diff --git "a/wandb/run-20220228_093705-yn2gmwrw/files/output.log" "b/wandb/run-20220228_093705-yn2gmwrw/files/output.log" new file mode 100644--- /dev/null +++ "b/wandb/run-20220228_093705-yn2gmwrw/files/output.log" @@ -0,0 +1,1621 @@ + + + 0%| | 0/1784 [00:00> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8979, 'learning_rate': 0.0, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-02-28 09:37:11,240 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 0%| | 1/1784 [00:04<2:09:15, 4.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:37:13,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.0308, 'learning_rate': 0.0, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-02-28 09:37:15,034 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 0%| | 2/1784 [00:08<1:59:24, 4.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:37:16,937 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:37:18,772 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.1394, 'learning_rate': 0.0, 'epoch': 0.0} + 0%|▏ | 3/1784 [00:11<1:56:53, 3.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:37:20,727 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.684, 'learning_rate': 2e-08, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-02-28 09:37:22,506 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 0%|▏ | 4/1784 [00:15<1:55:06, 3.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:37:24,563 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7728, 'learning_rate': 4e-08, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-02-28 09:37:26,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 0%|▏ | 5/1784 [00:19<1:53:59, 3.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:37:28,305 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8141, 'learning_rate': 6.000000000000001e-08, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-02-28 09:37:30,137 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 0%|▎ | 6/1784 [00:23<1:52:56, 3.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:37:32,034 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6878, 'learning_rate': 8e-08, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-02-28 09:37:33,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 0%|▎ | 7/1784 [00:27<1:51:50, 3.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:37:35,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8455, 'learning_rate': 1.0000000000000001e-07, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-02-28 09:37:37,632 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 0%|▎ | 8/1784 [00:30<1:51:54, 3.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:37:39,527 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:37:41,279 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▍ | 9/1784 [00:34<1:50:37, 3.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:37:43,149 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.0892, 'learning_rate': 1.2000000000000002e-07, 'epoch': 0.01} +{'loss': 4.7674, 'learning_rate': 1.4e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 09:37:44,894 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▍ | 10/1784 [00:38<1:49:25, 3.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:37:46,750 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8139, 'learning_rate': 1.6e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 09:37:48,485 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▍ | 11/1784 [00:41<1:48:19, 3.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:37:50,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7889, 'learning_rate': 1.8e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 09:37:52,038 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▌ | 12/1784 [00:45<1:47:15, 3.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:37:53,895 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.0036, 'learning_rate': 2.0000000000000002e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 09:37:55,638 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▌ | 13/1784 [00:48<1:46:54, 3.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:37:57,447 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.621, 'learning_rate': 2.2e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 09:37:59,119 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▌ | 14/1784 [00:52<1:45:34, 3.58s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:00,935 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7464, 'learning_rate': 2.4000000000000003e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:02,605 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▋ | 15/1784 [00:55<1:44:43, 3.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:04,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:06,070 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8966, 'learning_rate': 2.6e-07, 'epoch': 0.01} + 1%|▋ | 16/1784 [00:59<1:43:53, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:07,829 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9026, 'learning_rate': 2.8e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:09,497 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▊ | 17/1784 [01:02<1:42:58, 3.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:11,232 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8133, 'learning_rate': 3.0000000000000004e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:12,891 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▊ | 18/1784 [01:06<1:41:59, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:14,658 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:16,294 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7758, 'learning_rate': 3.2e-07, 'epoch': 0.01} + 1%|▊ | 19/1784 [01:09<1:41:23, 3.45s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:18,014 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.0714, 'learning_rate': 3.4000000000000003e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:19,670 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▉ | 20/1784 [01:12<1:40:42, 3.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7965, 'learning_rate': 3.6e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:23,055 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▉ | 21/1784 [01:16<1:40:16, 3.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:24,810 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.1218, 'learning_rate': 3.8e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:26,438 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▉ | 22/1784 [01:19<1:39:59, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:28,185 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9747, 'learning_rate': 4.0000000000000003e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:29,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|█ | 23/1784 [01:22<1:39:27, 3.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:31,503 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7182, 'learning_rate': 4.2000000000000006e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:33,071 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|█ | 24/1784 [01:26<1:38:27, 3.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:34,794 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:36,358 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9117, 'learning_rate': 4.4e-07, 'epoch': 0.01} + 1%|█ | 25/1784 [01:29<1:37:46, 3.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:38,028 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.0119, 'learning_rate': 4.6000000000000004e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:39,622 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|█▏ | 26/1784 [01:32<1:37:05, 3.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:41,277 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.849, 'learning_rate': 4.800000000000001e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:42,854 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▏ | 27/1784 [01:36<1:36:19, 3.29s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:44,537 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5669, 'learning_rate': 5.000000000000001e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:46,157 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▏ | 28/1784 [01:39<1:36:24, 3.29s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:47,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9379, 'learning_rate': 5.2e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:49,373 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▎ | 29/1784 [01:42<1:35:37, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:51,032 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7604, 'learning_rate': 5.4e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:52,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▎ | 30/1784 [01:45<1:34:46, 3.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:54,176 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6528, 'learning_rate': 5.6e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:55,702 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▎ | 31/1784 [01:48<1:33:55, 3.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:38:57,328 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:38:58,824 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▍ | 32/1784 [01:51<1:33:05, 3.19s/it] + + 2%|█▍ | 32/1784 [01:51<1:33:05, 3.19s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:00,433 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7666, 'learning_rate': 6.000000000000001e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:01,894 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▍ | 33/1784 [01:55<1:32:00, 3.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:03,481 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:04,903 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▌ | 34/1784 [01:58<1:30:40, 3.11s/it] + + 2%|█▌ | 34/1784 [01:58<1:30:40, 3.11s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:06,435 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8797, 'learning_rate': 6.4e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:07,858 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▌ | 35/1784 [02:01<1:29:16, 3.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:09,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.1419, 'learning_rate': 6.6e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:10,804 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▌ | 36/1784 [02:03<1:28:12, 3.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:12,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7931, 'learning_rate': 6.800000000000001e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:13,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▋ | 37/1784 [02:06<1:26:35, 2.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:15,129 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8808, 'learning_rate': 7.000000000000001e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:16,460 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▋ | 38/1784 [02:09<1:25:05, 2.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:17,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:19,167 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▋ | 39/1784 [02:12<1:23:08, 2.86s/it] + + 2%|█▋ | 39/1784 [02:12<1:23:08, 2.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:20,550 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9645, 'learning_rate': 7.4e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:21,813 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▊ | 40/1784 [02:14<1:21:14, 2.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:23,174 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8041, 'learning_rate': 7.6e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:24,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▊ | 41/1784 [02:17<1:19:21, 2.73s/it] + 2%|█▊ | 41/1784 [02:17<1:19:21, 2.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:25,669 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:26,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▊ | 42/1784 [02:19<1:16:46, 2.64s/it] + 2%|█▊ | 42/1784 [02:19<1:16:46, 2.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:28,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:29,139 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▉ | 43/1784 [02:22<1:13:43, 2.54s/it] + 2%|█▉ | 43/1784 [02:22<1:13:43, 2.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:30,292 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:31,301 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▉ | 44/1784 [02:24<1:10:24, 2.43s/it] + 2%|█▉ | 44/1784 [02:24<1:10:24, 2.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:32,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:33,281 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|█▉ | 45/1784 [02:26<1:06:29, 2.29s/it] + 3%|█▉ | 45/1784 [02:26<1:06:29, 2.29s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:34,232 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:35,034 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██ | 46/1784 [02:28<1:01:44, 2.13s/it] + 3%|██ | 46/1784 [02:28<1:01:44, 2.13s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:35,888 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:36,604 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▏ | 47/1784 [02:29<56:50, 1.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:37,388 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.6315, 'learning_rate': 9.000000000000001e-07, 'epoch': 0.03} +{'loss': 5.6405, 'learning_rate': 9.200000000000001e-07, 'epoch': 0.03} +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:38,035 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▏ | 48/1784 [02:31<52:09, 1.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:38,722 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:39,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▏ | 49/1784 [02:32<47:22, 1.64s/it] + 3%|██▏ | 49/1784 [02:32<47:22, 1.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:39,951 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:39:41,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 50/1784 [02:34<48:33, 1.68s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:43,161 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 50/1784 [02:34<48:33, 1.68s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:43,161 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 51/1784 [02:38<1:08:22, 2.37s/it]g-point operations will not be computed-28 09:39:43,161 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 51/1784 [02:38<1:08:22, 2.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:46,961 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 51/1784 [02:38<1:08:22, 2.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:46,961 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 52/1784 [02:41<1:20:31, 2.79s/it]g-point operations will not be computed-28 09:39:46,961 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 52/1784 [02:41<1:20:31, 2.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:50,791 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 52/1784 [02:41<1:20:31, 2.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:50,791 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 53/1784 [02:45<1:29:28, 3.10s/it]g-point operations will not be computed-28 09:39:50,791 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 53/1784 [02:45<1:29:28, 3.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:54,562 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 53/1784 [02:45<1:29:28, 3.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:54,562 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▍ | 54/1784 [02:49<1:34:58, 3.29s/it]g-point operations will not be computed-28 09:39:54,562 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▍ | 54/1784 [02:49<1:34:58, 3.29s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:58,257 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▍ | 54/1784 [02:49<1:34:58, 3.29s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:39:58,257 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▍ | 55/1784 [02:53<1:38:02, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:01,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▍ | 55/1784 [02:53<1:38:02, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:01,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:40:03,667 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▍ | 56/1784 [02:56<1:39:55, 3.47s/it] + 3%|██▍ | 56/1784 [02:56<1:39:55, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:05,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▍ | 56/1784 [02:56<1:39:55, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:05,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▌ | 57/1784 [03:00<1:41:15, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:05,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▌ | 57/1784 [03:00<1:41:15, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:09,137 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▌ | 57/1784 [03:00<1:41:15, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:09,137 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▌ | 58/1784 [03:04<1:41:51, 3.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:09,137 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▌ | 58/1784 [03:04<1:41:51, 3.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:12,716 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▌ | 58/1784 [03:04<1:41:51, 3.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:12,716 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▌ | 59/1784 [03:07<1:41:44, 3.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:12,716 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▌ | 59/1784 [03:07<1:41:44, 3.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:16,289 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▌ | 59/1784 [03:07<1:41:44, 3.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:16,289 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▋ | 60/1784 [03:11<1:42:18, 3.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:19,869 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▋ | 60/1784 [03:11<1:42:18, 3.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:19,869 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▋ | 61/1784 [03:14<1:41:49, 3.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:19,869 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▋ | 61/1784 [03:14<1:41:49, 3.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:23,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▋ | 61/1784 [03:14<1:41:49, 3.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:23,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▋ | 62/1784 [03:18<1:41:21, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:23,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▋ | 62/1784 [03:18<1:41:21, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:26,834 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▋ | 62/1784 [03:18<1:41:21, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:26,834 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▊ | 63/1784 [03:21<1:41:08, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:30,389 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▊ | 64/1784 [03:25<1:41:06, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:30,389 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▊ | 64/1784 [03:25<1:41:06, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:30,389 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▊ | 64/1784 [03:25<1:41:06, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:33,867 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▊ | 64/1784 [03:25<1:41:06, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:33,867 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▉ | 65/1784 [03:28<1:40:28, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:33,867 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▉ | 65/1784 [03:28<1:40:28, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:37,296 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▉ | 65/1784 [03:28<1:40:28, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:37,296 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▉ | 66/1784 [03:32<1:39:38, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:37,296 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▉ | 66/1784 [03:32<1:39:38, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:37,296 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▉ | 67/1784 [03:35<1:39:24, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:40,752 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▉ | 67/1784 [03:35<1:39:24, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:44,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▉ | 67/1784 [03:35<1:39:24, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:44,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███ | 68/1784 [03:38<1:38:26, 3.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:44,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███ | 68/1784 [03:38<1:38:26, 3.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:47,521 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███ | 68/1784 [03:38<1:38:26, 3.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:47,521 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███ | 69/1784 [03:42<1:37:43, 3.42s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:50,902 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███ | 70/1784 [03:45<1:37:24, 3.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:50,902 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███ | 70/1784 [03:45<1:37:24, 3.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:50,902 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███ | 70/1784 [03:45<1:37:24, 3.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:54,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███ | 70/1784 [03:45<1:37:24, 3.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:54,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▏ | 71/1784 [03:49<1:36:34, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:54,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▏ | 71/1784 [03:49<1:36:34, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:57,605 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▏ | 71/1784 [03:49<1:36:34, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:40:57,605 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▏ | 72/1784 [03:52<1:36:24, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:00,954 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▏ | 73/1784 [03:55<1:36:03, 3.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:00,954 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▏ | 73/1784 [03:55<1:36:03, 3.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:00,954 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▏ | 73/1784 [03:55<1:36:03, 3.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:04,306 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▏ | 73/1784 [03:55<1:36:03, 3.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:04,306 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▎ | 74/1784 [03:59<1:35:25, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:04,306 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + [WARNING|modeling_utils.py:388] 2022-02-28 09:41:07,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + [WARNING|modeling_utils.py:388] 2022-02-28 09:41:07,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▎ | 75/1784 [04:02<1:34:53, 3.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:10,826 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▎ | 75/1784 [04:02<1:34:53, 3.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:10,826 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▎ | 76/1784 [04:05<1:33:47, 3.29s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:10,826 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 77/1784 [04:08<1:32:57, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:14,057 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 77/1784 [04:08<1:32:57, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:14,057 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 77/1784 [04:08<1:32:57, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:17,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 77/1784 [04:08<1:32:57, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:17,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 78/1784 [04:11<1:32:15, 3.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:17,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 78/1784 [04:11<1:32:15, 3.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:20,419 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 78/1784 [04:11<1:32:15, 3.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:20,419 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 79/1784 [04:15<1:31:18, 3.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:23,540 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 79/1784 [04:15<1:31:18, 3.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:23,540 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▌ | 80/1784 [04:18<1:30:28, 3.19s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:23,540 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + [WARNING|modeling_utils.py:388] 2022-02-28 09:41:26,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + [WARNING|modeling_utils.py:388] 2022-02-28 09:41:26,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▌ | 81/1784 [04:21<1:29:34, 3.16s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:29,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 82/1784 [04:24<1:28:22, 3.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:29,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 82/1784 [04:24<1:28:22, 3.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:29,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 83/1784 [04:27<1:27:56, 3.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:32,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 83/1784 [04:27<1:27:56, 3.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:32,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 83/1784 [04:27<1:27:56, 3.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:35,736 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 84/1784 [04:30<1:26:35, 3.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:35,736 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 84/1784 [04:30<1:26:35, 3.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:35,736 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 85/1784 [04:33<1:25:06, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:38,653 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 85/1784 [04:33<1:25:06, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:38,653 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 85/1784 [04:33<1:25:06, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:41,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 85/1784 [04:33<1:25:06, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:41,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 86/1784 [04:36<1:23:51, 2.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:44,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 87/1784 [04:38<1:22:44, 2.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:44,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 87/1784 [04:38<1:22:44, 2.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:44,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 88/1784 [04:41<1:20:48, 2.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:47,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 88/1784 [04:41<1:20:48, 2.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:47,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 88/1784 [04:41<1:20:48, 2.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:49,853 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 88/1784 [04:41<1:20:48, 2.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:49,853 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 89/1784 [04:44<1:18:55, 2.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:52,452 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 90/1784 [04:46<1:16:59, 2.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:54,916 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 90/1784 [04:46<1:16:59, 2.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:54,916 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 91/1784 [04:49<1:13:55, 2.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:54,916 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 91/1784 [04:49<1:13:55, 2.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:54,916 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 92/1784 [04:51<1:11:07, 2.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 92/1784 [04:51<1:11:07, 2.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 93/1784 [04:53<1:07:44, 2.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:59,475 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 93/1784 [04:53<1:07:44, 2.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:41:59,475 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▏ | 94/1784 [04:55<1:03:38, 2.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:01,490 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▏ | 94/1784 [04:55<1:03:38, 2.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:01,490 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 95/1784 [04:57<59:13, 2.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:03,353 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 95/1784 [04:57<59:13, 2.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:03,353 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 96/1784 [04:58<55:19, 1.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:06,566 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 96/1784 [04:58<55:19, 1.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:06,566 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5352, 'learning_rate': 1.8600000000000002e-06, 'epoch': 0.05} + 5%|████▍ | 98/1784 [05:01<46:31, 1.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:07,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▍ | 98/1784 [05:01<46:31, 1.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:07,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 99/1784 [05:02<43:08, 1.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:10,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 99/1784 [05:02<43:08, 1.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:10,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.1079, 'learning_rate': 1.9200000000000003e-06, 'epoch': 0.06} + 6%|████▍ | 100/1784 [05:04<43:51, 1.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:10,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 100/1784 [05:04<43:51, 1.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:13,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 100/1784 [05:04<43:51, 1.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:13,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 101/1784 [05:08<1:03:05, 2.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:13,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 102/1784 [05:12<1:15:29, 2.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:17,200 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 102/1784 [05:12<1:15:29, 2.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:17,200 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 102/1784 [05:12<1:15:29, 2.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:20,887 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 103/1784 [05:15<1:23:27, 2.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:20,887 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 103/1784 [05:15<1:23:27, 2.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:20,887 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 103/1784 [05:15<1:23:27, 2.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:24,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 104/1784 [05:19<1:29:25, 3.19s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:24,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 104/1784 [05:19<1:29:25, 3.19s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:24,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 104/1784 [05:19<1:29:25, 3.19s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:28,202 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 104/1784 [05:19<1:29:25, 3.19s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:28,202 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 105/1784 [05:23<1:32:58, 3.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:28,202 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 106/1784 [05:26<1:35:20, 3.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:31,809 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 106/1784 [05:26<1:35:20, 3.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:31,809 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 106/1784 [05:26<1:35:20, 3.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:35,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 107/1784 [05:30<1:36:23, 3.45s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:35,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 107/1784 [05:30<1:36:23, 3.45s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:35,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 107/1784 [05:30<1:36:23, 3.45s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:38,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 108/1784 [05:33<1:37:29, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:38,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 108/1784 [05:33<1:37:29, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:38,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 108/1784 [05:33<1:37:29, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:42,497 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 109/1784 [05:37<1:37:55, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:46,063 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 109/1784 [05:37<1:37:55, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:46,063 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 110/1784 [05:40<1:38:18, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:46,063 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 110/1784 [05:40<1:38:18, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:46,063 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 110/1784 [05:40<1:38:18, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:49,635 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 111/1784 [05:44<1:38:24, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:49,635 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 111/1784 [05:44<1:38:24, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:49,635 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 111/1784 [05:44<1:38:24, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:53,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 112/1784 [05:47<1:37:14, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:56,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 112/1784 [05:47<1:37:14, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:56,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2627, 'learning_rate': 2.16e-06, 'epoch': 0.06} + 6%|████▉ | 113/1784 [05:51<1:36:52, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:56,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 113/1784 [05:51<1:36:52, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:59,991 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 113/1784 [05:51<1:36:52, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:59,991 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 114/1784 [05:54<1:37:02, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:42:59,991 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 114/1784 [05:54<1:37:02, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:03,474 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 114/1784 [05:54<1:37:02, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:03,474 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 115/1784 [05:58<1:36:34, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:03,474 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 115/1784 [05:58<1:36:34, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:03,474 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 115/1784 [05:58<1:36:34, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:06,881 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████ | 116/1784 [06:01<1:36:35, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:10,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████ | 116/1784 [06:01<1:36:35, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:10,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████ | 117/1784 [06:05<1:36:06, 3.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:10,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████ | 117/1784 [06:05<1:36:06, 3.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:13,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████ | 117/1784 [06:05<1:36:06, 3.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:13,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 118/1784 [06:08<1:35:01, 3.42s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:13,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 119/1784 [06:11<1:34:28, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:17,113 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 119/1784 [06:11<1:34:28, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:17,113 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 119/1784 [06:11<1:34:28, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:20,456 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 119/1784 [06:11<1:34:28, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:20,456 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 120/1784 [06:15<1:33:41, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:20,456 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 120/1784 [06:15<1:33:41, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:23,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 120/1784 [06:15<1:33:41, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:23,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 121/1784 [06:18<1:32:52, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:27,057 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 121/1784 [06:18<1:32:52, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:27,057 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 122/1784 [06:21<1:32:54, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:27,057 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 122/1784 [06:21<1:32:54, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:30,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 122/1784 [06:21<1:32:54, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:30,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 123/1784 [06:25<1:32:25, 3.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:30,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 124/1784 [06:28<1:31:54, 3.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:33,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 124/1784 [06:28<1:31:54, 3.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:33,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 124/1784 [06:28<1:31:54, 3.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:36,946 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 124/1784 [06:28<1:31:54, 3.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:36,946 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 125/1784 [06:31<1:31:17, 3.30s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:36,946 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 126/1784 [06:34<1:30:29, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:40,197 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 126/1784 [06:34<1:30:29, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:40,197 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 126/1784 [06:34<1:30:29, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:43,405 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 126/1784 [06:34<1:30:29, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:43,405 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 127/1784 [06:38<1:29:39, 3.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:43,405 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 127/1784 [06:38<1:29:39, 3.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:46,559 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 127/1784 [06:38<1:29:39, 3.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:46,559 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 128/1784 [06:41<1:28:52, 3.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:46,559 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 128/1784 [06:41<1:28:52, 3.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:46,559 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 129/1784 [06:44<1:28:21, 3.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:49,701 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 129/1784 [06:44<1:28:21, 3.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:52,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 129/1784 [06:44<1:28:21, 3.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:52,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 130/1784 [06:47<1:27:28, 3.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:52,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 130/1784 [06:47<1:27:28, 3.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:52,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 131/1784 [06:50<1:26:33, 3.14s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:55,924 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 131/1784 [06:50<1:26:33, 3.14s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:58,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 131/1784 [06:50<1:26:33, 3.14s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:58,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 132/1784 [06:53<1:25:44, 3.11s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:58,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 132/1784 [06:53<1:25:44, 3.11s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:43:58,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 133/1784 [06:56<1:25:00, 3.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:02,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 133/1784 [06:56<1:25:00, 3.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:05,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 133/1784 [06:56<1:25:00, 3.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:05,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▊ | 134/1784 [06:59<1:23:25, 3.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:07,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▊ | 134/1784 [06:59<1:23:25, 3.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:07,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▉ | 135/1784 [07:02<1:22:28, 3.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:07,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▉ | 135/1784 [07:02<1:22:28, 3.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:10,855 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▉ | 135/1784 [07:02<1:22:28, 3.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:10,855 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▉ | 136/1784 [07:05<1:21:27, 2.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:13,658 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▉ | 136/1784 [07:05<1:21:27, 2.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:13,658 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▉ | 137/1784 [07:08<1:19:54, 2.91s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:16,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 138/1784 [07:10<1:18:36, 2.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:16,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 138/1784 [07:10<1:18:36, 2.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:16,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 139/1784 [07:13<1:16:45, 2.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:19,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 139/1784 [07:13<1:16:45, 2.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:19,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 139/1784 [07:13<1:16:45, 2.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:21,768 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 139/1784 [07:13<1:16:45, 2.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:21,768 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 140/1784 [07:16<1:15:01, 2.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:24,320 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 140/1784 [07:16<1:15:01, 2.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:24,320 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▏ | 141/1784 [07:18<1:12:50, 2.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:26,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▏ | 141/1784 [07:18<1:12:50, 2.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:26,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▏ | 142/1784 [07:20<1:10:15, 2.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:26,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▎ | 143/1784 [07:23<1:07:32, 2.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:29,026 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▎ | 143/1784 [07:23<1:07:32, 2.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:29,026 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▎ | 144/1784 [07:25<1:04:00, 2.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:31,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▎ | 144/1784 [07:25<1:04:00, 2.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:31,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▎ | 145/1784 [07:27<1:00:21, 2.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:33,115 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▎ | 145/1784 [07:27<1:00:21, 2.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:33,115 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7135, 'learning_rate': 2.82e-06, 'epoch': 0.08} + 8%|██████▌ | 146/1784 [07:28<56:32, 2.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:36,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 146/1784 [07:28<56:32, 2.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:36,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 148/1784 [07:31<48:09, 1.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:38,093 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 148/1784 [07:31<48:09, 1.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:38,093 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7001, 'learning_rate': 2.88e-06, 'epoch': 0.08} + 8%|██████▋ | 149/1784 [07:33<44:04, 1.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:40,646 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 149/1784 [07:33<44:04, 1.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:40,646 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 150/1784 [07:34<44:48, 1.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:40,646 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 150/1784 [07:34<44:48, 1.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:43,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 150/1784 [07:34<44:48, 1.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:43,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 151/1784 [07:38<1:03:02, 2.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:43,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 151/1784 [07:38<1:03:02, 2.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:47,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 151/1784 [07:38<1:03:02, 2.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:47,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 152/1784 [07:42<1:14:32, 2.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:51,236 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 152/1784 [07:42<1:14:32, 2.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:51,236 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 153/1784 [07:46<1:22:36, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:54,949 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 154/1784 [07:49<1:27:51, 3.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:54,949 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 154/1784 [07:49<1:27:51, 3.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:54,949 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 154/1784 [07:49<1:27:51, 3.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:58,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 155/1784 [07:53<1:31:08, 3.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:58,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 155/1784 [07:53<1:31:08, 3.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:44:58,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 155/1784 [07:53<1:31:08, 3.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:02,263 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 155/1784 [07:53<1:31:08, 3.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:02,263 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 156/1784 [07:57<1:33:18, 3.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:02,263 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 156/1784 [07:57<1:33:18, 3.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:05,858 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 156/1784 [07:57<1:33:18, 3.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:05,858 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 157/1784 [08:00<1:34:24, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:09,453 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 158/1784 [08:04<1:34:59, 3.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:09,453 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 158/1784 [08:04<1:34:59, 3.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:09,453 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 158/1784 [08:04<1:34:59, 3.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:12,994 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 159/1784 [08:07<1:35:12, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:12,994 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 159/1784 [08:07<1:35:12, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:12,994 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 159/1784 [08:07<1:35:12, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:16,537 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 159/1784 [08:07<1:35:12, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:16,537 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 160/1784 [08:11<1:35:20, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:16,537 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 160/1784 [08:11<1:35:20, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:20,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 160/1784 [08:11<1:35:20, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:20,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 161/1784 [08:14<1:35:19, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:23,541 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 162/1784 [08:18<1:34:47, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:23,541 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 162/1784 [08:18<1:34:47, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:23,541 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4913, 'learning_rate': 3.1600000000000002e-06, 'epoch': 0.09} + 9%|███████ | 162/1784 [08:18<1:34:47, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:23,541 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 163/1784 [08:21<1:34:14, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:23,541 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 163/1784 [08:21<1:34:14, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:23,541 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 163/1784 [08:21<1:34:14, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:23,541 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 164/1784 [08:25<1:33:44, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 165/1784 [08:28<1:33:24, 3.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 165/1784 [08:28<1:33:24, 3.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3314, 'learning_rate': 3.2200000000000005e-06, 'epoch': 0.09} + 9%|███████▎ | 166/1784 [08:32<1:32:39, 3.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 166/1784 [08:32<1:32:39, 3.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:45:42,237 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:45:42,237 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3964, 'learning_rate': 3.2600000000000006e-06, 'epoch': 0.09} + 9%|███████▎ | 168/1784 [08:38<1:31:13, 3.39s/it]g-point operations will not be computed-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 168/1784 [08:38<1:31:13, 3.39s/it]g-point operations will not be computed-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.088, 'learning_rate': 3.2800000000000004e-06, 'epoch': 0.09} + 9%|███████▎ | 168/1784 [08:38<1:31:13, 3.39s/it]g-point operations will not be computed-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▍ | 169/1784 [08:42<1:30:48, 3.37s/it]g-point operations will not be computed-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:45:52,334 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:45:52,334 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.344, 'learning_rate': 3.3200000000000004e-06, 'epoch': 0.1} + 10%|███████▍ | 171/1784 [08:48<1:30:25, 3.36s/it]g-point operations will not be computed-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▍ | 171/1784 [08:48<1:30:25, 3.36s/it]g-point operations will not be computed-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4334, 'learning_rate': 3.3400000000000006e-06, 'epoch': 0.1} + 10%|███████▍ | 171/1784 [08:48<1:30:25, 3.36s/it]g-point operations will not be computed-28 09:45:33,877 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 172/1784 [08:52<1:30:10, 3.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:00,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 173/1784 [08:55<1:29:46, 3.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:00,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 173/1784 [08:55<1:29:46, 3.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:00,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3677, 'learning_rate': 3.3800000000000007e-06, 'epoch': 0.1} + 10%|███████▌ | 174/1784 [08:58<1:28:56, 3.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:00,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 174/1784 [08:58<1:28:56, 3.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:00,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:46:08,825 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:46:00,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:46:08,825 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:46:00,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4863, 'learning_rate': 3.4200000000000007e-06, 'epoch': 0.1} + 10%|███████▋ | 176/1784 [09:05<1:27:41, 3.27s/it]g-point operations will not be computed-28 09:46:00,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▋ | 176/1784 [09:05<1:27:41, 3.27s/it]g-point operations will not be computed-28 09:46:00,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:46:15,260 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:46:00,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:46:15,260 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:46:00,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2847, 'learning_rate': 3.46e-06, 'epoch': 0.1} + 10%|███████▊ | 178/1784 [09:11<1:26:30, 3.23s/it]g-point operations will not be computed-28 09:46:00,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 178/1784 [09:11<1:26:30, 3.23s/it]g-point operations will not be computed-28 09:46:00,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2671, 'learning_rate': 3.48e-06, 'epoch': 0.1} + 10%|███████▊ | 178/1784 [09:11<1:26:30, 3.23s/it]g-point operations will not be computed-28 09:46:00,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 179/1784 [09:14<1:25:35, 3.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:23,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 180/1784 [09:17<1:24:53, 3.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:23,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 180/1784 [09:17<1:24:53, 3.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:23,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4798, 'learning_rate': 3.52e-06, 'epoch': 0.1} + 10%|███████▊ | 180/1784 [09:17<1:24:53, 3.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:23,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▉ | 181/1784 [09:20<1:24:30, 3.16s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:29,414 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▉ | 182/1784 [09:24<1:23:32, 3.13s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:29,414 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▉ | 182/1784 [09:24<1:23:32, 3.13s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:29,414 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2923, 'learning_rate': 3.5600000000000002e-06, 'epoch': 0.1} + 10%|███████▉ | 182/1784 [09:24<1:23:32, 3.13s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:29,414 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 183/1784 [09:27<1:22:22, 3.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:35,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 184/1784 [09:29<1:20:51, 3.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:35,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 184/1784 [09:29<1:20:51, 3.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:35,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:46:39,668 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:46:35,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:46:39,668 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:46:35,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4057, 'learning_rate': 3.62e-06, 'epoch': 0.1} + 10%|████████▏ | 186/1784 [09:35<1:18:43, 2.96s/it]g-point operations will not be computed-28 09:46:35,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████▏ | 186/1784 [09:35<1:18:43, 2.96s/it]g-point operations will not be computed-28 09:46:35,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:46:45,432 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:46:35,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:46:45,432 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:46:35,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2751, 'learning_rate': 3.66e-06, 'epoch': 0.1} +[WARNING|modeling_utils.py:388] 2022-02-28 09:46:45,432 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:46:35,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▏ | 188/1784 [09:41<1:17:30, 2.91s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:49,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 189/1784 [09:44<1:15:33, 2.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:49,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 189/1784 [09:44<1:15:33, 2.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:49,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:46:53,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:46:49,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:46:53,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:46:49,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:46:55,981 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:46:49,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:46:55,981 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:46:49,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4653, 'learning_rate': 3.74e-06, 'epoch': 0.11} +[WARNING|modeling_utils.py:388] 2022-02-28 09:46:55,981 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:46:49,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 192/1784 [09:51<1:08:05, 2.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:59,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 192/1784 [09:51<1:08:05, 2.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:46:59,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 193/1784 [09:53<1:04:45, 2.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:01,558 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 193/1784 [09:53<1:04:45, 2.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:01,558 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 194/1784 [09:55<1:01:52, 2.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:03,587 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 194/1784 [09:55<1:01:52, 2.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:03,587 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 195/1784 [09:57<58:49, 2.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:05,465 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 195/1784 [09:57<58:49, 2.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:05,465 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 197/1784 [10:01<51:17, 1.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:07,138 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 197/1784 [10:01<51:17, 1.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:07,138 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 198/1784 [10:02<47:17, 1.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:10,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 198/1784 [10:02<47:17, 1.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:10,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4062, 'learning_rate': 3.88e-06, 'epoch': 0.11} + 11%|████████▉ | 199/1784 [10:03<43:07, 1.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:11,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 199/1784 [10:03<43:07, 1.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:11,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 200/1784 [10:05<43:34, 1.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:11,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 201/1784 [10:09<1:01:08, 2.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:14,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 201/1784 [10:09<1:01:08, 2.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:14,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 201/1784 [10:09<1:01:08, 2.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 202/1784 [10:13<1:12:30, 2.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 202/1784 [10:13<1:12:30, 2.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2316, 'learning_rate': 3.96e-06, 'epoch': 0.11} + 11%|████████▉ | 203/1784 [10:16<1:19:36, 3.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 203/1784 [10:16<1:19:36, 3.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4342, 'learning_rate': 3.980000000000001e-06, 'epoch': 0.11} + 11%|████████▉ | 204/1784 [10:20<1:24:47, 3.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 204/1784 [10:20<1:24:47, 3.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1104, 'learning_rate': 4.000000000000001e-06, 'epoch': 0.11} + 11%|████████▉ | 204/1784 [10:20<1:24:47, 3.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 205/1784 [10:23<1:27:32, 3.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:47:34,355 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:47:34,355 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3397, 'learning_rate': 4.04e-06, 'epoch': 0.12} + 12%|█████████ | 207/1784 [10:31<1:30:05, 3.43s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████ | 207/1784 [10:31<1:30:05, 3.43s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4085, 'learning_rate': 4.060000000000001e-06, 'epoch': 0.12} + 12%|█████████ | 208/1784 [10:34<1:31:12, 3.47s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████ | 208/1784 [10:34<1:31:12, 3.47s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:47:44,964 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:47:44,964 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:47:44,964 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▏ | 210/1784 [10:41<1:31:35, 3.49s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▏ | 210/1784 [10:41<1:31:35, 3.49s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3254, 'learning_rate': 4.12e-06, 'epoch': 0.12} + 12%|█████████▏ | 211/1784 [10:45<1:31:35, 3.49s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▏ | 211/1784 [10:45<1:31:35, 3.49s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:47:55,409 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:47:55,409 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2394, 'learning_rate': 4.16e-06, 'epoch': 0.12} +[WARNING|modeling_utils.py:388] 2022-02-28 09:47:55,409 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▎ | 213/1784 [10:51<1:30:31, 3.46s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▎ | 213/1784 [10:51<1:30:31, 3.46s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▎ | 213/1784 [10:51<1:30:31, 3.46s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▎ | 214/1784 [10:55<1:30:18, 3.45s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:48:05,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:48:05,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4445, 'learning_rate': 4.22e-06, 'epoch': 0.12} +[WARNING|modeling_utils.py:388] 2022-02-28 09:48:05,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▍ | 216/1784 [11:02<1:29:30, 3.43s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▍ | 216/1784 [11:02<1:29:30, 3.43s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▍ | 216/1784 [11:02<1:29:30, 3.43s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▍ | 217/1784 [11:05<1:28:57, 3.41s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▍ | 217/1784 [11:05<1:28:57, 3.41s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▍ | 217/1784 [11:05<1:28:57, 3.41s/it]g-point operations will not be computed-28 09:47:18,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▌ | 218/1784 [11:08<1:28:31, 3.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:17,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▌ | 218/1784 [11:08<1:28:31, 3.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:17,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▌ | 219/1784 [11:12<1:27:36, 3.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:17,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▌ | 219/1784 [11:12<1:27:36, 3.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:17,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▌ | 219/1784 [11:12<1:27:36, 3.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:17,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▌ | 220/1784 [11:15<1:26:56, 3.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:17,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:48:25,622 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:48:17,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:48:25,622 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:48:17,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3815, 'learning_rate': 4.34e-06, 'epoch': 0.12} + 12%|█████████▋ | 222/1784 [11:22<1:26:16, 3.31s/it]g-point operations will not be computed-28 09:48:17,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▋ | 222/1784 [11:22<1:26:16, 3.31s/it]g-point operations will not be computed-28 09:48:17,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3849, 'learning_rate': 4.360000000000001e-06, 'epoch': 0.12} + 12%|█████████▋ | 222/1784 [11:22<1:26:16, 3.31s/it]g-point operations will not be computed-28 09:48:17,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▊ | 223/1784 [11:25<1:26:08, 3.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:33,916 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▊ | 223/1784 [11:25<1:26:08, 3.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:33,916 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|█████████▊ | 224/1784 [11:28<1:25:50, 3.30s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:33,916 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|█████████▊ | 224/1784 [11:28<1:25:50, 3.30s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:33,916 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|█████████▊ | 225/1784 [11:31<1:24:54, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|█████████▊ | 225/1784 [11:31<1:24:54, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|█████████▉ | 226/1784 [11:35<1:24:31, 3.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|█████████▉ | 226/1784 [11:35<1:24:31, 3.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4939, 'learning_rate': 4.440000000000001e-06, 'epoch': 0.13} + 13%|█████████▉ | 227/1784 [11:38<1:23:35, 3.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|█████████▉ | 227/1784 [11:38<1:23:35, 3.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:48:48,195 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:48:48,195 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0854, 'learning_rate': 4.48e-06, 'epoch': 0.13} + 13%|██████████ | 229/1784 [11:44<1:22:20, 3.18s/it]g-point operations will not be computed-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 229/1784 [11:44<1:22:20, 3.18s/it]g-point operations will not be computed-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:48:54,411 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:48:54,411 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2702, 'learning_rate': 4.520000000000001e-06, 'epoch': 0.13} + 13%|██████████ | 231/1784 [11:50<1:20:54, 3.13s/it]g-point operations will not be computed-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 231/1784 [11:50<1:20:54, 3.13s/it]g-point operations will not be computed-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:00,501 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:00,501 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:48:40,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2866, 'learning_rate': 4.56e-06, 'epoch': 0.13} + 13%|██████████▏ | 233/1784 [11:56<1:19:03, 3.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:49:04,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 233/1784 [11:56<1:19:03, 3.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:49:04,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.447, 'learning_rate': 4.58e-06, 'epoch': 0.13} + 13%|██████████▏ | 234/1784 [11:59<1:17:50, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:49:04,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:09,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:04,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:09,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:04,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:09,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:04,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 236/1784 [12:05<1:15:27, 2.92s/it]g-point operations will not be computed-28 09:49:04,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 236/1784 [12:05<1:15:27, 2.92s/it]g-point operations will not be computed-28 09:49:04,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:14,833 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:04,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:14,833 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:04,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3739, 'learning_rate': 4.66e-06, 'epoch': 0.13} + 13%|██████████▍ | 238/1784 [12:10<1:12:27, 2.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:49:18,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 238/1784 [12:10<1:12:27, 2.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:49:18,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3531, 'learning_rate': 4.680000000000001e-06, 'epoch': 0.13} + 13%|██████████▍ | 239/1784 [12:13<1:10:54, 2.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 239/1784 [12:13<1:10:54, 2.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 240/1784 [12:15<1:08:41, 2.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 240/1784 [12:15<1:08:41, 2.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:24,829 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:24,829 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:26,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:26,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:28,884 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:28,884 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:30,666 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:30,666 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:32,354 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:32,354 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:35,300 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:35,300 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4221, 'learning_rate': 4.86e-06, 'epoch': 0.14} +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:36,575 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:36,575 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.179, 'learning_rate': 4.9000000000000005e-06, 'epoch': 0.14} +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:39,448 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:39,448 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:43,384 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:43,384 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2367, 'learning_rate': 4.94e-06, 'epoch': 0.14} +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:43,384 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:47,128 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:47,128 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:49:47,128 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 253/1784 [12:44<1:16:57, 3.02s/it]g-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 253/1784 [12:44<1:16:57, 3.02s/it]g-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 253/1784 [12:44<1:16:57, 3.02s/it]g-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 254/1784 [12:47<1:22:30, 3.24s/it]g-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 254/1784 [12:47<1:22:30, 3.24s/it]g-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 254/1784 [12:47<1:22:30, 3.24s/it]g-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 255/1784 [12:51<1:25:36, 3.36s/it]g-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:50:01,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:50:01,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2106, 'learning_rate': 5.04e-06, 'epoch': 0.14} +[WARNING|modeling_utils.py:388] 2022-02-28 09:50:01,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 257/1784 [12:58<1:28:35, 3.48s/it]g-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 257/1784 [12:58<1:28:35, 3.48s/it]g-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 257/1784 [12:58<1:28:35, 3.48s/it]g-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▎ | 258/1784 [13:02<1:29:07, 3.50s/it]g-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▎ | 258/1784 [13:02<1:29:07, 3.50s/it]g-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▎ | 258/1784 [13:02<1:29:07, 3.50s/it]g-point operations will not be computed-28 09:49:21,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▎ | 259/1784 [13:05<1:29:22, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:14,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▎ | 259/1784 [13:05<1:29:22, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:14,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▎ | 260/1784 [13:09<1:30:01, 3.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:17,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▎ | 260/1784 [13:09<1:30:01, 3.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:17,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▍ | 261/1784 [13:12<1:29:41, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:17,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▍ | 261/1784 [13:12<1:29:41, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:17,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▍ | 261/1784 [13:12<1:29:41, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:17,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▍ | 262/1784 [13:16<1:29:06, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:17,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▍ | 262/1784 [13:16<1:29:06, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:17,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▍ | 262/1784 [13:16<1:29:06, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:17,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▍ | 263/1784 [13:19<1:28:50, 3.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▍ | 263/1784 [13:19<1:28:50, 3.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▌ | 264/1784 [13:23<1:28:50, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▌ | 264/1784 [13:23<1:28:50, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▌ | 264/1784 [13:23<1:28:50, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▌ | 265/1784 [13:26<1:28:14, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▌ | 265/1784 [13:26<1:28:14, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▌ | 265/1784 [13:26<1:28:14, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▋ | 266/1784 [13:30<1:27:37, 3.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▋ | 266/1784 [13:30<1:27:37, 3.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:50:40,393 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:50:40,393 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:50:40,393 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▋ | 268/1784 [13:36<1:26:14, 3.41s/it]g-point operations will not be computed-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▋ | 268/1784 [13:36<1:26:14, 3.41s/it]g-point operations will not be computed-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▋ | 268/1784 [13:36<1:26:14, 3.41s/it]g-point operations will not be computed-28 09:50:28,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▊ | 269/1784 [13:40<1:25:33, 3.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:48,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▊ | 269/1784 [13:40<1:25:33, 3.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:48,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▊ | 270/1784 [13:43<1:25:18, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:48,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▊ | 270/1784 [13:43<1:25:18, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:48,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▊ | 270/1784 [13:43<1:25:18, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:48,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▊ | 271/1784 [13:46<1:24:50, 3.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:50:48,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:50:57,034 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:50:48,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:50:57,034 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:50:48,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1232, 'learning_rate': 5.36e-06, 'epoch': 0.15} +[WARNING|modeling_utils.py:388] 2022-02-28 09:50:57,034 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:50:48,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▉ | 273/1784 [13:53<1:23:53, 3.33s/it]g-point operations will not be computed-28 09:50:48,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▉ | 273/1784 [13:53<1:23:53, 3.33s/it]g-point operations will not be computed-28 09:50:48,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▉ | 273/1784 [13:53<1:23:53, 3.33s/it]g-point operations will not be computed-28 09:50:48,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▉ | 274/1784 [13:56<1:23:19, 3.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▉ | 274/1784 [13:56<1:23:19, 3.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████ | 275/1784 [13:59<1:22:29, 3.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████ | 275/1784 [13:59<1:22:29, 3.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████ | 275/1784 [13:59<1:22:29, 3.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████ | 276/1784 [14:03<1:22:08, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████ | 276/1784 [14:03<1:22:08, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:13,270 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:13,270 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:13,270 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▏ | 278/1784 [14:09<1:20:48, 3.22s/it]g-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:19,565 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:19,565 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2352, 'learning_rate': 5.500000000000001e-06, 'epoch': 0.16} +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:19,565 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▏ | 280/1784 [14:15<1:19:33, 3.17s/it]g-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:25,773 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:25,773 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.312, 'learning_rate': 5.540000000000001e-06, 'epoch': 0.16} +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:25,773 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▎ | 282/1784 [14:22<1:18:29, 3.14s/it]g-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:31,903 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:31,903 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3619, 'learning_rate': 5.580000000000001e-06, 'epoch': 0.16} +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:31,903 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▍ | 284/1784 [14:28<1:16:32, 3.06s/it]g-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:37,819 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:37,819 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2813, 'learning_rate': 5.620000000000001e-06, 'epoch': 0.16} +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:37,819 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:05,254 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▌ | 286/1784 [14:33<1:14:22, 2.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:51:42,145 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▌ | 286/1784 [14:33<1:14:22, 2.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:51:42,145 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▌ | 287/1784 [14:36<1:13:23, 2.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:51:42,145 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:46,218 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:42,145 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:46,218 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:42,145 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5288, 'learning_rate': 5.68e-06, 'epoch': 0.16} +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:46,218 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:42,145 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▋ | 289/1784 [14:41<1:09:25, 2.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▋ | 289/1784 [14:41<1:09:25, 2.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▋ | 290/1784 [14:44<1:07:21, 2.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|███████���████▋ | 290/1784 [14:44<1:07:21, 2.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:53,686 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:53,686 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:55,908 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:55,908 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:58,033 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:51:58,033 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:00,027 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:00,027 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:01,904 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:01,904 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:03,667 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:03,667 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:06,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:06,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5077, 'learning_rate': 5.8800000000000005e-06, 'epoch': 0.17} +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:08,060 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:08,060 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:09,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:09,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:09,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:13,820 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:13,820 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:13,820 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▏ | 302/1784 [15:10<1:08:45, 2.78s/it]g-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:52:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3298, 'learning_rate': 5.98e-06, 'epoch': 0.17} + 17%|█████████████▎ | 304/1784 [15:18<1:20:02, 3.25s/it]g-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 304/1784 [15:18<1:20:02, 3.25s/it]g-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1611, 'learning_rate': 6e-06, 'epoch': 0.17} + 17%|█████████████▎ | 305/1784 [15:21<1:23:03, 3.37s/it]g-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 305/1784 [15:21<1:23:03, 3.37s/it]g-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3209, 'learning_rate': 6.02e-06, 'epoch': 0.17} + 17%|█████████████▎ | 305/1784 [15:21<1:23:03, 3.37s/it]g-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 306/1784 [15:25<1:24:49, 3.44s/it]g-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 306/1784 [15:25<1:24:49, 3.44s/it]g-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 306/1784 [15:25<1:24:49, 3.44s/it]g-point operations will not be computed-28 09:51:50,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 307/1784 [15:28<1:25:38, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:37,642 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 308/1784 [15:32<1:26:23, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:37,642 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 308/1784 [15:32<1:26:23, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:37,642 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4931, 'learning_rate': 6.08e-06, 'epoch': 0.17} + 17%|█████████████▌ | 309/1784 [15:36<1:26:51, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:37,642 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 309/1784 [15:36<1:26:51, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:37,642 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4734, 'learning_rate': 6.1e-06, 'epoch': 0.17} + 17%|█████████████▌ | 309/1784 [15:36<1:26:51, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:37,642 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 310/1784 [15:39<1:26:39, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:37,642 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 310/1784 [15:39<1:26:39, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:37,642 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 310/1784 [15:39<1:26:39, 3.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:37,642 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 311/1784 [15:43<1:26:28, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:51,799 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▋ | 312/1784 [15:46<1:26:24, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:51,799 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▋ | 312/1784 [15:46<1:26:24, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:51,799 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2364, 'learning_rate': 6.16e-06, 'epoch': 0.17} + 17%|█████████████▋ | 312/1784 [15:46<1:26:24, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:51,799 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▋ | 313/1784 [15:50<1:26:00, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:51,799 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▋ | 313/1784 [15:50<1:26:00, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:51,799 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▋ | 313/1784 [15:50<1:26:00, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:52:51,799 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▋ | 314/1784 [15:53<1:25:11, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:02,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▊ | 315/1784 [15:56<1:24:44, 3.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:02,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▊ | 315/1784 [15:56<1:24:44, 3.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:02,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4123, 'learning_rate': 6.220000000000001e-06, 'epoch': 0.18} + 18%|█████████████▊ | 316/1784 [16:00<1:23:58, 3.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:02,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▊ | 316/1784 [16:00<1:23:58, 3.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:02,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:53:10,543 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:53:02,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:53:10,543 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:53:02,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2291, 'learning_rate': 6.26e-06, 'epoch': 0.18} + 18%|█████████████▉ | 318/1784 [16:07<1:23:42, 3.43s/it]g-point operations will not be computed-28 09:53:02,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▉ | 318/1784 [16:07<1:23:42, 3.43s/it]g-point operations will not be computed-28 09:53:02,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.9427, 'learning_rate': 6.280000000000001e-06, 'epoch': 0.18} + 18%|█████████████▉ | 318/1784 [16:07<1:23:42, 3.43s/it]g-point operations will not be computed-28 09:53:02,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▉ | 319/1784 [16:10<1:23:11, 3.41s/it]g-point operations will not be computed-28 09:53:02,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▉ | 319/1784 [16:10<1:23:11, 3.41s/it]g-point operations will not be computed-28 09:53:02,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▉ | 319/1784 [16:10<1:23:11, 3.41s/it]g-point operations will not be computed-28 09:53:02,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▉ | 320/1784 [16:13<1:22:29, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:22,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████ | 321/1784 [16:17<1:21:41, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:22,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████ | 321/1784 [16:17<1:21:41, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:22,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5014, 'learning_rate': 6.34e-06, 'epoch': 0.18} + 18%|██████████████ | 321/1784 [16:17<1:21:41, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:22,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████ | 322/1784 [16:20<1:21:29, 3.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:22,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:53:30,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:53:22,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:53:30,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:53:22,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3505, 'learning_rate': 6.380000000000001e-06, 'epoch': 0.18} + 18%|██████████████▏ | 324/1784 [16:26<1:20:02, 3.29s/it]g-point operations will not be computed-28 09:53:22,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▏ | 324/1784 [16:26<1:20:02, 3.29s/it]g-point operations will not be computed-28 09:53:22,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:53:36,969 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:53:22,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:53:36,969 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:53:22,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2019, 'learning_rate': 6.42e-06, 'epoch': 0.18} + 18%|██████████████▎ | 326/1784 [16:33<1:18:56, 3.25s/it]g-point operations will not be computed-28 09:53:22,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▎ | 326/1784 [16:33<1:18:56, 3.25s/it]g-point operations will not be computed-28 09:53:22,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1783, 'learning_rate': 6.440000000000001e-06, 'epoch': 0.18} + 18%|██████████████▎ | 326/1784 [16:33<1:18:56, 3.25s/it]g-point operations will not be computed-28 09:53:22,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▎ | 327/1784 [16:36<1:18:31, 3.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:45,031 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▎ | 328/1784 [16:39<1:17:42, 3.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:45,031 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▎ | 328/1784 [16:39<1:17:42, 3.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:45,031 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2332, 'learning_rate': 6.480000000000001e-06, 'epoch': 0.18} + 18%|██████████████▎ | 328/1784 [16:39<1:17:42, 3.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:45,031 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▍ | 329/1784 [16:42<1:17:23, 3.19s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:51,300 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▍ | 330/1784 [16:45<1:16:45, 3.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:51,300 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▍ | 330/1784 [16:45<1:16:45, 3.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:51,300 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4648, 'learning_rate': 6.520000000000001e-06, 'epoch': 0.18} + 18%|██████████████▍ | 330/1784 [16:45<1:16:45, 3.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:51,300 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▍ | 331/1784 [16:49<1:16:00, 3.14s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:57,442 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▌ | 332/1784 [16:52<1:15:24, 3.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:57,442 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▌ | 332/1784 [16:52<1:15:24, 3.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:57,442 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3966, 'learning_rate': 6.560000000000001e-06, 'epoch': 0.19} + 19%|██████████████▌ | 332/1784 [16:52<1:15:24, 3.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:53:57,442 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▌ | 333/1784 [16:55<1:14:28, 3.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:03,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▌ | 334/1784 [16:57<1:13:05, 3.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:03,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▌ | 334/1784 [16:57<1:13:05, 3.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:03,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:54:07,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:54:03,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:54:07,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:54:03,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3986, 'learning_rate': 6.620000000000001e-06, 'epoch': 0.19} +[WARNING|modeling_utils.py:388] 2022-02-28 09:54:07,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:54:03,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▋ | 336/1784 [17:03<1:11:06, 2.95s/it]g-point operations will not be computed-28 09:54:03,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:54:13,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:54:03,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:54:13,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:54:03,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2845, 'learning_rate': 6.660000000000001e-06, 'epoch': 0.19} +[WARNING|modeling_utils.py:388] 2022-02-28 09:54:13,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:54:03,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▊ | 338/1784 [17:09<1:09:11, 2.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:17,594 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▊ | 338/1784 [17:09<1:09:11, 2.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:17,594 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▊ | 339/1784 [17:12<1:07:48, 2.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:17,594 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:54:21,474 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:54:17,594 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:54:21,474 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:54:17,594 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:54:24,053 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:54:17,594 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:54:24,053 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:54:17,594 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2032, 'learning_rate': 6.740000000000001e-06, 'epoch': 0.19} +[WARNING|modeling_utils.py:388] 2022-02-28 09:54:24,053 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:54:17,594 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▉ | 342/1784 [17:19<1:02:49, 2.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:27,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▉ | 343/1784 [17:21<1:00:23, 2.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:29,905 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▉ | 343/1784 [17:21<1:00:23, 2.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:29,905 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▍ | 344/1784 [17:24<57:48, 2.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:31,964 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▍ | 344/1784 [17:24<57:48, 2.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:31,964 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0314, 'learning_rate': 6.800000000000001e-06, 'epoch': 0.19} + 19%|███████████████▍ | 345/1784 [17:26<54:31, 2.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:33,848 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▍ | 345/1784 [17:26<54:31, 2.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:33,848 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▌ | 346/1784 [17:27<51:18, 2.14s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:35,581 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▌ | 346/1784 [17:27<51:18, 2.14s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:35,581 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 348/1784 [17:30<43:56, 1.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:37,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 348/1784 [17:30<43:56, 1.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:37,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5665, 'learning_rate': 6.88e-06, 'epoch': 0.2} + 20%|███████████████▋ | 349/1784 [17:32<39:56, 1.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:39,749 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▋ | 350/1784 [17:34<40:22, 1.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:39,749 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▋ | 350/1784 [17:34<40:22, 1.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:39,749 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▋ | 350/1784 [17:34<40:22, 1.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:42,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▋ | 350/1784 [17:34<40:22, 1.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:42,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▋ | 351/1784 [17:37<56:25, 2.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:54:42,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:54:48,500 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:54:42,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:54:48,500 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:54:42,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.412, 'learning_rate': 6.96e-06, 'epoch': 0.2} + 20%|███████████████▍ | 353/1784 [17:45<1:12:27, 3.04s/it]g-point operations will not be computed-28 09:54:42,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▍ | 353/1784 [17:45<1:12:27, 3.04s/it]g-point operations will not be computed-28 09:54:42,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0509, 'learning_rate': 6.98e-06, 'epoch': 0.2} + 20%|███████████████▍ | 354/1784 [17:48<1:16:56, 3.23s/it]g-point operations will not be computed-28 09:54:42,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▍ | 354/1784 [17:48<1:16:56, 3.23s/it]g-point operations will not be computed-28 09:54:42,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.222, 'learning_rate': 7e-06, 'epoch': 0.2} + 20%|███████████████▌ | 355/1784 [17:52<1:19:57, 3.36s/it]g-point operations will not be computed-28 09:54:42,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 355/1784 [17:52<1:19:57, 3.36s/it]g-point operations will not be computed-28 09:54:42,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.8822, 'learning_rate': 7.0200000000000006e-06, 'epoch': 0.2} + 20%|███████████████▌ | 355/1784 [17:52<1:19:57, 3.36s/it]g-point operations will not be computed-28 09:54:42,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 356/1784 [17:56<1:21:37, 3.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 357/1784 [17:59<1:22:12, 3.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 357/1784 [17:59<1:22:12, 3.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3387, 'learning_rate': 7.06e-06, 'epoch': 0.2} + 20%|███████████████▋ | 358/1784 [18:03<1:22:54, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▋ | 358/1784 [18:03<1:22:54, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3317, 'learning_rate': 7.08e-06, 'epoch': 0.2} + 20%|███████████████▋ | 359/1784 [18:06<1:23:22, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▋ | 359/1784 [18:06<1:23:22, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:55:17,324 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:55:17,324 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2113, 'learning_rate': 7.1200000000000004e-06, 'epoch': 0.2} + 20%|███████████████▊ | 361/1784 [18:14<1:23:53, 3.54s/it]g-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▊ | 361/1784 [18:14<1:23:53, 3.54s/it]g-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2384, 'learning_rate': 7.14e-06, 'epoch': 0.2} + 20%|███████████████▊ | 362/1784 [18:17<1:23:14, 3.51s/it]g-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▊ | 362/1784 [18:17<1:23:14, 3.51s/it]g-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0246, 'learning_rate': 7.16e-06, 'epoch': 0.2} + 20%|███████████████▊ | 362/1784 [18:17<1:23:14, 3.51s/it]g-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▊ | 363/1784 [18:20<1:22:39, 3.49s/it]g-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:55:31,173 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:55:31,173 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.319, 'learning_rate': 7.2000000000000005e-06, 'epoch': 0.2} + 20%|███████████████▉ | 365/1784 [18:27<1:21:48, 3.46s/it]g-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▉ | 365/1784 [18:27<1:21:48, 3.46s/it]g-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2642, 'learning_rate': 7.22e-06, 'epoch': 0.2} + 21%|████████████████ | 366/1784 [18:31<1:20:56, 3.43s/it]g-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████ | 366/1784 [18:31<1:20:56, 3.43s/it]g-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:55:41,360 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:55:41,360 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2273, 'learning_rate': 7.260000000000001e-06, 'epoch': 0.21} + 21%|████████████████ | 368/1784 [18:37<1:19:56, 3.39s/it]g-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████ | 368/1784 [18:37<1:19:56, 3.39s/it]g-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1541, 'learning_rate': 7.280000000000001e-06, 'epoch': 0.21} + 21%|████████████████ | 368/1784 [18:37<1:19:56, 3.39s/it]g-point operations will not be computed-28 09:55:04,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▏ | 369/1784 [18:41<1:19:44, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:55:49,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▏ | 370/1784 [18:44<1:19:48, 3.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:55:49,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▏ | 370/1784 [18:44<1:19:48, 3.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:55:49,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1406, 'learning_rate': 7.32e-06, 'epoch': 0.21} + 21%|████████████████▏ | 371/1784 [18:47<1:19:15, 3.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:55:49,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▏ | 371/1784 [18:47<1:19:15, 3.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:55:49,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:55:58,083 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:55:49,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:55:58,083 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:55:49,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5768, 'learning_rate': 7.360000000000001e-06, 'epoch': 0.21} + 21%|████████████████▎ | 373/1784 [18:54<1:18:18, 3.33s/it]g-point operations will not be computed-28 09:55:49,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 373/1784 [18:54<1:18:18, 3.33s/it]g-point operations will not be computed-28 09:55:49,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2027, 'learning_rate': 7.3800000000000005e-06, 'epoch': 0.21} + 21%|████████████████▎ | 374/1784 [18:57<1:17:31, 3.30s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▎ | 374/1784 [18:57<1:17:31, 3.30s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▍ | 375/1784 [19:00<1:16:36, 3.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▍ | 375/1784 [19:00<1:16:36, 3.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0183, 'learning_rate': 7.420000000000001e-06, 'epoch': 0.21} + 21%|████████████████▍ | 376/1784 [19:04<1:15:50, 3.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▍ | 376/1784 [19:04<1:15:50, 3.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:14,143 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:14,143 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1234, 'learning_rate': 7.4600000000000006e-06, 'epoch': 0.21} + 21%|████████████████▌ | 378/1784 [19:10<1:14:58, 3.20s/it]g-point operations will not be computed-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 378/1784 [19:10<1:14:58, 3.20s/it]g-point operations will not be computed-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:20,408 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:20,408 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.183, 'learning_rate': 7.500000000000001e-06, 'epoch': 0.21} + 21%|████████████████▌ | 380/1784 [19:16<1:13:45, 3.15s/it]g-point operations will not be computed-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 380/1784 [19:16<1:13:45, 3.15s/it]g-point operations will not be computed-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:26,593 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:26,593 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.9576, 'learning_rate': 7.540000000000001e-06, 'epoch': 0.21} + 21%|████████████████▋ | 382/1784 [19:22<1:13:45, 3.16s/it]g-point operations will not be computed-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▋ | 382/1784 [19:22<1:13:45, 3.16s/it]g-point operations will not be computed-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:32,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:32,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:06,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2602, 'learning_rate': 7.58e-06, 'epoch': 0.21} + 22%|████████████████▊ | 384/1784 [19:28<1:11:25, 3.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:56:37,258 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▊ | 384/1784 [19:28<1:11:25, 3.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:56:37,258 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▊ | 385/1784 [19:31<1:09:56, 3.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:56:37,258 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▊ | 385/1784 [19:31<1:09:56, 3.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:56:37,258 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:41,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:37,258 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:41,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:37,258 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3552, 'learning_rate': 7.640000000000001e-06, 'epoch': 0.22} +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:41,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:37,258 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▉ | 387/1784 [19:37<1:07:54, 2.92s/it]g-point operations will not be computed-28 09:56:37,258 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▉ | 387/1784 [19:37<1:07:54, 2.92s/it]g-point operations will not be computed-28 09:56:37,258 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:46,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:37,258 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:49,603 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:37,258 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:49,603 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:37,258 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.385, 'learning_rate': 7.7e-06, 'epoch': 0.22} + 22%|█████████████████ | 390/1784 [19:45<1:02:50, 2.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████ | 390/1784 [19:45<1:02:50, 2.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████ | 391/1784 [19:47<1:00:32, 2.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████ | 391/1784 [19:47<1:00:32, 2.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:56,772 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:56,772 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:58,883 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:56:58,883 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:00,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:00,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:02,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:02,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:05,664 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:05,664 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3002, 'learning_rate': 7.840000000000001e-06, 'epoch': 0.22} +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:08,103 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:08,103 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7235, 'learning_rate': 7.88e-06, 'epoch': 0.22} +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:09,779 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:09,779 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9442, 'learning_rate': 7.92e-06, 'epoch': 0.22} +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:13,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:13,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3973, 'learning_rate': 7.94e-06, 'epoch': 0.22} +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:17,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:17,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0756, 'learning_rate': 7.960000000000002e-06, 'epoch': 0.23} + 23%|█████████████████▌ | 403/1784 [20:14<1:09:08, 3.00s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▌ | 403/1784 [20:14<1:09:08, 3.00s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1005, 'learning_rate': 7.980000000000002e-06, 'epoch': 0.23} + 23%|█████████████████▋ | 404/1784 [20:17<1:13:21, 3.19s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▋ | 404/1784 [20:17<1:13:21, 3.19s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:28,379 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:28,379 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0213, 'learning_rate': 8.020000000000001e-06, 'epoch': 0.23} + 23%|█████████████████▊ | 406/1784 [20:25<1:18:37, 3.42s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▊ | 406/1784 [20:25<1:18:37, 3.42s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2101, 'learning_rate': 8.040000000000001e-06, 'epoch': 0.23} + 23%|█████████████████▊ | 407/1784 [20:28<1:19:24, 3.46s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▊ | 407/1784 [20:28<1:19:24, 3.46s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1213, 'learning_rate': 8.06e-06, 'epoch': 0.23} + 23%|█████████████████▊ | 408/1784 [20:32<1:19:51, 3.48s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▊ | 408/1784 [20:32<1:19:51, 3.48s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:42,652 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:42,652 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3338, 'learning_rate': 8.1e-06, 'epoch': 0.23} + 23%|█████████████████▉ | 410/1784 [20:39<1:20:10, 3.50s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▉ | 410/1784 [20:39<1:20:10, 3.50s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2651, 'learning_rate': 8.120000000000002e-06, 'epoch': 0.23} + 23%|█████████████████▉ | 411/1784 [20:42<1:19:56, 3.49s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▉ | 411/1784 [20:42<1:19:56, 3.49s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:53,128 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:57:53,128 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2575, 'learning_rate': 8.16e-06, 'epoch': 0.23} + 23%|██████████████████ | 413/1784 [20:49<1:19:51, 3.49s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████ | 413/1784 [20:49<1:19:51, 3.49s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2992, 'learning_rate': 8.18e-06, 'epoch': 0.23} + 23%|██████████████████ | 414/1784 [20:53<1:19:18, 3.47s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████ | 414/1784 [20:53<1:19:18, 3.47s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.258, 'learning_rate': 8.2e-06, 'epoch': 0.23} + 23%|██████████████████▏ | 415/1784 [20:56<1:19:15, 3.47s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▏ | 415/1784 [20:56<1:19:15, 3.47s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:58:06,922 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:58:06,922 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1584, 'learning_rate': 8.24e-06, 'epoch': 0.23} + 23%|██████████████████▏ | 417/1784 [21:03<1:18:33, 3.45s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▏ | 417/1784 [21:03<1:18:33, 3.45s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2493, 'learning_rate': 8.26e-06, 'epoch': 0.23} + 23%|██████████████████▎ | 418/1784 [21:06<1:18:34, 3.45s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▎ | 418/1784 [21:06<1:18:34, 3.45s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:58:17,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:58:17,163 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2966, 'learning_rate': 8.3e-06, 'epoch': 0.23} + 24%|██████████████████▎ | 420/1784 [21:13<1:17:33, 3.41s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▎ | 420/1784 [21:13<1:17:33, 3.41s/it]g-point operations will not be computed-28 09:56:53,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2481, 'learning_rate': 8.32e-06, 'epoch': 0.24} + 24%|██████████████████▍ | 421/1784 [21:17<1:17:15, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:58:25,619 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▍ | 421/1784 [21:17<1:17:15, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:58:25,619 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▍ | 422/1784 [21:20<1:16:19, 3.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:58:25,619 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▍ | 422/1784 [21:20<1:16:19, 3.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:58:25,619 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4645, 'learning_rate': 8.36e-06, 'epoch': 0.24} + 24%|██████████████████▍ | 423/1784 [21:23<1:15:34, 3.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:58:25,619 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▍ | 423/1784 [21:23<1:15:34, 3.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:58:25,619 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0371, 'learning_rate': 8.380000000000001e-06, 'epoch': 0.24} + 24%|██████████████████▍ | 423/1784 [21:23<1:15:34, 3.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:58:25,619 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▌ | 424/1784 [21:26<1:14:47, 3.30s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:58:35,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▌ | 425/1784 [21:30<1:14:04, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:58:35,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▌ | 425/1784 [21:30<1:14:04, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:58:35,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:58:40,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:58:35,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:58:40,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:58:35,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.275, 'learning_rate': 8.44e-06, 'epoch': 0.24} + 24%|██████████████████▋ | 427/1784 [21:36<1:13:05, 3.23s/it]g-point operations will not be computed-28 09:58:35,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▋ | 427/1784 [21:36<1:13:05, 3.23s/it]g-point operations will not be computed-28 09:58:35,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.06, 'learning_rate': 8.46e-06, 'epoch': 0.24} + 24%|██████████████████▋ | 428/1784 [21:39<1:12:41, 3.22s/it]g-point operations will not be computed-28 09:58:35,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▋ | 428/1784 [21:39<1:12:41, 3.22s/it]g-point operations will not be computed-28 09:58:35,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:58:49,550 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:58:35,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:58:49,550 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:58:35,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2012, 'learning_rate': 8.5e-06, 'epoch': 0.24} + 24%|██████████████████▊ | 430/1784 [21:45<1:11:08, 3.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:58:54,260 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▊ | 430/1784 [21:45<1:11:08, 3.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:58:54,260 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▊ | 431/1784 [21:48<1:10:43, 3.14s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:58:54,260 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▊ | 431/1784 [21:48<1:10:43, 3.14s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:58:54,260 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1564, 'learning_rate': 8.540000000000001e-06, 'epoch': 0.24} + 24%|██████████████████▉ | 432/1784 [21:51<1:09:42, 3.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:00,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▉ | 432/1784 [21:51<1:09:42, 3.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:00,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▉ | 433/1784 [21:54<1:08:23, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:00,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▉ | 433/1784 [21:54<1:08:23, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:00,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2468, 'learning_rate': 8.580000000000001e-06, 'epoch': 0.24} +[WARNING|modeling_utils.py:388] 2022-02-28 09:59:04,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:59:00,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:59:04,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:59:00,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:59:04,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:59:00,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████ | 435/1784 [22:00<1:06:32, 2.96s/it]g-point operations will not be computed-28 09:59:00,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████ | 435/1784 [22:00<1:06:32, 2.96s/it]g-point operations will not be computed-28 09:59:00,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:59:10,185 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:59:00,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:59:10,185 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:59:00,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:59:10,185 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:59:00,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████ | 437/1784 [22:06<1:04:03, 2.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:14,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████ | 437/1784 [22:06<1:04:03, 2.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:14,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▏ | 438/1784 [22:08<1:03:25, 2.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:14,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▏ | 438/1784 [22:08<1:03:25, 2.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:14,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:59:18,353 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:59:14,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:59:18,353 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:59:14,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:59:20,923 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:59:14,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:59:20,923 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:59:14,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 09:59:20,923 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 09:59:14,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▊ | 441/1784 [22:16<58:51, 2.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:24,531 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▊ | 441/1784 [22:16<58:51, 2.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:24,531 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▊ | 442/1784 [22:18<55:55, 2.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:26,652 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▊ | 442/1784 [22:18<55:55, 2.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:26,652 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▊ | 443/1784 [22:20<52:40, 2.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:28,582 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▊ | 443/1784 [22:20<52:40, 2.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:28,582 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▉ | 444/1784 [22:22<49:29, 2.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:30,441 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▉ | 444/1784 [22:22<49:29, 2.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:30,441 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████ | 446/1784 [22:26<43:38, 1.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:32,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████ | 446/1784 [22:26<43:38, 1.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:32,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9054, 'learning_rate': 8.84e-06, 'epoch': 0.25} + 25%|████████████████████ | 447/1784 [22:27<40:16, 1.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:35,100 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████ | 447/1784 [22:27<40:16, 1.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:35,100 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▏ | 449/1784 [22:30<34:17, 1.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:36,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▏ | 449/1784 [22:30<34:17, 1.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:36,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4318, 'learning_rate': 8.900000000000001e-06, 'epoch': 0.25} + 25%|████████████████████▏ | 450/1784 [22:31<35:35, 1.60s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:37,630 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▏ | 450/1784 [22:31<35:35, 1.60s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:40,772 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▏ | 450/1784 [22:31<35:35, 1.60s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:40,772 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▏ | 451/1784 [22:35<51:14, 2.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:40,772 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▏ | 451/1784 [22:35<51:14, 2.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:44,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▏ | 451/1784 [22:35<51:14, 2.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:44,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▊ | 452/1784 [22:39<1:01:16, 2.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:44,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████��███▊ | 452/1784 [22:39<1:01:16, 2.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:44,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▊ | 452/1784 [22:39<1:01:16, 2.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:44,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▊ | 453/1784 [22:43<1:07:37, 3.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:44,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▊ | 453/1784 [22:43<1:07:37, 3.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:44,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▊ | 453/1784 [22:43<1:07:37, 3.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:44,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▊ | 454/1784 [22:47<1:12:17, 3.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:44,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▊ | 454/1784 [22:47<1:12:17, 3.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:44,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▊ | 454/1784 [22:47<1:12:17, 3.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:44,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|███████████████████▉ | 455/1784 [22:50<1:14:58, 3.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:59,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|███████████████████▉ | 456/1784 [22:54<1:16:48, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:59,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|███████████████████▉ | 456/1784 [22:54<1:16:48, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:59,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.164, 'learning_rate': 9.040000000000002e-06, 'epoch': 0.26} + 26%|███████████████████▉ | 456/1784 [22:54<1:16:48, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:59,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|███████████████████▉ | 457/1784 [22:58<1:17:54, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:59,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|███████████████████▉ | 457/1784 [22:58<1:17:54, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:59,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|███████████████████▉ | 457/1784 [22:58<1:17:54, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:59,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 458/1784 [23:01<1:18:35, 3.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:59,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 458/1784 [23:01<1:18:35, 3.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:59,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 458/1784 [23:01<1:18:35, 3.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 09:59:59,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 459/1784 [23:05<1:18:39, 3.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 460/1784 [23:08<1:18:55, 3.58s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 460/1784 [23:08<1:18:55, 3.58s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.161, 'learning_rate': 9.12e-06, 'epoch': 0.26} + 26%|████████████████████ | 460/1784 [23:08<1:18:55, 3.58s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▏ | 461/1784 [23:12<1:18:48, 3.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▏ | 461/1784 [23:12<1:18:48, 3.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▏ | 461/1784 [23:12<1:18:48, 3.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▏ | 462/1784 [23:16<1:18:23, 3.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:00:26,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:00:26,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1192, 'learning_rate': 9.180000000000002e-06, 'epoch': 0.26} +[WARNING|modeling_utils.py:388] 2022-02-28 10:00:26,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▎ | 464/1784 [23:23<1:17:38, 3.53s/it]g-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▎ | 464/1784 [23:23<1:17:38, 3.53s/it]g-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▎ | 464/1784 [23:23<1:17:38, 3.53s/it]g-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▎ | 465/1784 [23:26<1:16:54, 3.50s/it]g-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:00:36,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:00:36,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2841, 'learning_rate': 9.240000000000001e-06, 'epoch': 0.26} + 26%|████████████████████▍ | 467/1784 [23:33<1:15:59, 3.46s/it]g-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▍ | 467/1784 [23:33<1:15:59, 3.46s/it]g-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1138, 'learning_rate': 9.260000000000001e-06, 'epoch': 0.26} + 26%|████████████████████▍ | 467/1784 [23:33<1:15:59, 3.46s/it]g-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▍ | 468/1784 [23:36<1:15:26, 3.44s/it]g-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▍ | 468/1784 [23:36<1:15:26, 3.44s/it]g-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▍ | 468/1784 [23:36<1:15:26, 3.44s/it]g-point operations will not be computed-28 10:00:13,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▌ | 469/1784 [23:40<1:15:12, 3.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▌ | 469/1784 [23:40<1:15:12, 3.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▌ | 470/1784 [23:43<1:14:36, 3.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▌ | 470/1784 [23:43<1:14:36, 3.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▌ | 470/1784 [23:43<1:14:36, 3.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▌ | 471/1784 [23:46<1:14:29, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:00:57,058 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:00:57,058 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1338, 'learning_rate': 9.360000000000002e-06, 'epoch': 0.26} +[WARNING|modeling_utils.py:388] 2022-02-28 10:00:57,058 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▋ | 473/1784 [23:53<1:13:29, 3.36s/it]g-point operations will not be computed-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▋ | 473/1784 [23:53<1:13:29, 3.36s/it]g-point operations will not be computed-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▋ | 473/1784 [23:53<1:13:29, 3.36s/it]g-point operations will not be computed-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▋ | 474/1784 [23:56<1:13:16, 3.36s/it]g-point operations will not be computed-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:01:06,955 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:01:06,955 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2336, 'learning_rate': 9.42e-06, 'epoch': 0.27} +[WARNING|modeling_utils.py:388] 2022-02-28 10:01:06,955 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▊ | 476/1784 [24:03<1:12:08, 3.31s/it]g-point operations will not be computed-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▊ | 476/1784 [24:03<1:12:08, 3.31s/it]g-point operations will not be computed-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▊ | 476/1784 [24:03<1:12:08, 3.31s/it]g-point operations will not be computed-28 10:00:48,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▊ | 477/1784 [24:06<1:11:13, 3.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:15,044 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▉ | 478/1784 [24:09<1:10:17, 3.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:15,044 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▉ | 478/1784 [24:09<1:10:17, 3.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:15,044 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2287, 'learning_rate': 9.48e-06, 'epoch': 0.27} + 27%|████████████████████▉ | 478/1784 [24:09<1:10:17, 3.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:15,044 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▉ | 479/1784 [24:12<1:09:47, 3.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:21,300 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▉ | 480/1784 [24:15<1:09:12, 3.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:21,300 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▉ | 480/1784 [24:15<1:09:12, 3.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:21,300 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1659, 'learning_rate': 9.52e-06, 'epoch': 0.27} + 27%|████████████████████▉ | 480/1784 [24:15<1:09:12, 3.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:21,300 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████ | 481/1784 [24:19<1:08:31, 3.16s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:27,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████ | 482/1784 [24:22<1:08:22, 3.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:27,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████ | 482/1784 [24:22<1:08:22, 3.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:27,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1384, 'learning_rate': 9.56e-06, 'epoch': 0.27} + 27%|█████████████████████ | 482/1784 [24:22<1:08:22, 3.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:27,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████ | 483/1784 [24:25<1:07:43, 3.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:33,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▏ | 484/1784 [24:28<1:06:50, 3.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:33,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▏ | 484/1784 [24:28<1:06:50, 3.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:33,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0477, 'learning_rate': 9.600000000000001e-06, 'epoch': 0.27} + 27%|█████████████████████▏ | 484/1784 [24:28<1:06:50, 3.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:33,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▏ | 485/1784 [24:31<1:05:54, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:33,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▏ | 485/1784 [24:31<1:05:54, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:33,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:01:40,955 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:33,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:01:40,955 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:33,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:01:40,955 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:33,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▎ | 487/1784 [24:36<1:04:05, 2.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:45,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▎ | 487/1784 [24:36<1:04:05, 2.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:45,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▎ | 488/1784 [24:39<1:02:44, 2.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:45,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▎ | 488/1784 [24:39<1:02:44, 2.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:45,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:01:49,308 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:45,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:01:51,960 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:45,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:01:51,960 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:45,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2926, 'learning_rate': 9.72e-06, 'epoch': 0.27} +[WARNING|modeling_utils.py:388] 2022-02-28 10:01:51,960 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:45,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████ | 491/1784 [24:47<58:42, 2.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:55,786 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████ | 491/1784 [24:47<58:42, 2.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:55,786 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████ | 492/1784 [24:50<56:26, 2.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████ | 492/1784 [24:50<56:26, 2.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████ | 493/1784 [24:52<54:05, 2.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████ | 493/1784 [24:52<54:05, 2.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:02:01,291 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:02:01,291 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:02:03,287 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:02:03,287 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:02:05,095 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:02:05,095 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:02:08,102 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:02:08,102 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6219, 'learning_rate': 9.88e-06, 'epoch': 0.28} +[WARNING|modeling_utils.py:388] 2022-02-28 10:02:09,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-02-28 10:02:09,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2369] 2022-02-28 10:02:11,254 >> Batch size = 8aluation *****e number of tokens of the input, floating-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 0%| | 0/331 [00:00> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▌ | 2/331 [00:02<06:45, 1.23s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▌ | 2/331 [00:02<06:45, 1.23s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▊ | 3/331 [00:04<08:58, 1.64s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|█ | 4/331 [00:06<10:13, 1.88s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▎ | 5/331 [00:09<11:45, 2.16s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▌ | 6/331 [00:12<12:45, 2.35s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▊ | 7/331 [00:14<13:02, 2.41s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|██ | 8/331 [00:17<13:25, 2.49s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 9/331 [00:20<14:00, 2.61s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▍ | 10/331 [00:23<15:00, 2.80s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▋ | 11/331 [00:26<14:39, 2.75s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▉ | 12/331 [00:29<14:33, 2.74s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▏ | 13/331 [00:31<14:17, 2.70s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 14/331 [00:34<14:07, 2.67s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 15/331 [00:37<15:15, 2.90s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 16/331 [00:41<16:05, 3.06s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▏ | 17/331 [00:44<16:11, 3.10s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▍ | 18/331 [00:46<14:57, 2.87s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 19/331 [00:49<14:38, 2.82s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 20/331 [00:51<13:42, 2.64s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████▏ | 21/331 [00:54<14:18, 2.77s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 22/331 [00:58<15:23, 2.99s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 23/331 [01:02<16:47, 3.27s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▉ | 24/331 [01:06<17:46, 3.47s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▏ | 25/331 [01:09<17:06, 3.36s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▍ | 26/331 [01:11<15:57, 3.14s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 27/331 [01:14<15:58, 3.15s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▉ | 28/331 [01:17<15:19, 3.03s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 29/331 [01:20<14:57, 2.97s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▍ | 30/331 [01:23<14:19, 2.85s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▋ | 31/331 [01:25<13:39, 2.73s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▉ | 32/331 [01:28<13:24, 2.69s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████▏ | 33/331 [01:30<13:23, 2.69s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████▍ | 34/331 [01:33<13:23, 2.71s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 35/331 [01:36<13:36, 2.76s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 36/331 [01:39<14:06, 2.87s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|█████████▏ | 37/331 [01:42<14:49, 3.02s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|█████████▍ | 38/331 [01:46<14:57, 3.06s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▋ | 39/331 [01:49<15:01, 3.09s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▉ | 40/331 [01:51<13:56, 2.87s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|██████████▏ | 41/331 [01:54<13:24, 2.77s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|���█████████▍ | 42/331 [01:57<14:18, 2.97s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 42/331 [01:57<14:18, 2.97s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 42/331 [01:57<14:18, 2.97s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▉ | 44/331 [02:04<15:16, 3.19s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 45/331 [02:07<14:22, 3.01s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▍ | 46/331 [02:09<13:21, 2.81s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▋ | 47/331 [02:11<12:34, 2.66s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▉ | 48/331 [02:14<12:55, 2.74s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████▏ | 49/331 [02:17<13:37, 2.90s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████▍ | 50/331 [02:20<13:26, 2.87s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████▋ | 51/331 [02:23<13:49, 2.96s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▉ | 52/331 [02:26<13:12, 2.84s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|█████████████▏ | 53/331 [02:29<13:13, 2.85s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|█████████████▍ | 54/331 [02:31<12:36, 2.73s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▋ | 55/331 [02:35<13:38, 2.96s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▊ | 56/331 [02:38<13:25, 2.93s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|██████████████ | 57/331 [02:40<12:58, 2.84s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▎ | 58/331 [02:43<13:25, 2.95s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▌ | 59/331 [02:46<12:40, 2.80s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▊ | 60/331 [02:49<12:27, 2.76s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|███████████████ | 61/331 [02:52<12:45, 2.84s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▎ | 62/331 [02:54<12:38, 2.82s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▌ | 63/331 [02:58<13:53, 3.11s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▊ | 64/331 [03:01<13:33, 3.05s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████ | 65/331 [03:04<13:16, 2.99s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▎ | 66/331 [03:08<14:23, 3.26s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▌ | 67/331 [03:12<15:05, 3.43s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▊ | 68/331 [03:15<15:11, 3.46s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|█████████████████ | 69/331 [03:18<14:49, 3.40s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|█████████████████▎ | 70/331 [03:22<14:30, 3.34s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|█████████████████▌ | 71/331 [03:25<14:34, 3.36s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▊ | 72/331 [03:28<14:29, 3.36s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|██████████████████ | 73/331 [03:31<14:00, 3.26s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|██████████████████▎ | 74/331 [03:34<13:43, 3.20s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▌ | 75/331 [03:38<13:55, 3.26s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▊ | 76/331 [03:41<13:10, 3.10s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|███████████████████ | 77/331 [03:43<12:47, 3.02s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▎ | 78/331 [03:46<12:11, 2.89s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▌ | 79/331 [03:49<11:48, 2.81s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▊ | 80/331 [03:51<11:40, 2.79s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|████████████████████ | 81/331 [03:55<12:05, 2.90s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▎ | 82/331 [03:57<11:55, 2.87s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▌ | 83/331 [04:01<12:19, 2.98s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▊ | 84/331 [04:04<13:10, 3.20s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|█████████████████████ | 85/331 [04:07<12:19, 3.01s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|█████████████████████▎ | 86/331 [04:10<12:57, 3.17s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|█████████████████████▌ | 87/331 [04:13<12:34, 3.09s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▊ | 88/331 [04:16<12:12, 3.02s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|██████████████████████ | 89/331 [04:18<11:21, 2.82s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|██████████████████████▎ | 90/331 [04:21<10:45, 2.68s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|██████████████████████▌ | 91/331 [04:24<11:12, 2.80s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▊ | 92/331 [04:26<10:28, 2.63s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|███████████████████████ | 93/331 [04:29<10:35, 2.67s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|███████████████████████▎ | 94/331 [04:32<10:53, 2.76s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████▌ | 95/331 [04:35<11:02, 2.81s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████▊ | 96/331 [04:38<11:10, 2.85s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|████████████████████████ | 97/331 [04:40<10:46, 2.76s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|████████████████████████▎ | 98/331 [04:43<11:10, 2.88s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|████████████████████████▌ | 99/331 [04:46<11:07, 2.88s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|████████████████████████▍ | 100/331 [04:49<10:41, 2.78s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▋ | 101/331 [04:52<10:36, 2.77s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▉ | 102/331 [04:55<11:24, 2.99s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|█████████████████████████▏ | 103/331 [04:58<10:52, 2.86s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|█████████████████████████▍ | 104/331 [05:00<10:45, 2.85s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▋ | 105/331 [05:03<10:44, 2.85s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▉ | 106/331 [05:06<10:43, 2.86s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|██████████████████████████▏ | 107/331 [05:09<10:02, 2.69s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▍ | 108/331 [05:11<09:46, 2.63s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▋ | 109/331 [05:14<09:40, 2.61s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▉ | 110/331 [05:17<10:05, 2.74s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▏ | 111/331 [05:19<10:05, 2.75s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▍ | 112/331 [05:22<10:01, 2.75s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▋ | 113/331 [05:24<09:31, 2.62s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▉ | 114/331 [05:27<09:37, 2.66s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▏ | 115/331 [05:30<09:40, 2.69s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▍ | 116/331 [05:33<09:55, 2.77s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▋ | 117/331 [05:36<09:57, 2.79s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▉ | 118/331 [05:38<09:44, 2.74s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|█████████████████████████████ | 119/331 [05:41<09:46, 2.77s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|█████████████████████████████▎ | 120/331 [05:44<09:48, 2.79s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▌ | 121/331 [05:47<10:18, 2.95s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▊ | 122/331 [05:50<10:03, 2.89s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|██████████████████████████████ | 123/331 [05:54<10:39, 3.07s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|██████████████████████████████▎ | 124/331 [05:57<10:31, 3.05s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▌ | 125/331 [06:00<11:05, 3.23s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▊ | 126/331 [06:04<11:09, 3.27s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|███████████████████████████████ | 127/331 [06:07<11:30, 3.38s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▎ | 128/331 [06:11<11:29, 3.39s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▌ | 129/331 [06:14<11:14, 3.34s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▊ | 130/331 [06:17<11:16, 3.37s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████ | 131/331 [06:21<11:28, 3.44s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▎ | 132/331 [06:24<10:56, 3.30s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▌ | 133/331 [06:27<10:15, 3.11s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▊ | 134/331 [06:29<09:53, 3.01s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|█████████████████████████████████ | 135/331 [06:33<10:01, 3.07s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|█████████████████████████████████▎ | 136/331 [06:36<10:14, 3.15s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|█████████████████████████████████▌ | 137/331 [06:40<10:34, 3.27s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|█████████████████████████████████▊ | 138/331 [06:43<10:45, 3.35s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|██████████████████████████████████ | 139/331 [06:45<09:34, 2.99s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|██████████████████████████████████▎ | 140/331 [06:49<10:17, 3.23s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 43%|██████████████████████████████████▌ | 141/331 [06:52<09:48, 3.10s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 43%|██████████████████████████████████▋ | 142/331 [06:55<09:35, 3.05s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 43%|██████████████████████████████████▉ | 143/331 [06:58<09:54, 3.16s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 44%|███████████████████████████████████▏ | 144/331 [07:01<09:28, 3.04s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 44%|███████████████████████████████████▍ | 145/331 [07:04<09:17, 3.00s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 44%|███████████████████████████████████▋ | 146/331 [07:07<09:43, 3.15s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 44%|███████████████████████████████████▉ | 147/331 [07:10<09:23, 3.06s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 45%|████████████████████████████████████▏ | 148/331 [07:13<08:43, 2.86s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 45%|████████████████████████████████████▍ | 149/331 [07:15<08:16, 2.73s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 45%|█████████████���██████████████████████▋ | 150/331 [07:18<08:38, 2.86s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 46%|████████████████████████████████████▉ | 151/331 [07:21<08:34, 2.86s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 46%|█████████████████████████████████████▏ | 152/331 [07:23<08:11, 2.75s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 46%|█████████████████████████████████████▍ | 153/331 [07:26<08:01, 2.70s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 47%|█████████████████████████████████████▋ | 154/331 [07:29<08:21, 2.83s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 47%|█████████████████████████████████████▉ | 155/331 [07:32<08:42, 2.97s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 47%|██████████████████████████████████████▏ | 156/331 [07:36<08:54, 3.05s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 47%|██████████████████████████████████████▍ | 157/331 [07:39<09:13, 3.18s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 48%|██████████████████████████████████████▋ | 158/331 [07:43<09:19, 3.23s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 48%|██████████████████████████████████████▉ | 159/331 [07:46<09:18, 3.25s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 48%|███████████████████████████████████████▏ | 160/331 [07:49<08:45, 3.07s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 49%|███████████████████████████████████████▍ | 161/331 [07:51<08:31, 3.01s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 49%|███████████████████████████████████████▋ | 162/331 [07:55<08:58, 3.18s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 49%|███████████████████████████████████████▉ | 163/331 [07:58<09:10, 3.28s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 50%|████████████████████████████████████████▏ | 164/331 [08:01<08:41, 3.12s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 50%|████████████████████████████████████████▍ | 165/331 [08:04<08:28, 3.06s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 50%|████████████████████████████████████████▌ | 166/331 [08:07<08:10, 2.98s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 50%|████████████████████████████████████████▊ | 167/331 [08:10<08:24, 3.08s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 51%|█████████████████████████████████████████ | 168/331 [08:13<08:02, 2.96s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 51%|█████████████████████████████████████████▎ | 169/331 [08:16<08:08, 3.01s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 51%|█████████████████████████████████████████▌ | 170/331 [08:19<07:42, 2.87s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 52%|█████████████████████████████████████████▊ | 171/331 [08:21<07:40, 2.88s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 52%|██████████████████████████████████████████ | 172/331 [08:24<07:16, 2.74s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 52%|██████████████████████████████████████████▎ | 173/331 [08:27<07:28, 2.84s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 53%|██████████████████████████████████████████▌ | 174/331 [08:30<07:12, 2.76s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 53%|██████████████████████████████████████████▊ | 175/331 [08:33<07:19, 2.82s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 53%|███████████████████████████████████████████ | 176/331 [08:35<07:06, 2.75s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 53%|███████████████████████████████████████████▎ | 177/331 [08:38<07:27, 2.91s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 54%|███████████████████████████████████████████▌ | 178/331 [08:42<07:52, 3.09s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 54%|███████████████████████████████████████████▊ | 179/331 [08:45<08:13, 3.24s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 54%|████████████████████████████████████████████ | 180/331 [08:49<08:07, 3.23s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 55%|████████████████████████████████████████████▎ | 181/331 [08:52<07:59, 3.20s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 55%|████████████████████████████████████████████▌ | 182/331 [08:54<07:24, 2.98s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 55%|████████████████████████████████████████████▊ | 183/331 [08:57<06:51, 2.78s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 56%|█████████████████████████████████████████████ | 184/331 [08:59<06:25, 2.63s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 56%|█████████████████████████████████████████████▎ | 185/331 [09:01<05:59, 2.47s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 56%|█████████████████████████████████████████████▌ | 186/331 [09:04<06:07, 2.53s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 56%|█████████████████████████████████████████████▊ | 187/331 [09:07<06:37, 2.76s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 57%|██████████████████████████████████████████████ | 188/331 [09:10<06:34, 2.76s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 57%|██████████████████████████████████████████████▎ | 189/331 [09:12<06:14, 2.63s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 57%|██████████████████████████████████████████████▍ | 190/331 [09:14<06:02, 2.57s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 58%|██████████████████████████████████████████████▋ | 191/331 [09:17<05:56, 2.55s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 58%|████████████████████��█████████████████████████▉ | 192/331 [09:19<05:48, 2.50s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 58%|███████████████████████████████████████████████▏ | 193/331 [09:23<06:16, 2.73s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 59%|███████████████████████████████████████████████▍ | 194/331 [09:25<05:56, 2.60s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 59%|███████████████████████████████████████████████▋ | 195/331 [09:27<05:48, 2.56s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 59%|███████████████████████████████████████████████▉ | 196/331 [09:30<05:56, 2.64s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 60%|████████████████████████████████████████████████▏ | 197/331 [09:33<06:09, 2.76s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 60%|████████████████████████████████████████████████▍ | 198/331 [09:36<05:53, 2.66s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 60%|████████████████████████████████████████████████▋ | 199/331 [09:39<05:59, 2.73s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 60%|████████████████████████████████████████████████▉ | 200/331 [09:41<05:43, 2.62s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 61%|█████████████████████████████████████████████████▏ | 201/331 [09:43<05:35, 2.58s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 61%|█████████████████████████████████████████████████▍ | 202/331 [09:46<05:42, 2.65s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 61%|█████████████████████████████████████████████████▋ | 203/331 [09:49<05:41, 2.67s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 62%|█████████████████████████████████████████████████▉ | 204/331 [09:52<05:59, 2.83s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 62%|██████████████████████████████████████████████████▏ | 205/331 [09:55<06:03, 2.89s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 62%|██████████████████████████████████████████████████▍ | 206/331 [09:58<06:00, 2.88s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 63%|██████████████████████████████████████████████████▋ | 207/331 [10:01<06:12, 3.00s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 63%|██████████████████████████████████████████████████▉ | 208/331 [10:05<06:18, 3.08s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 63%|███████████████████████████████████████████████████▏ | 209/331 [10:07<05:45, 2.84s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 63%|███████████████████████████████████████████████████▍ | 210/331 [10:09<05:22, 2.67s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 64%|███████████████████████████████████████████████████▋ | 211/331 [10:12<05:25, 2.71s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 64%|███████████████████████████████████████████████████▉ | 212/331 [10:14<05:10, 2.61s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 64%|████████████████████████████████████████████████████ | 213/331 [10:17<05:11, 2.64s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 65%|████████████████████████████████████████████████████▎ | 214/331 [10:19<04:56, 2.54s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 65%|████████████████████████████████████████████████████▌ | 215/331 [10:22<04:42, 2.44s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 65%|████████████████████████████████████████████████████▊ | 216/331 [10:25<05:12, 2.71s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 66%|█████████████████████████████████████████████████████ | 217/331 [10:28<05:11, 2.74s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 66%|█████████████████████████████████████████████████████▎ | 218/331 [10:31<05:25, 2.88s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 66%|█████████████████████████████████████████████████████▌ | 219/331 [10:34<05:17, 2.84s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 66%|█████████████████████████████████████████████████████▊ | 220/331 [10:36<05:02, 2.73s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 67%|██████████████████████████████████████████████████████ | 221/331 [10:39<05:04, 2.77s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 67%|██████████████████████████████████████████████████████▎ | 222/331 [10:41<04:52, 2.69s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 67%|██████████████████████████████████████████████████████▌ | 223/331 [10:44<04:55, 2.74s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 68%|██████████████████████████████████████████████████████▊ | 224/331 [10:47<04:55, 2.76s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 68%|███████████████████████████████████████████████████████ | 225/331 [10:50<04:53, 2.77s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 68%|███████████████████████████████████████████████████████▎ | 226/331 [10:53<05:04, 2.90s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 69%|███████████████████████████████████████████████████████▌ | 227/331 [10:56<04:57, 2.86s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 69%|███████████████████████████████████████████████████████▊ | 228/331 [10:59<04:48, 2.80s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 69%|████████████████████████████████████████████████████████ | 229/331 [11:01<04:43, 2.78s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 69%|████████████████████████████████████████████████████████▎ | 230/331 [11:04<04:36, 2.74s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 70%|████████████████████████████████████████████████████████▌ | 231/331 [11:07<04:44, 2.85s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 70%|████████████████████████████████████████████████████████▊ | 232/331 [11:10<04:37, 2.80s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 70%|█████████████████████████████████████████████████████████ | 233/331 [11:13<04:44, 2.90s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 71%|█████████████████████████████████████████████████████████▎ | 234/331 [11:15<04:27, 2.76s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 71%|█████████████████████████████████████████████████████████▌ | 235/331 [11:18<04:17, 2.68s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 71%|█████████████████████████████████████████████████████████▊ | 236/331 [11:21<04:43, 2.98s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 72%|█████████████████████████████████████████████████████████▉ | 237/331 [11:25<04:55, 3.14s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 72%|██████████████████████████████████████████████████████████▏ | 238/331 [11:28<04:50, 3.12s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 72%|██████████████████████████████████████████████████████████▍ | 239/331 [11:31<04:50, 3.15s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 73%|██████████████████████████████████████████████████████████▋ | 240/331 [11:35<04:51, 3.21s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 73%|██████████████████████████████████████████████████████████▉ | 241/331 [11:38<04:56, 3.29s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 73%|███████████████████████████████████████████████████████████▏ | 242/331 [11:41<04:54, 3.31s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 73%|███████████████████████████████████████████████████████████▍ | 243/331 [11:45<04:53, 3.33s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 74%|███████████████████████████████████████████████████████████▋ | 244/331 [11:48<04:57, 3.43s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 74%|███████████████████████████████████████████████████████████▉ | 245/331 [11:52<04:45, 3.32s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 74%|████████████████████████████████████████████████████████████▏ | 246/331 [11:55<04:56, 3.49s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 75%|████████████████████████████████████████████████████████████▍ | 247/331 [11:59<04:44, 3.39s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 75%|████████████████████████████████████████████████████████████▋ | 248/331 [12:01<04:23, 3.18s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 75%|████████████████████████████████████████████████████████████▉ | 249/331 [12:04<04:01, 2.94s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 76%|█████████████████████████████████████████████████████████████▏ | 250/331 [12:06<03:46, 2.79s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 76%|█████████████████████████████████████████████████████████████▍ | 251/331 [12:09<03:46, 2.84s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 76%|█████████████████████████████████████████████████████████████▋ | 252/331 [12:11<03:34, 2.71s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 76%|█████████████████████████████████████████████████████████████▉ | 253/331 [12:15<03:44, 2.87s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 77%|██████████████████████████████████████████████████████████████▏ | 254/331 [12:17<03:37, 2.83s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 77%|██████████████████████████████████████████████████████████████▍ | 255/331 [12:21<03:44, 2.95s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 77%|██████████████████████████████████████████████████████████████▋ | 256/331 [12:23<03:35, 2.88s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 78%|██████████████████████████████████████████████████████████████▉ | 257/331 [12:27<03:41, 2.99s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 78%|███████████████████████████████████████████████████████████████▏ | 258/331 [12:29<03:25, 2.82s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 78%|███████████████████████████████████████████████████████████████▍ | 259/331 [12:32<03:20, 2.78s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 79%|███████████████████████████████████████████████████████████████▋ | 260/331 [12:35<03:23, 2.87s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 79%|███████████████████████████████████████████████████████████████▊ | 261/331 [12:37<03:08, 2.69s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 79%|████████████████████████████████████████████████████████████████ | 262/331 [12:40<03:07, 2.72s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 79%|████████████████████████████████████████████████████████████████▎ | 263/331 [12:43<03:16, 2.88s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 80%|████████████████████████████████████████████████████████████████▌ | 264/331 [12:46<03:06, 2.79s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 80%|████████████████████████████████████████████████████████████████▊ | 265/331 [12:48<03:01, 2.75s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 80%|█████████████████████████████████████████████████████████████████ | 266/331 [12:51<02:54, 2.69s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 81%|█████████████████████████████████████████████████████████████████▎ | 267/331 [12:54<03:04, 2.89s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 81%|█████████████████████████████████████████████████████████████████▌ | 268/331 [12:57<03:02, 2.90s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 81%|█████████████████████████████████████████████████████████████████▊ | 269/331 [13:01<03:10, 3.07s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 82%|██████████████████████████████████████████████████████████████████ | 270/331 [13:04<03:05, 3.04s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 82%|██████████████████████████████████████████████████████████████████▎ | 271/331 [13:07<03:07, 3.13s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 82%|██████████████████████████████████████████████████████████████████▌ | 272/331 [13:10<02:58, 3.03s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 82%|██████████████████████████████████████████████████████████████████▊ | 273/331 [13:13<02:57, 3.05s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 83%|███████████████████████████████████████████████████████████████████ | 274/331 [13:16<03:01, 3.19s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 83%|███████████████████████████████████████████████████████████████████▎ | 275/331 [13:20<03:02, 3.26s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 83%|███████████████████████████████████████████████████████████████████▌ | 276/331 [13:22<02:48, 3.06s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 84%|███████████████████████████████████████████████████████████████████▊ | 277/331 [13:25<02:41, 3.00s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 84%|████████████████████████████████████████████████████████████████████ | 278/331 [13:28<02:37, 2.96s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 84%|████████████████████████████████████████████████████████████████████▎ | 279/331 [13:32<02:45, 3.18s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 85%|████████████████████████████████████████████████████████████████████▌ | 280/331 [13:35<02:38, 3.11s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 85%|████████████████████████████████████████████████████████████████████▊ | 281/331 [13:38<02:41, 3.22s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 85%|██████████████████████████████████████████��██████████████████████████ | 282/331 [13:41<02:38, 3.23s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 85%|█████████████████████████████████████████████████████████████████████▎ | 283/331 [13:45<02:39, 3.32s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 86%|█████████████████████████████████████████████████████████████████████▍ | 284/331 [13:49<02:40, 3.42s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 86%|█████████████████████████████████████████████████████████████████████▋ | 285/331 [13:52<02:39, 3.48s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 86%|█████████████████████████████████████████████████████████████████████▉ | 286/331 [13:56<02:36, 3.47s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 87%|██████████████████████████████████████████████████████████████████████▏ | 287/331 [14:00<02:37, 3.58s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 87%|██████████████████████████████████████████████████████████████████████▍ | 288/331 [14:03<02:33, 3.56s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 87%|██████████████████████████████████████████████████████████████████████▋ | 289/331 [14:06<02:21, 3.36s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 88%|██████████████████████████████████████████████████████████████████████▉ | 290/331 [14:09<02:10, 3.19s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 88%|███████████████████████████████████████████████████████████████████████▏ | 291/331 [14:11<02:00, 3.02s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 88%|███████████████████████████████████████████████████████████████████████▍ | 292/331 [14:14<01:54, 2.94s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 89%|███████████████████████████████████████████████████████████████████████▋ | 293/331 [14:17<01:51, 2.93s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 89%|███████████████████████████████████████████████████████████���███████████▉ | 294/331 [14:20<01:43, 2.80s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 89%|████████████████████████████████████████████████████████████████████████▏ | 295/331 [14:22<01:38, 2.73s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 89%|████████████████████████████████████████████████████████████████████████▍ | 296/331 [14:25<01:32, 2.64s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 90%|████████████████████████████████████████████████████████████████████████▋ | 297/331 [14:28<01:38, 2.91s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 90%|████████████████████████████████████████████████████████████████████████▉ | 298/331 [14:32<01:44, 3.16s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 90%|█████████████████████████████████████████████████████████████████████████▏ | 299/331 [14:35<01:37, 3.04s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 91%|█████████████████████████████████████████████████████████████████████████▍ | 300/331 [14:38<01:33, 3.01s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 91%|█████████████████████████████████████████████████████████████████████████▋ | 301/331 [14:40<01:29, 2.99s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 91%|█████████████████████████████████████████████████████████████████████████▉ | 302/331 [14:43<01:25, 2.94s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 92%|██████████████████████████████████████████████████████████████████████████▏ | 303/331 [14:46<01:19, 2.83s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 92%|██████████████████████████████████████████████████████████████████████████▍ | 304/331 [14:49<01:19, 2.93s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 92%|██████████████████████████████████████████████████████████████████████████▋ | 305/331 [14:52<01:18, 3.03s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 92%|██████████████████████████████████████████████████████████████████████████▉ | 306/331 [14:56<01:20, 3.22s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 93%|███████████████████████████████████████████████████████████████████████████▏ | 307/331 [15:00<01:20, 3.35s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 93%|███████████████████████████████████████████████████████████████████████████▎ | 308/331 [15:04<01:21, 3.55s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 93%|███████████████████████████████████████████████████████████████████████████▌ | 309/331 [15:07<01:18, 3.56s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 94%|███████████████████████████████████████████████████████████████████████████▊ | 310/331 [15:10<01:09, 3.33s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 94%|████████████████████████████████████████████████████████████████████████████ | 311/331 [15:13<01:06, 3.34s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 94%|████████████████████████████████████████████████████████████████████████████▎ | 312/331 [15:16<00:59, 3.13s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 95%|████████████████████████████████████████████████████████████████████████████▌ | 313/331 [15:19<00:55, 3.06s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 95%|████████████████████████████████████████████████████████████████████████████▊ | 314/331 [15:22<00:52, 3.09s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 95%|█████████████████████████████████████████████████████████████████████████████ | 315/331 [15:25<00:50, 3.15s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 95%|█████████████████████████████████████████████████████████████████████████████▎ | 316/331 [15:29<00:47, 3.17s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 96%|█████████████████████████████████████████████████████████████████████████████▌ | 317/331 [15:32<00:46, 3.32s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 96%|█████████████████████████████████████████████████████████████████████████████▊ | 318/331 [15:35<00:41, 3.16s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 96%|██████████████████████████████████████████████████████████████████████████████ | 319/331 [15:38<00:36, 3.03s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 97%|██████████████████████████████████████████████████████████████████████████████▎ | 320/331 [15:41<00:33, 3.08s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 97%|██████████████████████████████████████████████████████████████████████████████▌ | 321/331 [15:44<00:30, 3.00s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 97%|██████████████████████████████████████████████████████████████████████████████▊ | 322/331 [15:47<00:28, 3.15s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 98%|███████████████████████████████████████████████████████████████████████████████ | 323/331 [15:50<00:24, 3.07s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 98%|███████████████████████████████████████████████████████████████████████████████▎ | 324/331 [15:54<00:22, 3.17s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 98%|███████████████████████████████████████████████████████████████████████████████▌ | 325/331 [15:57<00:19, 3.18s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 98%|███████████████████████████████████████████████████████████████████████████████▊ | 326/331 [16:00<00:16, 3.23s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 99%|████████████████████████████████████████████████████████████████████████████████ | 327/331 [16:03<00:12, 3.24s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 99%|████████████████████████████████████████████████████████████████████████████████▎| 328/331 [16:07<00:09, 3.27s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 99%|████████████████████████████████████████████████████████████████████████████████▌| 329/331 [16:10<00:06, 3.21s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +100%|████████████████████████████████████████████████████████████████████████████████▊| 330/331 [16:14<00:03, 3.38s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +100%|█████████████████████████████████████████████████████████████████████████████████| 331/331 [16:15<00:00, 2.95s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +100%|█████████████████████████████████████████████████████████████████████████████████| 331/331 [16:15<00:00, 2.95s/it]g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +02/28/2022 10:18:30 - INFO - datasets.metric - Removing /home/sanchit_huggingface_co/.cache/huggingface/metrics/wer/default/default_experiment-1-0.arrow +[INFO|configuration_utils.py:438] 2022-02-28 10:18:30,523 >> Configuration saved in ./checkpoint-500/config.json g-point operations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|feature_extraction_utils.py:324] 2022-02-28 10:18:35,798 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonerations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|feature_extraction_utils.py:324] 2022-02-28 10:18:35,798 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonerations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|feature_extraction_utils.py:324] 2022-02-28 10:18:35,798 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonerations will not be computed-28 10:01:58,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +02/28/2022 10:18:56 - WARNING - huggingface_hub.repository - Adding files tracked by Git LFS: ['wandb/run-20220228_093705-yn2gmwrw/run-yn2gmwrw.wandb']. This may take a bit of time if the files are large.