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:28:29,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:28:32,387 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▊ | 155/1019 [12:08<1:15:01, 5.21s/it] + + 15%|███████████▊ | 155/1019 [12:08<1:15:01, 5.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:28:35,247 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:28:38,027 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2237, 'learning_rate': 9.12e-06, 'epoch': 0.15} + + 15%|███████████▉ | 156/1019 [12:14<1:16:47, 5.34s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:28:40,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:28:43,666 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████ | 157/1019 [12:20<1:17:59, 5.43s/it] + + 15%|████████████ | 157/1019 [12:20<1:17:59, 5.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:28:46,599 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:28:49,403 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████ | 158/1019 [12:25<1:19:13, 5.52s/it] + + 16%|████████████ | 158/1019 [12:25<1:19:13, 5.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:28:52,247 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:28:55,054 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▏ | 159/1019 [12:31<1:19:41, 5.56s/it] + + 16%|████████████▏ | 159/1019 [12:31<1:19:41, 5.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:28:57,908 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:29:00,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▏ | 160/1019 [12:36<1:19:30, 5.55s/it] + + 16%|████████████▏ | 160/1019 [12:36<1:19:30, 5.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:29:03,411 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:29:06,047 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▎ | 161/1019 [12:42<1:19:00, 5.52s/it] + + 16%|████████████▎ | 161/1019 [12:42<1:19:00, 5.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:29:08,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:29:11,510 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▍ | 162/1019 [12:47<1:18:38, 5.51s/it] + + 16%|████████████▍ | 162/1019 [12:47<1:18:38, 5.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:29:14,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:29:17,036 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▍ | 163/1019 [12:53<1:18:38, 5.51s/it] + + 16%|████████████▍ | 163/1019 [12:53<1:18:38, 5.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:29:19,784 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2495, 'learning_rate': 9.600000000000001e-06, 'epoch': 0.16} +[WARNING|modeling_utils.py:388] 2022-03-01 14:29:22,466 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 16%|████████████▌ | 164/1019 [12:58<1:18:11, 5.49s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:29:25,214 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.281, 'learning_rate': 9.66e-06, 'epoch': 0.16} +[WARNING|modeling_utils.py:388] 2022-03-01 14:29:27,881 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 16%|████████████▋ | 165/1019 [13:04<1:17:47, 5.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:29:30,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1642, 'learning_rate': 9.72e-06, 'epoch': 0.16} +[WARNING|modeling_utils.py:388] 2022-03-01 14:29:33,287 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 16%|████████████▋ | 166/1019 [13:09<1:17:26, 5.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:29:36,039 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2312, 'learning_rate': 9.780000000000001e-06, 'epoch': 0.16} +[WARNING|modeling_utils.py:388] 2022-03-01 14:29:38,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 16%|████████████▊ | 167/1019 [13:15<1:16:57, 5.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:29:41,360 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0764, 'learning_rate': 9.84e-06, 'epoch': 0.16} +[WARNING|modeling_utils.py:388] 2022-03-01 14:29:43,935 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 16%|████████████▊ | 168/1019 [13:20<1:16:19, 5.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:29:46,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0845, 'learning_rate': 9.9e-06, 'epoch': 0.17} +[WARNING|modeling_utils.py:388] 2022-03-01 14:29:49,118 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 17%|████████████▉ | 169/1019 [13:25<1:15:23, 5.32s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:29:51,742 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1362, 'learning_rate': 9.960000000000001e-06, 'epoch': 0.17} +[WARNING|modeling_utils.py:388] 2022-03-01 14:29:54,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 17%|█████████████ | 170/1019 [13:30<1:14:43, 5.28s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:29:56,925 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4225, 'learning_rate': 1.002e-05, 'epoch': 0.17} +[WARNING|modeling_utils.py:388] 2022-03-01 14:29:59,371 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 17%|█████████████ | 171/1019 [13:35<1:13:44, 5.22s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:30:01,965 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:30:04,444 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2555, 'learning_rate': 1.008e-05, 'epoch': 0.17} + + 17%|█████████████▏ | 172/1019 [13:40<1:13:01, 5.17s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:30:07,051 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.228, 'learning_rate': 1.0140000000000001e-05, 'epoch': 0.17} +[WARNING|modeling_utils.py:388] 2022-03-01 14:30:09,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 17%|█████████████▏ | 173/1019 [13:45<1:12:31, 5.14s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:30:12,060 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:30:14,460 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 174/1019 [13:50<1:11:35, 5.08s/it] + + 17%|█████████████▎ | 174/1019 [13:50<1:11:35, 5.08s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:30:17,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2782, 'learning_rate': 1.0260000000000002e-05, 'epoch': 0.17} +[WARNING|modeling_utils.py:388] 2022-03-01 14:30:19,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 17%|█████████████▍ | 175/1019 [13:55<1:11:02, 5.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:30:21,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1353, 'learning_rate': 1.032e-05, 'epoch': 0.17} +[WARNING|modeling_utils.py:388] 2022-03-01 14:30:24,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 17%|█████████████▍ | 176/1019 [14:00<1:10:34, 5.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:30:26,937 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2218, 'learning_rate': 1.0379999999999999e-05, 'epoch': 0.17} +[WARNING|modeling_utils.py:388] 2022-03-01 14:30:29,382 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 17%|█████████████▌ | 177/1019 [14:05<1:10:21, 5.01s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:30:31,870 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2825, 'learning_rate': 1.044e-05, 'epoch': 0.17} +[WARNING|modeling_utils.py:388] 2022-03-01 14:30:34,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 17%|█████████████▋ | 178/1019 [14:10<1:09:33, 4.96s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:30:36,701 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:30:39,051 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▋ | 179/1019 [14:15<1:08:53, 4.92s/it] + + 18%|█████████████▋ | 179/1019 [14:15<1:08:53, 4.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:30:41,438 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3827, 'learning_rate': 1.0559999999999999e-05, 'epoch': 0.18} +[WARNING|modeling_utils.py:388] 2022-03-01 14:30:43,782 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 18%|█████████████▊ | 180/1019 [14:20<1:08:01, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:30:46,236 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4277, 'learning_rate': 1.062e-05, 'epoch': 0.18} +[WARNING|modeling_utils.py:388] 2022-03-01 14:30:48,530 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 18%|█████████████▊ | 181/1019 [14:24<1:07:27, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:30:50,971 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:30:53,279 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▉ | 182/1019 [14:29<1:07:01, 4.80s/it] + + 18%|█████████████▉ | 182/1019 [14:29<1:07:01, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:30:55,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:30:57,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████ | 183/1019 [14:34<1:06:01, 4.74s/it] + + 18%|██████████████ | 183/1019 [14:34<1:06:01, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:00,183 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:02,413 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2316, 'learning_rate': 1.08e-05, 'epoch': 0.18} + 18%|██████████████ | 184/1019 [14:38<1:05:09, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:04,716 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:06,907 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▏ | 185/1019 [14:43<1:04:17, 4.63s/it] + + 18%|██████████████▏ | 185/1019 [14:43<1:04:17, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:09,191 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3426, 'learning_rate': 1.092e-05, 'epoch': 0.18} +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:11,311 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 18%|██████████████▏ | 186/1019 [14:47<1:03:18, 4.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:13,529 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3689, 'learning_rate': 1.098e-05, 'epoch': 0.18} +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:15,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 18%|██████████████▎ | 187/1019 [14:51<1:02:04, 4.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:17,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2104, 'learning_rate': 1.104e-05, 'epoch': 0.18} +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:19,879 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▍ | 188/1019 [14:56<1:01:12, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:21,934 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:23,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▊ | 189/1019 [15:00<59:28, 4.30s/it] + + 19%|██████████████▊ | 189/1019 [15:00<59:28, 4.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:25,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:27,781 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▉ | 190/1019 [15:04<57:40, 4.17s/it] + + 19%|██████████████▉ | 190/1019 [15:04<57:40, 4.17s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:29,727 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3558, 'learning_rate': 1.1220000000000001e-05, 'epoch': 0.19} +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:31,482 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 19%|██████████████▉ | 191/1019 [15:07<55:38, 4.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:33,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2807, 'learning_rate': 1.128e-05, 'epoch': 0.19} +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:34,953 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████ | 192/1019 [15:11<53:15, 3.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:36,644 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:38,192 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▏ | 193/1019 [15:14<50:36, 3.68s/it] + + 19%|███████████████▏ | 193/1019 [15:14<50:36, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:39,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.416, 'learning_rate': 1.1400000000000001e-05, 'epoch': 0.19} +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:41,226 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▏ | 194/1019 [15:17<47:53, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:42,675 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:43,963 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▎ | 195/1019 [15:20<44:46, 3.26s/it] + 19%|███████████████▎ | 195/1019 [15:20<44:46, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:45,289 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:46,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▍ | 196/1019 [15:22<41:44, 3.04s/it] + + 19%|███████████████▍ | 196/1019 [15:22<41:44, 3.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:47,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4825, 'learning_rate': 1.1580000000000001e-05, 'epoch': 0.19} +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:48,802 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▍ | 197/1019 [15:25<38:37, 2.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:49,888 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5113, 'learning_rate': 1.164e-05, 'epoch': 0.19} +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:50,829 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▌ | 198/1019 [15:27<35:20, 2.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:51,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:52,593 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 199/1019 [15:28<31:56, 2.34s/it] + 20%|███████████████▌ | 199/1019 [15:28<31:56, 2.34s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:53,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 14:31:54,538 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 199/1019 [15:28<31:56, 2.34s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:53,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3417, 'learning_rate': 1.1760000000000001e-05, 'epoch': 0.2} + 20%|███████████████▌ | 199/1019 [15:28<31:56, 2.34s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:53,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▊ | 201/1019 [15:36<45:57, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:53,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▊ | 201/1019 [15:36<45:57, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:31:53,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▊ | 201/1019 [15:36<45:57, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:03,638 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▊ | 201/1019 [15:36<45:57, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:03,638 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▊ | 201/1019 [15:36<45:57, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:03,638 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2096, 'learning_rate': 1.1880000000000001e-05, 'epoch': 0.2} + 20%|███████████████▌ | 203/1019 [15:48<1:03:01, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:03,638 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 203/1019 [15:48<1:03:01, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:03,638 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 203/1019 [15:48<1:03:01, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:15,267 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 203/1019 [15:48<1:03:01, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:15,267 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 203/1019 [15:48<1:03:01, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:15,267 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1117, 'learning_rate': 1.2e-05, 'epoch': 0.2} + 20%|███████████████▌ | 203/1019 [15:48<1:03:01, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:15,267 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▋ | 205/1019 [16:00<1:10:06, 5.17s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:15,267 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▋ | 205/1019 [16:00<1:10:06, 5.17s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:26,586 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▋ | 205/1019 [16:00<1:10:06, 5.17s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:26,586 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▋ | 205/1019 [16:00<1:10:06, 5.17s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:26,586 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1161, 'learning_rate': 1.2120000000000001e-05, 'epoch': 0.2} + 20%|███████████████▋ | 205/1019 [16:00<1:10:06, 5.17s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:26,586 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▊ | 207/1019 [16:11<1:12:53, 5.39s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:26,586 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▊ | 207/1019 [16:11<1:12:53, 5.39s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:26,586 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▊ | 207/1019 [16:11<1:12:53, 5.39s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:37,755 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▊ | 207/1019 [16:11<1:12:53, 5.39s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:37,755 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2981, 'learning_rate': 1.224e-05, 'epoch': 0.2} + 20%|███████████████▊ | 207/1019 [16:11<1:12:53, 5.39s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:37,755 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + [WARNING|modeling_utils.py:388] 2022-03-01 14:32:37,755 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + [WARNING|modeling_utils.py:388] 2022-03-01 14:32:37,755 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|███████████████▉ | 209/1019 [16:22<1:13:48, 5.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:37,755 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|███████████████▉ | 209/1019 [16:22<1:13:48, 5.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:48,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|███████████████▉ | 209/1019 [16:22<1:13:48, 5.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:48,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|███████████████▉ | 209/1019 [16:22<1:13:48, 5.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:48,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2566, 'learning_rate': 1.236e-05, 'epoch': 0.21} + 21%|████████████████▏ | 211/1019 [16:33<1:14:32, 5.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:48,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▏ | 211/1019 [16:33<1:14:32, 5.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:32:48,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▏ | 211/1019 [16:33<1:14:32, 5.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:00,039 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▏ | 211/1019 [16:33<1:14:32, 5.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:00,039 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▏ | 211/1019 [16:33<1:14:32, 5.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:00,039 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1639, 'learning_rate': 1.2479999999999999e-05, 'epoch': 0.21} + 21%|████████████████▏ | 211/1019 [16:33<1:14:32, 5.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:00,039 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:00,039 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:00,039 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3047, 'learning_rate': 1.26e-05, 'epoch': 0.21} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1754, 'learning_rate': 1.2659999999999999e-05, 'epoch': 0.21} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3123, 'learning_rate': 1.272e-05, 'epoch': 0.21} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3246, 'learning_rate': 1.278e-05, 'epoch': 0.21} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.091, 'learning_rate': 1.284e-05, 'epoch': 0.21} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2503, 'learning_rate': 1.29e-05, 'epoch': 0.21} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1214, 'learning_rate': 1.296e-05, 'epoch': 0.22} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.062, 'learning_rate': 1.302e-05, 'epoch': 0.22} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4116, 'learning_rate': 1.308e-05, 'epoch': 0.22} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1355, 'learning_rate': 1.314e-05, 'epoch': 0.22} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2368, 'learning_rate': 1.32e-05, 'epoch': 0.22} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2528, 'learning_rate': 1.326e-05, 'epoch': 0.22} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1508, 'learning_rate': 1.3320000000000001e-05, 'epoch': 0.22} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1623, 'learning_rate': 1.338e-05, 'epoch': 0.22} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0788, 'learning_rate': 1.344e-05, 'epoch': 0.22} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1977, 'learning_rate': 1.3500000000000001e-05, 'epoch': 0.22} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2113, 'learning_rate': 1.356e-05, 'epoch': 0.23} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0999, 'learning_rate': 1.362e-05, 'epoch': 0.23} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1771, 'learning_rate': 1.3680000000000001e-05, 'epoch': 0.23} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3331, 'learning_rate': 1.374e-05, 'epoch': 0.23} + 21%|██████████████���█▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.116, 'learning_rate': 1.3800000000000002e-05, 'epoch': 0.23} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3639, 'learning_rate': 1.3860000000000001e-05, 'epoch': 0.23} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1692, 'learning_rate': 1.392e-05, 'epoch': 0.23} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1643, 'learning_rate': 1.3980000000000002e-05, 'epoch': 0.23} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2614, 'learning_rate': 1.4040000000000001e-05, 'epoch': 0.23} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2296, 'learning_rate': 1.4099999999999999e-05, 'epoch': 0.23} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4573, 'learning_rate': 1.416e-05, 'epoch': 0.24} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2955, 'learning_rate': 1.422e-05, 'epoch': 0.24} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6286, 'learning_rate': 1.428e-05, 'epoch': 0.24} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2858, 'learning_rate': 1.434e-05, 'epoch': 0.24} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4545, 'learning_rate': 1.44e-05, 'epoch': 0.24} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.372, 'learning_rate': 1.446e-05, 'epoch': 0.24} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6181, 'learning_rate': 1.452e-05, 'epoch': 0.24} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3365, 'learning_rate': 1.458e-05, 'epoch': 0.24} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9304, 'learning_rate': 1.464e-05, 'epoch': 0.24} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4167, 'learning_rate': 1.47e-05, 'epoch': 0.24} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8835, 'learning_rate': 1.4760000000000001e-05, 'epoch': 0.25} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0269, 'learning_rate': 1.482e-05, 'epoch': 0.25} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2125, 'learning_rate': 1.488e-05, 'epoch': 0.25} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.114, 'learning_rate': 1.4940000000000001e-05, 'epoch': 0.25} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.9126, 'learning_rate': 1.5e-05, 'epoch': 0.25} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0764, 'learning_rate': 1.506e-05, 'epoch': 0.25} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0163, 'learning_rate': 1.5120000000000001e-05, 'epoch': 0.25} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.257, 'learning_rate': 1.518e-05, 'epoch': 0.25} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.9459, 'learning_rate': 1.524e-05, 'epoch': 0.25} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.045, 'learning_rate': 1.53e-05, 'epoch': 0.25} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1164, 'learning_rate': 1.5360000000000002e-05, 'epoch': 0.26} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0137, 'learning_rate': 1.542e-05, 'epoch': 0.26} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1465, 'learning_rate': 1.548e-05, 'epoch': 0.26} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1794, 'learning_rate': 1.554e-05, 'epoch': 0.26} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1316, 'learning_rate': 1.56e-05, 'epoch': 0.26} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0712, 'learning_rate': 1.5660000000000003e-05, 'epoch': 0.26} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3572, 'learning_rate': 1.5720000000000002e-05, 'epoch': 0.26} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2738, 'learning_rate': 1.578e-05, 'epoch': 0.26} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3429, 'learning_rate': 1.584e-05, 'epoch': 0.26} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0516, 'learning_rate': 1.59e-05, 'epoch': 0.26} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2589, 'learning_rate': 1.596e-05, 'epoch': 0.26} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.181, 'learning_rate': 1.6020000000000002e-05, 'epoch': 0.27} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1457, 'learning_rate': 1.6080000000000002e-05, 'epoch': 0.27} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1916, 'learning_rate': 1.614e-05, 'epoch': 0.27} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2991, 'learning_rate': 1.62e-05, 'epoch': 0.27} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1077, 'learning_rate': 1.626e-05, 'epoch': 0.27} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5493, 'learning_rate': 1.6320000000000003e-05, 'epoch': 0.27} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2357, 'learning_rate': 1.6380000000000002e-05, 'epoch': 0.27} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0973, 'learning_rate': 1.6440000000000002e-05, 'epoch': 0.27} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2607, 'learning_rate': 1.65e-05, 'epoch': 0.27} + 21%|██████████████��█▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.118, 'learning_rate': 1.656e-05, 'epoch': 0.27} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2394, 'learning_rate': 1.6620000000000004e-05, 'epoch': 0.28} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1779, 'learning_rate': 1.6680000000000003e-05, 'epoch': 0.28} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1311, 'learning_rate': 1.6740000000000002e-05, 'epoch': 0.28} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.015, 'learning_rate': 1.6800000000000002e-05, 'epoch': 0.28} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5039, 'learning_rate': 1.686e-05, 'epoch': 0.28} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1402, 'learning_rate': 1.6919999999999997e-05, 'epoch': 0.28} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2955, 'learning_rate': 1.698e-05, 'epoch': 0.28} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4529, 'learning_rate': 1.704e-05, 'epoch': 0.28} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3015, 'learning_rate': 1.71e-05, 'epoch': 0.28} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2742, 'learning_rate': 1.716e-05, 'epoch': 0.28} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2857, 'learning_rate': 1.7219999999999998e-05, 'epoch': 0.29} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4605, 'learning_rate': 1.728e-05, 'epoch': 0.29} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3054, 'learning_rate': 1.734e-05, 'epoch': 0.29} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2712, 'learning_rate': 1.74e-05, 'epoch': 0.29} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3289, 'learning_rate': 1.746e-05, 'epoch': 0.29} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.219, 'learning_rate': 1.7519999999999998e-05, 'epoch': 0.29} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5786, 'learning_rate': 1.758e-05, 'epoch': 0.29} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7392, 'learning_rate': 1.764e-05, 'epoch': 0.29} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8007, 'learning_rate': 1.77e-05, 'epoch': 0.29} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4203, 'learning_rate': 1.776e-05, 'epoch': 0.29} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3597, 'learning_rate': 1.782e-05, 'epoch': 0.3} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1231, 'learning_rate': 1.7879999999999998e-05, 'epoch': 0.3} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1559, 'learning_rate': 1.794e-05, 'epoch': 0.3} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2997, 'learning_rate': 1.8e-05, 'epoch': 0.3} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0011, 'learning_rate': 1.806e-05, 'epoch': 0.3} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3008, 'learning_rate': 1.812e-05, 'epoch': 0.3} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1842, 'learning_rate': 1.818e-05, 'epoch': 0.3} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0757, 'learning_rate': 1.824e-05, 'epoch': 0.3} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2437, 'learning_rate': 1.83e-05, 'epoch': 0.3} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4154, 'learning_rate': 1.836e-05, 'epoch': 0.3} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1719, 'learning_rate': 1.842e-05, 'epoch': 0.31} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0973, 'learning_rate': 1.848e-05, 'epoch': 0.31} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2067, 'learning_rate': 1.854e-05, 'epoch': 0.31} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2581, 'learning_rate': 1.86e-05, 'epoch': 0.31} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1801, 'learning_rate': 1.866e-05, 'epoch': 0.31} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2379, 'learning_rate': 1.872e-05, 'epoch': 0.31} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1823, 'learning_rate': 1.878e-05, 'epoch': 0.31} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3278, 'learning_rate': 1.884e-05, 'epoch': 0.31} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1928, 'learning_rate': 1.8900000000000002e-05, 'epoch': 0.31} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1694, 'learning_rate': 1.896e-05, 'epoch': 0.31} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1703, 'learning_rate': 1.902e-05, 'epoch': 0.31} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1081, 'learning_rate': 1.908e-05, 'epoch': 0.32} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0638, 'learning_rate': 1.914e-05, 'epoch': 0.32} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1422, 'learning_rate': 1.9200000000000003e-05, 'epoch': 0.32} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2349, 'learning_rate': 1.9260000000000002e-05, 'epoch': 0.32} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1533, 'learning_rate': 1.932e-05, 'epoch': 0.32} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1396, 'learning_rate': 1.938e-05, 'epoch': 0.32} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.172, 'learning_rate': 1.944e-05, 'epoch': 0.32} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.176, 'learning_rate': 1.95e-05, 'epoch': 0.32} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2705, 'learning_rate': 1.9560000000000002e-05, 'epoch': 0.32} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1291, 'learning_rate': 1.9620000000000002e-05, 'epoch': 0.32} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3034, 'learning_rate': 1.968e-05, 'epoch': 0.33} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.9674, 'learning_rate': 1.974e-05, 'epoch': 0.33} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3076, 'learning_rate': 1.98e-05, 'epoch': 0.33} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3168, 'learning_rate': 1.9860000000000003e-05, 'epoch': 0.33} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0993, 'learning_rate': 1.9920000000000002e-05, 'epoch': 0.33} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3112, 'learning_rate': 1.9980000000000002e-05, 'epoch': 0.33} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2759, 'learning_rate': 2.004e-05, 'epoch': 0.33} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3918, 'learning_rate': 2.01e-05, 'epoch': 0.33} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3703, 'learning_rate': 2.016e-05, 'epoch': 0.33} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.308, 'learning_rate': 2.0220000000000003e-05, 'epoch': 0.33} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2256, 'learning_rate': 2.0280000000000002e-05, 'epoch': 0.34} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3497, 'learning_rate': 2.0340000000000002e-05, 'epoch': 0.34} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3425, 'learning_rate': 2.04e-05, 'epoch': 0.34} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2189, 'learning_rate': 2.046e-05, 'epoch': 0.34} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2919, 'learning_rate': 2.0520000000000003e-05, 'epoch': 0.34} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4136, 'learning_rate': 2.0580000000000003e-05, 'epoch': 0.34} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3646, 'learning_rate': 2.064e-05, 'epoch': 0.34} + 21%|████████████████▎ | 213/1019 [16:44<1:13:53, 5.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7069, 'learning_rate': 2.0759999999999998e-05, 'epoch': 0.34} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0589, 'learning_rate': 2.082e-05, 'epoch': 0.34} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1303, 'learning_rate': 2.088e-05, 'epoch': 0.35} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.115, 'learning_rate': 2.094e-05, 'epoch': 0.35} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2286, 'learning_rate': 2.1e-05, 'epoch': 0.35} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0748, 'learning_rate': 2.1059999999999998e-05, 'epoch': 0.35} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1118, 'learning_rate': 2.1119999999999998e-05, 'epoch': 0.35} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1279, 'learning_rate': 2.118e-05, 'epoch': 0.35} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3656, 'learning_rate': 2.124e-05, 'epoch': 0.35} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1523, 'learning_rate': 2.13e-05, 'epoch': 0.35} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1246, 'learning_rate': 2.136e-05, 'epoch': 0.35} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2928, 'learning_rate': 2.1419999999999998e-05, 'epoch': 0.35} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3397, 'learning_rate': 2.148e-05, 'epoch': 0.36} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.241, 'learning_rate': 2.154e-05, 'epoch': 0.36} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2012, 'learning_rate': 2.16e-05, 'epoch': 0.36} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0962, 'learning_rate': 2.166e-05, 'epoch': 0.36} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2434, 'learning_rate': 2.172e-05, 'epoch': 0.36} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.9839, 'learning_rate': 2.178e-05, 'epoch': 0.36} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1594, 'learning_rate': 2.184e-05, 'epoch': 0.36} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.223, 'learning_rate': 2.19e-05, 'epoch': 0.36} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0741, 'learning_rate': 2.196e-05, 'epoch': 0.36} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3949, 'learning_rate': 2.202e-05, 'epoch': 0.36} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.189, 'learning_rate': 2.208e-05, 'epoch': 0.36} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2103, 'learning_rate': 2.214e-05, 'epoch': 0.37} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0786, 'learning_rate': 2.22e-05, 'epoch': 0.37} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.251, 'learning_rate': 2.226e-05, 'epoch': 0.37} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2908, 'learning_rate': 2.232e-05, 'epoch': 0.37} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2016, 'learning_rate': 2.238e-05, 'epoch': 0.37} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1318, 'learning_rate': 2.2440000000000002e-05, 'epoch': 0.37} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.268, 'learning_rate': 2.25e-05, 'epoch': 0.37} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2924, 'learning_rate': 2.256e-05, 'epoch': 0.37} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0712, 'learning_rate': 2.262e-05, 'epoch': 0.37} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1788, 'learning_rate': 2.268e-05, 'epoch': 0.37} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2122, 'learning_rate': 2.274e-05, 'epoch': 0.38} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2817, 'learning_rate': 2.2800000000000002e-05, 'epoch': 0.38} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3149, 'learning_rate': 2.286e-05, 'epoch': 0.38} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1973, 'learning_rate': 2.292e-05, 'epoch': 0.38} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0489, 'learning_rate': 2.298e-05, 'epoch': 0.38} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2602, 'learning_rate': 2.304e-05, 'epoch': 0.38} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0623, 'learning_rate': 2.3100000000000002e-05, 'epoch': 0.38} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2913, 'learning_rate': 2.3160000000000002e-05, 'epoch': 0.38} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1865, 'learning_rate': 2.322e-05, 'epoch': 0.38} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2424, 'learning_rate': 2.328e-05, 'epoch': 0.38} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2285, 'learning_rate': 2.334e-05, 'epoch': 0.39} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3396, 'learning_rate': 2.3400000000000003e-05, 'epoch': 0.39} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3649, 'learning_rate': 2.3460000000000002e-05, 'epoch': 0.39} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5363, 'learning_rate': 2.3520000000000002e-05, 'epoch': 0.39} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4627, 'learning_rate': 2.358e-05, 'epoch': 0.39} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5413, 'learning_rate': 2.364e-05, 'epoch': 0.39} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5831, 'learning_rate': 2.37e-05, 'epoch': 0.39} +{'loss': 4.2481, 'learning_rate': 2.3760000000000003e-05, 'epoch': 0.39} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1642, 'learning_rate': 2.3820000000000002e-05, 'epoch': 0.39} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2277, 'learning_rate': 2.3880000000000002e-05, 'epoch': 0.39} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1699, 'learning_rate': 2.394e-05, 'epoch': 0.4} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1581, 'learning_rate': 2.4e-05, 'epoch': 0.4} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2515, 'learning_rate': 2.4060000000000003e-05, 'epoch': 0.4} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0741, 'learning_rate': 2.4120000000000003e-05, 'epoch': 0.4} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0891, 'learning_rate': 2.4180000000000002e-05, 'epoch': 0.4} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0662, 'learning_rate': 2.4240000000000002e-05, 'epoch': 0.4} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████��▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2037, 'learning_rate': 2.43e-05, 'epoch': 0.4} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1706, 'learning_rate': 2.4360000000000004e-05, 'epoch': 0.4} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2115, 'learning_rate': 2.442e-05, 'epoch': 0.4} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2298, 'learning_rate': 2.448e-05, 'epoch': 0.4} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0516, 'learning_rate': 2.454e-05, 'epoch': 0.41} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3579, 'learning_rate': 2.4599999999999998e-05, 'epoch': 0.41} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0692, 'learning_rate': 2.4659999999999998e-05, 'epoch': 0.41} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0827, 'learning_rate': 2.472e-05, 'epoch': 0.41} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1162, 'learning_rate': 2.478e-05, 'epoch': 0.41} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.35, 'learning_rate': 2.484e-05, 'epoch': 0.41} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1919, 'learning_rate': 2.49e-05, 'epoch': 0.41} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2658, 'learning_rate': 2.4959999999999998e-05, 'epoch': 0.41} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1342, 'learning_rate': 2.502e-05, 'epoch': 0.41} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████��███████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.381, 'learning_rate': 2.508e-05, 'epoch': 0.41} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1331, 'learning_rate': 2.514e-05, 'epoch': 0.41} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3102, 'learning_rate': 2.52e-05, 'epoch': 0.42} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1476, 'learning_rate': 2.526e-05, 'epoch': 0.42} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1882, 'learning_rate': 2.5319999999999998e-05, 'epoch': 0.42} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0508, 'learning_rate': 2.538e-05, 'epoch': 0.42} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.301, 'learning_rate': 2.544e-05, 'epoch': 0.42} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.268, 'learning_rate': 2.55e-05, 'epoch': 0.42} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3428, 'learning_rate': 2.556e-05, 'epoch': 0.42} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1861, 'learning_rate': 2.562e-05, 'epoch': 0.42} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.257, 'learning_rate': 2.568e-05, 'epoch': 0.42} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2271, 'learning_rate': 2.574e-05, 'epoch': 0.42} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1993, 'learning_rate': 2.58e-05, 'epoch': 0.43} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1307, 'learning_rate': 2.586e-05, 'epoch': 0.43} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2263, 'learning_rate': 2.592e-05, 'epoch': 0.43} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.161, 'learning_rate': 2.5980000000000002e-05, 'epoch': 0.43} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0603, 'learning_rate': 2.604e-05, 'epoch': 0.43} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1518, 'learning_rate': 2.61e-05, 'epoch': 0.43} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2696, 'learning_rate': 2.616e-05, 'epoch': 0.43} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3789, 'learning_rate': 2.622e-05, 'epoch': 0.43} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0364, 'learning_rate': 2.628e-05, 'epoch': 0.43} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2641, 'learning_rate': 2.6340000000000002e-05, 'epoch': 0.43} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2707, 'learning_rate': 2.64e-05, 'epoch': 0.44} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4679, 'learning_rate': 2.646e-05, 'epoch': 0.44} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1984, 'learning_rate': 2.652e-05, 'epoch': 0.44} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3196, 'learning_rate': 2.658e-05, 'epoch': 0.44} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5357, 'learning_rate': 2.6640000000000002e-05, 'epoch': 0.44} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5346, 'learning_rate': 2.6700000000000002e-05, 'epoch': 0.44} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5169, 'learning_rate': 2.676e-05, 'epoch': 0.44} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2235, 'learning_rate': 2.682e-05, 'epoch': 0.44} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1592, 'learning_rate': 2.688e-05, 'epoch': 0.44} + 34%|███████████████���███████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1864, 'learning_rate': 2.6940000000000003e-05, 'epoch': 0.44} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2508, 'learning_rate': 2.7000000000000002e-05, 'epoch': 0.45} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2071, 'learning_rate': 2.7060000000000002e-05, 'epoch': 0.45} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1408, 'learning_rate': 2.712e-05, 'epoch': 0.45} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0335, 'learning_rate': 2.718e-05, 'epoch': 0.45} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1879, 'learning_rate': 2.724e-05, 'epoch': 0.45} + 34%|██████████████���████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1996, 'learning_rate': 2.7300000000000003e-05, 'epoch': 0.45} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2994, 'learning_rate': 2.7360000000000002e-05, 'epoch': 0.45} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0768, 'learning_rate': 2.7420000000000002e-05, 'epoch': 0.45} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2074, 'learning_rate': 2.748e-05, 'epoch': 0.45} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1172, 'learning_rate': 2.754e-05, 'epoch': 0.45} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0698, 'learning_rate': 2.7600000000000003e-05, 'epoch': 0.46} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1778, 'learning_rate': 2.7660000000000003e-05, 'epoch': 0.46} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2095, 'learning_rate': 2.7720000000000002e-05, 'epoch': 0.46} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2781, 'learning_rate': 2.778e-05, 'epoch': 0.46} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1683, 'learning_rate': 2.784e-05, 'epoch': 0.46} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.9799, 'learning_rate': 2.79e-05, 'epoch': 0.46} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3077, 'learning_rate': 2.7960000000000003e-05, 'epoch': 0.46} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2259, 'learning_rate': 2.8020000000000003e-05, 'epoch': 0.46} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3595, 'learning_rate': 2.8080000000000002e-05, 'epoch': 0.46} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2685, 'learning_rate': 2.8139999999999998e-05, 'epoch': 0.46} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1925, 'learning_rate': 2.8199999999999998e-05, 'epoch': 0.46} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2166, 'learning_rate': 2.826e-05, 'epoch': 0.47} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4206, 'learning_rate': 2.832e-05, 'epoch': 0.47} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.057, 'learning_rate': 2.838e-05, 'epoch': 0.47} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2305, 'learning_rate': 2.844e-05, 'epoch': 0.47} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.168, 'learning_rate': 2.8499999999999998e-05, 'epoch': 0.47} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2313, 'learning_rate': 2.856e-05, 'epoch': 0.47} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2979, 'learning_rate': 2.862e-05, 'epoch': 0.47} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3333, 'learning_rate': 2.868e-05, 'epoch': 0.47} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.942, 'learning_rate': 2.874e-05, 'epoch': 0.47} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1037, 'learning_rate': 2.88e-05, 'epoch': 0.47} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0133, 'learning_rate': 2.8859999999999998e-05, 'epoch': 0.48} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4522, 'learning_rate': 2.892e-05, 'epoch': 0.48} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3166, 'learning_rate': 2.898e-05, 'epoch': 0.48} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0517, 'learning_rate': 2.904e-05, 'epoch': 0.48} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1813, 'learning_rate': 2.91e-05, 'epoch': 0.48} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1101, 'learning_rate': 2.916e-05, 'epoch': 0.48} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1896, 'learning_rate': 2.922e-05, 'epoch': 0.48} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3391, 'learning_rate': 2.928e-05, 'epoch': 0.48} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2296, 'learning_rate': 2.934e-05, 'epoch': 0.48} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2125, 'learning_rate': 2.94e-05, 'epoch': 0.48} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3836, 'learning_rate': 2.946e-05, 'epoch': 0.49} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1361, 'learning_rate': 2.9520000000000002e-05, 'epoch': 0.49} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2316, 'learning_rate': 2.958e-05, 'epoch': 0.49} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5139, 'learning_rate': 2.964e-05, 'epoch': 0.49} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5592, 'learning_rate': 2.97e-05, 'epoch': 0.49} + 34%|███████████████████████████▍ | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2366] 2022-03-01 14:54:49,439 >> Num examples = 2642 | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2366] 2022-03-01 14:54:49,439 >> Num examples = 2642 | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2366] 2022-03-01 14:54:49,439 >> Num examples = 2642 | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2366] 2022-03-01 14:54:49,439 >> Num examples = 2642 | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2366] 2022-03-01 14:54:49,439 >> Num examples = 2642 | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2366] 2022-03-01 14:54:49,439 >> Num examples = 2642 | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2366] 2022-03-01 14:54:49,439 >> Num examples = 2642 | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2366] 2022-03-01 14:54:49,439 >> Num examples = 2642 | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2366] 2022-03-01 14:54:49,439 >> Num examples = 2642 | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2366] 2022-03-01 14:54:49,439 >> Num examples = 2642 | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2366] 2022-03-01 14:54:49,439 >> Num examples = 2642 | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2366] 2022-03-01 14:54:49,439 >> Num examples = 2642 | 350/1019 [26:56<22:40, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + File "/home/sanchit_huggingface_co/gcp/lib/python3.9/site-packages/torch/nn/functional.py", line 2347, in layer_normimplARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + File "/home/sanchit_huggingface_co/gcp/lib/python3.9/site-packages/torch/nn/functional.py", line 2347, in layer_normimplARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + File "/home/sanchit_huggingface_co/gcp/lib/python3.9/site-packages/torch/nn/functional.py", line 2347, in layer_normimplARNING|modeling_utils.py:388] 2022-03-01 14:33:10,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed \ No newline at end of file