diff --git "a/wandb/run-20220228_163348-20lja62k/files/output.log" "b/wandb/run-20220228_163348-20lja62k/files/output.log" new file mode 100644--- /dev/null +++ "b/wandb/run-20220228_163348-20lja62k/files/output.log" @@ -0,0 +1,1697 @@ + + + 0%| | 0/1189 [00:00> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8825, 'learning_rate': 0.0, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-02-28 16:33:55,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 0%| | 1/1189 [00:05<1:54:22, 5.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:33:58,585 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.0739, 'learning_rate': 0.0, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-02-28 16:34:01,084 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 0%|▏ | 2/1189 [00:10<1:46:54, 5.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:03,734 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.0609, 'learning_rate': 2e-08, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-02-28 16:34:06,331 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 0%|▏ | 3/1189 [00:16<1:47:35, 5.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:09,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8813, 'learning_rate': 4e-08, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-02-28 16:34:12,022 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 0%|▎ | 4/1189 [00:21<1:47:57, 5.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:14,666 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6007, 'learning_rate': 6.000000000000001e-08, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-02-28 16:34:17,115 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 0%|▎ | 5/1189 [00:27<1:45:11, 5.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:19,670 >> 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 16:34:22,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▍ | 6/1189 [00:32<1:43:06, 5.23s/it] + + 1%|▍ | 6/1189 [00:32<1:43:06, 5.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:24,743 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.743, 'learning_rate': 1.0000000000000001e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 16:34:27,235 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▍ | 7/1189 [00:37<1:42:06, 5.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:29,825 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7243, 'learning_rate': 1.2000000000000002e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 16:34:32,297 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▌ | 8/1189 [00:42<1:41:15, 5.14s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:34,867 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9582, 'learning_rate': 1.2000000000000002e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 16:34:37,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▌ | 9/1189 [00:47<1:40:02, 5.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:39,776 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8108, 'learning_rate': 1.4e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 16:34:42,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▋ | 10/1189 [00:52<1:38:59, 5.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:44,682 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8627, 'learning_rate': 1.6e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 16:34:47,074 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▋ | 11/1189 [00:56<1:38:00, 4.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:49,518 >> 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 16:34:51,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▊ | 12/1189 [01:01<1:36:38, 4.93s/it] + + 1%|▊ | 12/1189 [01:01<1:36:38, 4.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:54,321 >> 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 16:34:56,720 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▊ | 13/1189 [01:06<1:36:14, 4.91s/it] + + 1%|▊ | 13/1189 [01:06<1:36:14, 4.91s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:59,198 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7932, 'learning_rate': 2.2e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 16:35:01,545 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▉ | 14/1189 [01:11<1:35:38, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:04,005 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6951, 'learning_rate': 2.4000000000000003e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-02-28 16:35:06,380 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▉ | 15/1189 [01:16<1:35:16, 4.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:08,851 >> 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 16:35:11,139 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9232, 'learning_rate': 2.6e-07, 'epoch': 0.01} + 1%|█ | 16/1189 [01:21<1:34:33, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:13,576 >> 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 16:35:15,889 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|█▏ | 17/1189 [01:25<1:33:56, 4.81s/it] + + 1%|█▏ | 17/1189 [01:25<1:33:56, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:18,270 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.0363, 'learning_rate': 3.0000000000000004e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 16:35:20,558 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▏ | 18/1189 [01:30<1:33:02, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:22,951 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7808, 'learning_rate': 3.2e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 16:35:25,244 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▎ | 19/1189 [01:35<1:32:29, 4.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:27,675 >> 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 16:35:29,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▎ | 20/1189 [01:39<1:32:10, 4.73s/it] + + 2%|█▎ | 20/1189 [01:39<1:32:10, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:32,321 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9847, 'learning_rate': 3.6e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 16:35:34,594 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▍ | 21/1189 [01:44<1:31:36, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:36,895 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7493, 'learning_rate': 3.8e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 16:35:39,166 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▍ | 22/1189 [01:49<1:30:44, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:41,465 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9432, 'learning_rate': 4.0000000000000003e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 16:35:43,703 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▌ | 23/1189 [01:53<1:29:55, 4.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:46,042 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.0013, 'learning_rate': 4.2000000000000006e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 16:35:48,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▌ | 24/1189 [01:58<1:29:30, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:50,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7983, 'learning_rate': 4.4e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 16:35:52,803 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▋ | 25/1189 [02:02<1:28:57, 4.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:55,047 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9729, 'learning_rate': 4.6000000000000004e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 16:35:57,249 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▋ | 26/1189 [02:07<1:28:04, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:59,482 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8627, 'learning_rate': 4.800000000000001e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 16:36:01,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▊ | 27/1189 [02:11<1:27:06, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:03,894 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6941, 'learning_rate': 5.000000000000001e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 16:36:06,051 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▊ | 28/1189 [02:15<1:26:31, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:08,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7796, 'learning_rate': 5.2e-07, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-02-28 16:36:10,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▉ | 29/1189 [02:20<1:25:56, 4.45s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:12,625 >> 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 16:36:14,760 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|█▉ | 30/1189 [02:24<1:25:11, 4.41s/it] + + 3%|█▉ | 30/1189 [02:24<1:25:11, 4.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:16,879 >> 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 16:36:18,904 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██ | 31/1189 [02:28<1:23:34, 4.33s/it] + + 3%|██ | 31/1189 [02:28<1:23:34, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:21,041 >> 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 16:36:23,086 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▏ | 32/1189 [02:32<1:22:38, 4.29s/it] + + 3%|██▏ | 32/1189 [02:32<1:22:38, 4.29s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:25,228 >> 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 16:36:27,281 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▏ | 33/1189 [02:37<1:22:03, 4.26s/it] + + 3%|██▏ | 33/1189 [02:37<1:22:03, 4.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:29,409 >> 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 16:36:31,355 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 34/1189 [02:41<1:20:54, 4.20s/it] + + 3%|██▎ | 34/1189 [02:41<1:20:54, 4.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:33,423 >> 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 16:36:35,380 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 35/1189 [02:45<1:19:48, 4.15s/it] + + 3%|██▎ | 35/1189 [02:45<1:19:48, 4.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:37,410 >> 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 16:36:39,330 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▍ | 36/1189 [02:49<1:18:34, 4.09s/it] + + 3%|██▍ | 36/1189 [02:49<1:18:34, 4.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:41,315 >> 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 16:36:43,182 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▍ | 37/1189 [02:53<1:17:10, 4.02s/it] + + 3%|██▍ | 37/1189 [02:53<1:17:10, 4.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:45,136 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.745, 'learning_rate': 7.000000000000001e-07, 'epoch': 0.03} +[WARNING|modeling_utils.py:388] 2022-02-28 16:36:46,965 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 3%|██▌ | 38/1189 [02:56<1:15:44, 3.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:48,879 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.2413, 'learning_rate': 7.2e-07, 'epoch': 0.03} +[WARNING|modeling_utils.py:388] 2022-02-28 16:36:50,658 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 3%|██▌ | 39/1189 [03:00<1:14:12, 3.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:52,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8466, 'learning_rate': 7.4e-07, 'epoch': 0.03} +[WARNING|modeling_utils.py:388] 2022-02-28 16:36:54,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▋ | 40/1189 [03:04<1:12:25, 3.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:56,053 >> 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 16:36:57,710 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▋ | 41/1189 [03:07<1:10:36, 3.69s/it] + + 3%|██▋ | 41/1189 [03:07<1:10:36, 3.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:59,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7698, 'learning_rate': 7.8e-07, 'epoch': 0.04} +[WARNING|modeling_utils.py:388] 2022-02-28 16:37:00,920 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▊ | 42/1189 [03:10<1:07:48, 3.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:02,534 >> 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 16:37:03,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▊ | 43/1189 [03:13<1:04:54, 3.40s/it] + + 4%|██▊ | 43/1189 [03:13<1:04:54, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:05,428 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8656, 'learning_rate': 8.200000000000001e-07, 'epoch': 0.04} +[WARNING|modeling_utils.py:388] 2022-02-28 16:37:06,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▉ | 44/1189 [03:16<1:01:09, 3.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:08,073 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.0811, 'learning_rate': 8.400000000000001e-07, 'epoch': 0.04} +[WARNING|modeling_utils.py:388] 2022-02-28 16:37:09,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███ | 45/1189 [03:19<57:22, 3.01s/it] + 4%|███ | 45/1189 [03:19<57:22, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:10,482 >> 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 16:37:11,543 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▏ | 46/1189 [03:21<53:04, 2.79s/it] + 4%|███▏ | 46/1189 [03:21<53:04, 2.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:12,797 >> 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 16:37:13,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▏ | 47/1189 [03:23<49:35, 2.61s/it] + 4%|███▏ | 47/1189 [03:23<49:35, 2.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:14,698 >> 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 16:37:15,508 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▎ | 48/1189 [03:25<44:50, 2.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:16,337 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.6641, 'learning_rate': 9.200000000000001e-07, 'epoch': 0.04} +[WARNING|modeling_utils.py:388] 2022-02-28 16:37:17,029 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▎ | 49/1189 [03:26<40:01, 2.11s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:17,773 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.6525, 'learning_rate': 9.200000000000001e-07, 'epoch': 0.04} +[WARNING|modeling_utils.py:388] 2022-02-28 16:37:18,961 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 50/1189 [03:28<38:41, 2.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:22,042 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 50/1189 [03:28<38:41, 2.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:22,042 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 51/1189 [03:34<1:00:21, 3.18s/it]g-point operations will not be computed-28 16:37:22,042 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 51/1189 [03:34<1:00:21, 3.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:27,542 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 52/1189 [03:40<1:13:05, 3.86s/it]g-point operations will not be computed-28 16:37:27,542 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 52/1189 [03:40<1:13:05, 3.86s/it]g-point operations will not be computed-28 16:37:27,542 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 52/1189 [03:40<1:13:05, 3.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:32,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 52/1189 [03:40<1:13:05, 3.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:32,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▌ | 53/1189 [03:45<1:21:19, 4.30s/it]g-point operations will not be computed-28 16:37:32,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▌ | 53/1189 [03:45<1:21:19, 4.30s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:38,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▌ | 54/1189 [03:50<1:27:27, 4.62s/it]g-point operations will not be computed-28 16:37:38,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▌ | 54/1189 [03:50<1:27:27, 4.62s/it]g-point operations will not be computed-28 16:37:38,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▌ | 54/1189 [03:50<1:27:27, 4.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:43,747 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 55/1189 [03:56<1:32:20, 4.89s/it]g-point operations will not be computed-28 16:37:43,747 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 55/1189 [03:56<1:32:20, 4.89s/it]g-point operations will not be computed-28 16:37:43,747 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 55/1189 [03:56<1:32:20, 4.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:49,175 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 56/1189 [04:01<1:35:00, 5.03s/it]g-point operations will not be computed-28 16:37:49,175 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 56/1189 [04:01<1:35:00, 5.03s/it]g-point operations will not be computed-28 16:37:49,175 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 56/1189 [04:01<1:35:00, 5.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:54,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 57/1189 [04:06<1:36:18, 5.10s/it]g-point operations will not be computed-28 16:37:54,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 57/1189 [04:06<1:36:18, 5.10s/it]g-point operations will not be computed-28 16:37:54,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 57/1189 [04:06<1:36:18, 5.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:59,696 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 57/1189 [04:06<1:36:18, 5.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:59,696 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 58/1189 [04:12<1:36:25, 5.12s/it]g-point operations will not be computed-28 16:37:59,696 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 58/1189 [04:12<1:36:25, 5.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:04,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 59/1189 [04:17<1:35:56, 5.09s/it]g-point operations will not be computed-28 16:38:04,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 59/1189 [04:17<1:35:56, 5.09s/it]g-point operations will not be computed-28 16:38:04,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 59/1189 [04:17<1:35:56, 5.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:09,796 >> 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 16:38:12,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:38:09,796 >> 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 16:38:12,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:38:09,796 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 60/1189 [04:22<1:35:35, 5.08s/it]g-point operations will not be computed-28 16:38:09,796 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 60/1189 [04:22<1:35:35, 5.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:14,789 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 61/1189 [04:27<1:34:50, 5.04s/it]g-point operations will not be computed-28 16:38:14,789 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 61/1189 [04:27<1:34:50, 5.04s/it]g-point operations will not be computed-28 16:38:14,789 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 61/1189 [04:27<1:34:50, 5.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:19,836 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 62/1189 [04:32<1:34:35, 5.04s/it]g-point operations will not be computed-28 16:38:19,836 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 62/1189 [04:32<1:34:35, 5.04s/it]g-point operations will not be computed-28 16:38:19,836 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 62/1189 [04:32<1:34:35, 5.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:24,925 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▏ | 63/1189 [04:37<1:35:29, 5.09s/it]g-point operations will not be computed-28 16:38:24,925 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▏ | 63/1189 [04:37<1:35:29, 5.09s/it]g-point operations will not be computed-28 16:38:24,925 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▏ | 63/1189 [04:37<1:35:29, 5.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:29,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 64/1189 [04:42<1:34:38, 5.05s/it]g-point operations will not be computed-28 16:38:29,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 64/1189 [04:42<1:34:38, 5.05s/it]g-point operations will not be computed-28 16:38:29,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 64/1189 [04:42<1:34:38, 5.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:34,852 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 64/1189 [04:42<1:34:38, 5.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:34,852 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 65/1189 [04:47<1:33:06, 4.97s/it]g-point operations will not be computed-28 16:38:34,852 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 65/1189 [04:47<1:33:06, 4.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:39,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 66/1189 [04:52<1:32:41, 4.95s/it]g-point operations will not be computed-28 16:38:39,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 66/1189 [04:52<1:32:41, 4.95s/it]g-point operations will not be computed-28 16:38:39,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 66/1189 [04:52<1:32:41, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:44,748 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 66/1189 [04:52<1:32:41, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:44,748 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 67/1189 [04:57<1:33:56, 5.02s/it]g-point operations will not be computed-28 16:38:44,748 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 67/1189 [04:57<1:33:56, 5.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:49,892 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 68/1189 [05:02<1:33:32, 5.01s/it]g-point operations will not be computed-28 16:38:49,892 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 68/1189 [05:02<1:33:32, 5.01s/it]g-point operations will not be computed-28 16:38:49,892 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 68/1189 [05:02<1:33:32, 5.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:54,717 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 69/1189 [05:06<1:32:12, 4.94s/it]g-point operations will not be computed-28 16:38:54,717 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 69/1189 [05:06<1:32:12, 4.94s/it]g-point operations will not be computed-28 16:38:54,717 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 69/1189 [05:06<1:32:12, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:59,434 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 70/1189 [05:11<1:30:22, 4.85s/it]g-point operations will not be computed-28 16:38:59,434 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 70/1189 [05:11<1:30:22, 4.85s/it]g-point operations will not be computed-28 16:38:59,434 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 70/1189 [05:11<1:30:22, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:04,051 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 71/1189 [05:16<1:29:02, 4.78s/it]g-point operations will not be computed-28 16:39:04,051 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 71/1189 [05:16<1:29:02, 4.78s/it]g-point operations will not be computed-28 16:39:04,051 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 71/1189 [05:16<1:29:02, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:08,738 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 72/1189 [05:20<1:28:40, 4.76s/it]g-point operations will not be computed-28 16:39:08,738 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 72/1189 [05:20<1:28:40, 4.76s/it]g-point operations will not be computed-28 16:39:08,738 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 72/1189 [05:20<1:28:40, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:13,355 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 73/1189 [05:25<1:27:37, 4.71s/it]g-point operations will not be computed-28 16:39:13,355 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 73/1189 [05:25<1:27:37, 4.71s/it]g-point operations will not be computed-28 16:39:13,355 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 73/1189 [05:25<1:27:37, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:18,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + g-point operations will not be computed-28 16:39:18,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + g-point operations will not be computed-28 16:39:18,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 74/1189 [05:30<1:27:16, 4.70s/it]g-point operations will not be computed-28 16:39:18,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 74/1189 [05:30<1:27:16, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:22,667 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 74/1189 [05:30<1:27:16, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:22,667 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 75/1189 [05:34<1:26:46, 4.67s/it]g-point operations will not be computed-28 16:39:22,667 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 75/1189 [05:34<1:26:46, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:27,211 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 75/1189 [05:34<1:26:46, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:27,211 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 76/1189 [05:39<1:25:47, 4.62s/it]g-point operations will not be computed-28 16:39:27,211 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 76/1189 [05:39<1:25:47, 4.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:31,739 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 76/1189 [05:39<1:25:47, 4.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:31,739 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 77/1189 [05:43<1:25:05, 4.59s/it]g-point operations will not be computed-28 16:39:31,739 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 77/1189 [05:43<1:25:05, 4.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:36,244 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 78/1189 [05:48<1:24:39, 4.57s/it]g-point operations will not be computed-28 16:39:36,244 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 78/1189 [05:48<1:24:39, 4.57s/it]g-point operations will not be computed-28 16:39:36,244 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 78/1189 [05:48<1:24:39, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:40,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 79/1189 [05:52<1:23:41, 4.52s/it]g-point operations will not be computed-28 16:39:40,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 79/1189 [05:52<1:23:41, 4.52s/it]g-point operations will not be computed-28 16:39:40,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 79/1189 [05:52<1:23:41, 4.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:45,106 >> 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 16:39:47,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:39:45,106 >> 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 16:39:47,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:39:45,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 80/1189 [05:57<1:23:01, 4.49s/it]g-point operations will not be computed-28 16:39:45,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 80/1189 [05:57<1:23:01, 4.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:49,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 80/1189 [05:57<1:23:01, 4.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:49,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 81/1189 [06:01<1:21:56, 4.44s/it]g-point operations will not be computed-28 16:39:49,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 81/1189 [06:01<1:21:56, 4.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:53,798 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 81/1189 [06:01<1:21:56, 4.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:53,798 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 82/1189 [06:05<1:20:54, 4.38s/it]g-point operations will not be computed-28 16:39:53,798 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 83/1189 [06:09<1:19:56, 4.34s/it]g-point operations will not be computed-28 16:39:58,012 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 83/1189 [06:09<1:19:56, 4.34s/it]g-point operations will not be computed-28 16:39:58,012 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 83/1189 [06:09<1:19:56, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:02,174 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 83/1189 [06:09<1:19:56, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:02,174 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 84/1189 [06:14<1:18:24, 4.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:06,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 85/1189 [06:18<1:17:22, 4.21s/it]g-point operations will not be computed-28 16:40:06,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 85/1189 [06:18<1:17:22, 4.21s/it]g-point operations will not be computed-28 16:40:06,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 85/1189 [06:18<1:17:22, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:10,337 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 86/1189 [06:22<1:16:34, 4.17s/it]g-point operations will not be computed-28 16:40:10,337 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 86/1189 [06:22<1:16:34, 4.17s/it]g-point operations will not be computed-28 16:40:10,337 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 86/1189 [06:22<1:16:34, 4.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:14,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 87/1189 [06:26<1:14:51, 4.08s/it]g-point operations will not be computed-28 16:40:14,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 87/1189 [06:26<1:14:51, 4.08s/it]g-point operations will not be computed-28 16:40:14,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 87/1189 [06:26<1:14:51, 4.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:18,139 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 88/1189 [06:29<1:13:01, 3.98s/it]g-point operations will not be computed-28 16:40:18,139 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 88/1189 [06:29<1:13:01, 3.98s/it]g-point operations will not be computed-28 16:40:18,139 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 88/1189 [06:29<1:13:01, 3.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:21,883 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▉ | 89/1189 [06:33<1:12:07, 3.93s/it]g-point operations will not be computed-28 16:40:21,883 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▉ | 89/1189 [06:33<1:12:07, 3.93s/it]g-point operations will not be computed-28 16:40:21,883 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▉ | 89/1189 [06:33<1:12:07, 3.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:25,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▉ | 90/1189 [06:37<1:09:25, 3.79s/it]g-point operations will not be computed-28 16:40:25,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▉ | 90/1189 [06:37<1:09:25, 3.79s/it]g-point operations will not be computed-28 16:40:25,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 91/1189 [06:40<1:06:23, 3.63s/it]g-point operations will not be computed-28 16:40:28,917 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 91/1189 [06:40<1:06:23, 3.63s/it]g-point operations will not be computed-28 16:40:28,917 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 91/1189 [06:40<1:06:23, 3.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:32,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 91/1189 [06:40<1:06:23, 3.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:32,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 92/1189 [06:43<1:03:43, 3.48s/it]g-point operations will not be computed-28 16:40:32,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 92/1189 [06:43<1:03:43, 3.48s/it]g-point operations will not be computed-28 16:40:32,105 >> 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 16:40:36,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:40:35,142 >> 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 16:40:36,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:40:35,142 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▏ | 93/1189 [06:46<1:00:25, 3.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:37,879 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▏ | 93/1189 [06:46<1:00:25, 3.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:37,879 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▍ | 94/1189 [06:49<56:37, 3.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:40,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▍ | 95/1189 [06:51<52:45, 2.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:42,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▍ | 95/1189 [06:51<52:45, 2.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:42,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8917, 'learning_rate': 1.8200000000000002e-06, 'epoch': 0.08} + 8%|██████▌ | 96/1189 [06:53<48:32, 2.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:44,696 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 96/1189 [06:53<48:32, 2.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:44,696 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 97/1189 [06:55<44:44, 2.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:46,677 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 97/1189 [06:55<44:44, 2.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:46,677 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8917, 'learning_rate': 1.8800000000000002e-06, 'epoch': 0.08} + 8%|██████▋ | 99/1189 [06:58<37:15, 2.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:48,340 >> 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 16:40:49,011 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 99/1189 [06:58<37:15, 2.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:48,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 100/1189 [07:00<36:21, 2.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:49,745 >> 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 16:40:50,903 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 100/1189 [07:00<36:21, 2.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:53,820 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 100/1189 [07:00<36:21, 2.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:53,820 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▊ | 101/1189 [07:06<55:41, 3.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:53,820 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▊ | 101/1189 [07:06<55:41, 3.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:59,211 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▊ | 101/1189 [07:06<55:41, 3.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:59,211 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 102/1189 [07:11<1:08:10, 3.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:59,211 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 102/1189 [07:11<1:08:10, 3.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:04,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 102/1189 [07:11<1:08:10, 3.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:04,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 103/1189 [07:17<1:16:28, 4.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:04,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 103/1189 [07:17<1:16:28, 4.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:09,782 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 103/1189 [07:17<1:16:28, 4.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:09,782 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 104/1189 [07:22<1:22:16, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:09,782 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 104/1189 [07:22<1:22:16, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:15,250 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 105/1189 [07:27<1:26:17, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:15,250 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 105/1189 [07:27<1:26:17, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:15,250 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 105/1189 [07:27<1:26:17, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:20,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 105/1189 [07:27<1:26:17, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:20,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 106/1189 [07:32<1:28:24, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:20,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 106/1189 [07:32<1:28:24, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:25,585 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 107/1189 [07:37<1:29:29, 4.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:25,585 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 107/1189 [07:37<1:29:29, 4.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:25,585 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 107/1189 [07:37<1:29:29, 4.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:30,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 107/1189 [07:37<1:29:29, 4.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:30,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 108/1189 [07:43<1:29:59, 4.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:30,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 108/1189 [07:43<1:29:59, 4.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:35,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 109/1189 [07:48<1:30:19, 5.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:35,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 109/1189 [07:48<1:30:19, 5.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:35,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 109/1189 [07:48<1:30:19, 5.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:40,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 109/1189 [07:48<1:30:19, 5.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:40,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 110/1189 [07:53<1:29:40, 4.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:40,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 110/1189 [07:53<1:29:40, 4.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:45,587 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 111/1189 [07:57<1:28:50, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:45,587 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 111/1189 [07:57<1:28:50, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:45,587 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 111/1189 [07:57<1:28:50, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:50,440 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 112/1189 [08:02<1:28:22, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:50,440 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 112/1189 [08:02<1:28:22, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:50,440 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 112/1189 [08:02<1:28:22, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:55,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 112/1189 [08:02<1:28:22, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:55,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▍ | 113/1189 [08:07<1:28:09, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:55,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▍ | 113/1189 [08:07<1:28:09, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:00,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▍ | 114/1189 [08:12<1:28:34, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:00,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▍ | 114/1189 [08:12<1:28:34, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:00,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▍ | 114/1189 [08:12<1:28:34, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:05,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▍ | 114/1189 [08:12<1:28:34, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:05,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 115/1189 [08:17<1:28:40, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:05,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 115/1189 [08:17<1:28:40, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:10,198 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 116/1189 [08:22<1:28:28, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:10,198 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 116/1189 [08:22<1:28:28, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:10,198 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 116/1189 [08:22<1:28:28, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:15,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▋ | 117/1189 [08:27<1:28:14, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:15,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▋ | 117/1189 [08:27<1:28:14, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:15,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▋ | 117/1189 [08:27<1:28:14, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:20,025 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▋ | 117/1189 [08:27<1:28:14, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:20,025 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▋ | 118/1189 [08:32<1:27:26, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:20,025 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▋ | 118/1189 [08:32<1:27:26, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:24,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 119/1189 [08:37<1:27:00, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:24,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 119/1189 [08:37<1:27:00, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:24,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 119/1189 [08:37<1:27:00, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:29,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 119/1189 [08:37<1:27:00, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:29,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 120/1189 [08:41<1:26:13, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:29,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 120/1189 [08:41<1:26:13, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:34,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 120/1189 [08:41<1:26:13, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:34,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▉ | 121/1189 [08:46<1:25:31, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:34,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▉ | 121/1189 [08:46<1:25:31, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:39,038 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 122/1189 [08:51<1:24:36, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:39,038 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 122/1189 [08:51<1:24:36, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:39,038 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 122/1189 [08:51<1:24:36, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:43,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 123/1189 [08:55<1:23:55, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:43,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 123/1189 [08:55<1:23:55, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:43,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 123/1189 [08:55<1:23:55, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:48,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████▏ | 124/1189 [09:00<1:22:50, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:48,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████▏ | 124/1189 [09:00<1:22:50, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:48,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████▏ | 124/1189 [09:00<1:22:50, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:52,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▏ | 125/1189 [09:04<1:22:20, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:52,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▏ | 125/1189 [09:04<1:22:20, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:52,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▏ | 125/1189 [09:04<1:22:20, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:57,442 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 126/1189 [09:09<1:21:42, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:57,442 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 126/1189 [09:09<1:21:42, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:57,442 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 126/1189 [09:09<1:21:42, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:01,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 127/1189 [09:14<1:20:56, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:01,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 127/1189 [09:14<1:20:56, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:01,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 127/1189 [09:14<1:20:56, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:06,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 128/1189 [09:18<1:20:15, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:06,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 128/1189 [09:18<1:20:15, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:06,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 128/1189 [09:18<1:20:15, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:10,852 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 129/1189 [09:22<1:19:43, 4.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:10,852 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 129/1189 [09:22<1:19:43, 4.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:10,852 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 129/1189 [09:22<1:19:43, 4.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:15,275 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▌ | 130/1189 [09:27<1:18:54, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:15,275 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▌ | 130/1189 [09:27<1:18:54, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:15,275 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▌ | 130/1189 [09:27<1:18:54, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:19,636 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▌ | 130/1189 [09:27<1:18:54, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:19,636 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▌ | 131/1189 [09:31<1:18:01, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:19,636 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▌ | 131/1189 [09:31<1:18:01, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:23,897 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 132/1189 [09:35<1:17:18, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:23,897 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 132/1189 [09:35<1:17:18, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:23,897 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 132/1189 [09:35<1:17:18, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:28,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 133/1189 [09:40<1:16:21, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:28,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 133/1189 [09:40<1:16:21, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:28,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 133/1189 [09:40<1:16:21, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:32,327 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 134/1189 [09:44<1:14:46, 4.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:32,327 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 134/1189 [09:44<1:14:46, 4.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:32,327 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 134/1189 [09:44<1:14:46, 4.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:36,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 135/1189 [09:48<1:13:18, 4.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:36,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 135/1189 [09:48<1:13:18, 4.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:36,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 135/1189 [09:48<1:13:18, 4.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:40,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 136/1189 [09:52<1:11:55, 4.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:40,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 136/1189 [09:52<1:11:55, 4.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:40,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 136/1189 [09:52<1:11:55, 4.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:44,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|████████▉ | 137/1189 [09:56<1:10:58, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:44,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|████████▉ | 137/1189 [09:56<1:10:58, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:44,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|████████▉ | 137/1189 [09:56<1:10:58, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:48,125 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████ | 138/1189 [09:59<1:09:48, 3.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:48,125 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████ | 138/1189 [09:59<1:09:48, 3.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:48,125 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████ | 139/1189 [10:03<1:08:49, 3.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:51,887 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████ | 139/1189 [10:03<1:08:49, 3.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:55,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████ | 139/1189 [10:03<1:08:49, 3.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:55,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▏ | 140/1189 [10:07<1:06:39, 3.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:55,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▏ | 140/1189 [10:07<1:06:39, 3.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:55,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▏ | 140/1189 [10:07<1:06:39, 3.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:59,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▏ | 141/1189 [10:10<1:04:00, 3.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:59,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▏ | 141/1189 [10:10<1:04:00, 3.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:59,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▎ | 142/1189 [10:13<1:00:46, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:02,250 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▎ | 142/1189 [10:13<1:00:46, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:02,250 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▎ | 142/1189 [10:13<1:00:46, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:05,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▎ | 142/1189 [10:13<1:00:46, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:05,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▌ | 143/1189 [10:16<57:29, 3.30s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:07,947 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▌ | 143/1189 [10:16<57:29, 3.30s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:07,947 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▋ | 144/1189 [10:19<53:56, 3.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:07,947 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▊ | 145/1189 [10:21<50:10, 2.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:10,478 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▊ | 145/1189 [10:21<50:10, 2.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:10,478 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▊ | 146/1189 [10:23<46:34, 2.68s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:12,774 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▊ | 146/1189 [10:23<46:34, 2.68s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:12,774 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▉ | 147/1189 [10:25<42:47, 2.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:14,855 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▉ | 147/1189 [10:25<42:47, 2.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:14,855 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.444, 'learning_rate': 2.86e-06, 'epoch': 0.12} + 12%|█████████▉ | 148/1189 [10:27<38:52, 2.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:16,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 149/1189 [10:28<34:52, 2.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:19,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 149/1189 [10:28<34:52, 2.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:19,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 150/1189 [10:30<33:53, 1.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:19,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 150/1189 [10:30<33:53, 1.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:19,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 150/1189 [10:30<33:53, 1.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:23,702 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 150/1189 [10:30<33:53, 1.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:23,702 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 151/1189 [10:36<52:40, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:23,702 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 151/1189 [10:36<52:40, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:29,056 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 151/1189 [10:36<52:40, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:29,056 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|█████████▉ | 152/1189 [10:41<1:04:24, 3.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:29,056 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|█████████▉ | 152/1189 [10:41<1:04:24, 3.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:34,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|█████████▉ | 152/1189 [10:41<1:04:24, 3.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:34,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 153/1189 [10:46<1:11:57, 4.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:34,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 153/1189 [10:46<1:11:57, 4.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:39,554 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 153/1189 [10:46<1:11:57, 4.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:39,554 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 154/1189 [10:52<1:17:36, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:39,554 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 154/1189 [10:52<1:17:36, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:44,725 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 154/1189 [10:52<1:17:36, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:44,725 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 155/1189 [10:57<1:20:32, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:44,725 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 155/1189 [10:57<1:20:32, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:49,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 155/1189 [10:57<1:20:32, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:49,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 156/1189 [11:02<1:22:42, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:49,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 156/1189 [11:02<1:22:42, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:54,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 157/1189 [11:07<1:23:28, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:54,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 157/1189 [11:07<1:23:28, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:54,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 157/1189 [11:07<1:23:28, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:59,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 157/1189 [11:07<1:23:28, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:59,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 158/1189 [11:12<1:24:07, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:59,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 158/1189 [11:12<1:24:07, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 158/1189 [11:12<1:24:07, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 159/1189 [11:17<1:25:01, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 159/1189 [11:17<1:25:01, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 159/1189 [11:17<1:25:01, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 160/1189 [11:22<1:24:57, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 160/1189 [11:22<1:24:57, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▌ | 161/1189 [11:27<1:24:45, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▌ | 161/1189 [11:27<1:24:45, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3716, 'learning_rate': 3.1400000000000004e-06, 'epoch': 0.14} + 14%|██████████▌ | 161/1189 [11:27<1:24:45, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▋ | 162/1189 [11:32<1:24:19, 4.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▋ | 162/1189 [11:32<1:24:19, 4.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▋ | 162/1189 [11:32<1:24:19, 4.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▋ | 163/1189 [11:36<1:23:51, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▋ | 163/1189 [11:36<1:23:51, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▊ | 164/1189 [11:41<1:23:31, 4.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▊ | 164/1189 [11:41<1:23:31, 4.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0612, 'learning_rate': 3.2000000000000003e-06, 'epoch': 0.14} + 14%|██████████▊ | 164/1189 [11:41<1:23:31, 4.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▊ | 165/1189 [11:46<1:22:41, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▊ | 165/1189 [11:46<1:22:41, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▊ | 165/1189 [11:46<1:22:41, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▉ | 166/1189 [11:51<1:22:07, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▉ | 166/1189 [11:51<1:22:07, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> 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 16:45:04,893 >> 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 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3229, 'learning_rate': 3.2600000000000006e-06, 'epoch': 0.14} + [WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> 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 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 168/1189 [12:00<1:21:00, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 168/1189 [12:00<1:21:00, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 168/1189 [12:00<1:21:00, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 169/1189 [12:05<1:20:40, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 169/1189 [12:05<1:20:40, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 169/1189 [12:05<1:20:40, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 170/1189 [12:09<1:19:49, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 170/1189 [12:09<1:19:49, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 171/1189 [12:14<1:19:11, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 171/1189 [12:14<1:19:11, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3623, 'learning_rate': 3.3400000000000006e-06, 'epoch': 0.14} + 14%|███████████▏ | 171/1189 [12:14<1:19:11, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▎ | 172/1189 [12:19<1:18:47, 4.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▎ | 172/1189 [12:19<1:18:47, 4.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▎ | 172/1189 [12:19<1:18:47, 4.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▎ | 173/1189 [12:23<1:18:19, 4.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▎ | 173/1189 [12:23<1:18:19, 4.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▎ | 173/1189 [12:23<1:18:19, 4.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▍ | 174/1189 [12:28<1:18:00, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▍ | 174/1189 [12:28<1:18:00, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▍ | 175/1189 [12:32<1:17:03, 4.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▍ | 175/1189 [12:32<1:17:03, 4.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3485, 'learning_rate': 3.4200000000000007e-06, 'epoch': 0.15} + 15%|███████████▍ | 175/1189 [12:32<1:17:03, 4.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▌ | 176/1189 [12:37<1:16:10, 4.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▌ | 176/1189 [12:37<1:16:10, 4.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▌ | 177/1189 [12:41<1:15:31, 4.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▌ | 177/1189 [12:41<1:15:31, 4.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4658, 'learning_rate': 3.46e-06, 'epoch': 0.15} + 15%|███████████▋ | 178/1189 [12:45<1:14:51, 4.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▋ | 178/1189 [12:45<1:14:51, 4.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2413, 'learning_rate': 3.48e-06, 'epoch': 0.15} + 15%|███████████▋ | 179/1189 [12:50<1:14:36, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▋ | 179/1189 [12:50<1:14:36, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2862, 'learning_rate': 3.5e-06, 'epoch': 0.15} + 15%|███████████▊ | 180/1189 [12:54<1:14:03, 4.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▊ | 180/1189 [12:54<1:14:03, 4.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4141, 'learning_rate': 3.52e-06, 'epoch': 0.15} + [WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> 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 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3774, 'learning_rate': 3.54e-06, 'epoch': 0.15} + 15%|███████████▉ | 182/1189 [13:03<1:12:36, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▉ | 182/1189 [13:03<1:12:36, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4269, 'learning_rate': 3.5600000000000002e-06, 'epoch': 0.15} + 15%|████████████ | 183/1189 [13:07<1:11:48, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████ | 183/1189 [13:07<1:11:48, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2487, 'learning_rate': 3.58e-06, 'epoch': 0.15} + 15%|████████████ | 184/1189 [13:11<1:10:41, 4.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████ | 184/1189 [13:11<1:10:41, 4.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3575, 'learning_rate': 3.6000000000000003e-06, 'epoch': 0.15} + 16%|████████████▏ | 185/1189 [13:15<1:09:34, 4.16s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▏ | 185/1189 [13:15<1:09:34, 4.16s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1065, 'learning_rate': 3.62e-06, 'epoch': 0.16} + 16%|████████████▏ | 186/1189 [13:19<1:08:07, 4.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▏ | 186/1189 [13:19<1:08:07, 4.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2595, 'learning_rate': 3.6400000000000003e-06, 'epoch': 0.16} + 16%|████████████▎ | 187/1189 [13:23<1:06:45, 4.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▎ | 187/1189 [13:23<1:06:45, 4.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5998, 'learning_rate': 3.66e-06, 'epoch': 0.16} + 16%|████████████▎ | 188/1189 [13:26<1:04:50, 3.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▎ | 188/1189 [13:26<1:04:50, 3.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3651, 'learning_rate': 3.6800000000000003e-06, 'epoch': 0.16} + 16%|████████████▍ | 189/1189 [13:30<1:02:55, 3.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▍ | 189/1189 [13:30<1:02:55, 3.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> 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 16:47:23,648 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:45:04,893 >> 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 16:47:23,648 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1233, 'learning_rate': 3.7200000000000004e-06, 'epoch': 0.16} + 16%|████████████▊ | 191/1189 [13:36<57:30, 3.46s/it]g-point operations will not be computed-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▊ | 191/1189 [13:36<57:30, 3.46s/it]g-point operations will not be computed-28 16:45:04,893 >> 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 16:47:29,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:45:04,893 >> 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 16:47:29,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.569, 'learning_rate': 3.7600000000000004e-06, 'epoch': 0.16} +[WARNING|modeling_utils.py:388] 2022-02-28 16:47:29,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▉ | 193/1189 [13:42<51:32, 3.11s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:33,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|█████████████ | 194/1189 [13:44<48:13, 2.91s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:35,960 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|█████████████ | 194/1189 [13:44<48:13, 2.91s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:35,960 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|█████████████ | 195/1189 [13:46<45:07, 2.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:38,214 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|█████████████ | 195/1189 [13:46<45:07, 2.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:38,214 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|█████████████▏ | 196/1189 [13:49<42:15, 2.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:40,231 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|█████████████▏ | 196/1189 [13:49<42:15, 2.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:40,231 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 197/1189 [13:50<38:58, 2.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:42,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 197/1189 [13:50<38:58, 2.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:42,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 198/1189 [13:52<35:52, 2.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:43,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 198/1189 [13:52<35:52, 2.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:43,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 200/1189 [13:56<31:42, 1.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:45,050 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 200/1189 [13:56<31:42, 1.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:45,050 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.588, 'learning_rate': 3.900000000000001e-06, 'epoch': 0.17} + 17%|█████████████▍ | 200/1189 [13:56<31:42, 1.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 201/1189 [14:01<49:10, 2.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 201/1189 [14:01<49:10, 2.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3844, 'learning_rate': 3.94e-06, 'epoch': 0.17} + 17%|█████████████▌ | 201/1189 [14:01<49:10, 2.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 202/1189 [14:06<1:00:12, 3.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 202/1189 [14:06<1:00:12, 3.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 203/1189 [14:11<1:06:57, 4.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 203/1189 [14:11<1:06:57, 4.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2721, 'learning_rate': 3.980000000000001e-06, 'epoch': 0.17} + 17%|█████████████▍ | 204/1189 [14:16<1:11:18, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 204/1189 [14:16<1:11:18, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2226, 'learning_rate': 4.000000000000001e-06, 'epoch': 0.17} + 17%|█████████████▍ | 205/1189 [14:21<1:14:23, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 205/1189 [14:21<1:14:23, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1393, 'learning_rate': 4.0200000000000005e-06, 'epoch': 0.17} + 17%|█████████████▌ | 206/1189 [14:26<1:16:18, 4.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 206/1189 [14:26<1:16:18, 4.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2505, 'learning_rate': 4.04e-06, 'epoch': 0.17} + 17%|█████████████▌ | 207/1189 [14:31<1:18:03, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 207/1189 [14:31<1:18:03, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3549, 'learning_rate': 4.060000000000001e-06, 'epoch': 0.17} + 17%|█████████████▋ | 208/1189 [14:36<1:18:55, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▋ | 208/1189 [14:36<1:18:55, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5281, 'learning_rate': 4.08e-06, 'epoch': 0.17} + 17%|█████████████▋ | 208/1189 [14:36<1:18:55, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▋ | 208/1189 [14:36<1:18:55, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4086, 'learning_rate': 4.1e-06, 'epoch': 0.18} + 17%|█████████████▋ | 208/1189 [14:36<1:18:55, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▋ | 208/1189 [14:36<1:18:55, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▊ | 210/1189 [14:46<1:19:22, 4.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▊ | 210/1189 [14:46<1:19:22, 4.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▊ | 211/1189 [14:51<1:19:31, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▊ | 211/1189 [14:51<1:19:31, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2584, 'learning_rate': 4.14e-06, 'epoch': 0.18} + 18%|█████████████▊ | 211/1189 [14:51<1:19:31, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▉ | 212/1189 [14:56<1:19:01, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▉ | 212/1189 [14:56<1:19:01, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▉ | 212/1189 [14:56<1:19:01, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▉ | 213/1189 [15:00<1:18:39, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▉ | 213/1189 [15:00<1:18:39, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▉ | 213/1189 [15:00<1:18:39, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████ | 214/1189 [15:05<1:17:52, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████ | 214/1189 [15:05<1:17:52, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████ | 214/1189 [15:05<1:17:52, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████ | 215/1189 [15:10<1:17:46, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████ | 215/1189 [15:10<1:17:46, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████ | 215/1189 [15:10<1:17:46, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▏ | 216/1189 [15:15<1:17:05, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▏ | 216/1189 [15:15<1:17:05, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▏ | 216/1189 [15:15<1:17:05, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▏ | 217/1189 [15:19<1:16:26, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▏ | 217/1189 [15:19<1:16:26, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▎ | 218/1189 [15:24<1:16:14, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▎ | 218/1189 [15:24<1:16:14, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2388, 'learning_rate': 4.2800000000000005e-06, 'epoch': 0.18} + 18%|██████████████▎ | 218/1189 [15:24<1:16:14, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▎ | 219/1189 [15:29<1:15:53, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▎ | 219/1189 [15:29<1:15:53, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▎ | 219/1189 [15:29<1:15:53, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▍ | 220/1189 [15:33<1:15:18, 4.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▍ | 220/1189 [15:33<1:15:18, 4.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▍ | 221/1189 [15:38<1:14:15, 4.60s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▍ | 221/1189 [15:38<1:14:15, 4.60s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2568, 'learning_rate': 4.34e-06, 'epoch': 0.19} + 19%|██████████████▌ | 222/1189 [15:42<1:13:46, 4.58s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▌ | 222/1189 [15:42<1:13:46, 4.58s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.566, 'learning_rate': 4.360000000000001e-06, 'epoch': 0.19} + 19%|██████████████▋ | 223/1189 [15:47<1:13:11, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▋ | 223/1189 [15:47<1:13:11, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3124, 'learning_rate': 4.38e-06, 'epoch': 0.19} + 19%|██████████████▋ | 223/1189 [15:47<1:13:11, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▋ | 223/1189 [15:47<1:13:11, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3912, 'learning_rate': 4.4e-06, 'epoch': 0.19} + 19%|██████████████▋ | 223/1189 [15:47<1:13:11, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▋ | 223/1189 [15:47<1:13:11, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▊ | 225/1189 [15:55<1:11:37, 4.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▊ | 225/1189 [15:55<1:11:37, 4.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▊ | 226/1189 [16:00<1:11:16, 4.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▊ | 226/1189 [16:00<1:11:16, 4.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.109, 'learning_rate': 4.440000000000001e-06, 'epoch': 0.19} + 19%|██████████████▉ | 227/1189 [16:04<1:10:19, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▉ | 227/1189 [16:04<1:10:19, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2459, 'learning_rate': 4.4600000000000005e-06, 'epoch': 0.19} + 19%|██████████████▉ | 227/1189 [16:04<1:10:19, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▉ | 228/1189 [16:08<1:10:01, 4.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▉ | 228/1189 [16:08<1:10:01, 4.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████ | 229/1189 [16:13<1:09:07, 4.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████ | 229/1189 [16:13<1:09:07, 4.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1719, 'learning_rate': 4.5e-06, 'epoch': 0.19} + 19%|███████████████ | 230/1189 [16:17<1:08:28, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████ | 230/1189 [16:17<1:08:28, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3651, 'learning_rate': 4.520000000000001e-06, 'epoch': 0.19} + 19%|███████████████▏ | 231/1189 [16:21<1:07:51, 4.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▏ | 231/1189 [16:21<1:07:51, 4.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3436, 'learning_rate': 4.540000000000001e-06, 'epoch': 0.19} + 20%|███████████████▏ | 232/1189 [16:25<1:06:59, 4.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▏ | 232/1189 [16:25<1:06:59, 4.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3034, 'learning_rate': 4.56e-06, 'epoch': 0.2} + 20%|███████████████▎ | 233/1189 [16:29<1:06:45, 4.19s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▎ | 233/1189 [16:29<1:06:45, 4.19s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2627, 'learning_rate': 4.58e-06, 'epoch': 0.2} + 20%|███████████████▎ | 234/1189 [16:33<1:05:33, 4.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▎ | 234/1189 [16:33<1:05:33, 4.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2283, 'learning_rate': 4.600000000000001e-06, 'epoch': 0.2} + 20%|███████████████▍ | 235/1189 [16:37<1:04:34, 4.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▍ | 235/1189 [16:37<1:04:34, 4.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2872, 'learning_rate': 4.620000000000001e-06, 'epoch': 0.2} + 20%|███████████████▍ | 236/1189 [16:41<1:03:39, 4.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▍ | 236/1189 [16:41<1:03:39, 4.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4579, 'learning_rate': 4.6400000000000005e-06, 'epoch': 0.2} + 20%|███████████████▌ | 237/1189 [16:45<1:02:45, 3.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 237/1189 [16:45<1:02:45, 3.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1832, 'learning_rate': 4.66e-06, 'epoch': 0.2} + 20%|███████████████▌ | 238/1189 [16:49<1:01:36, 3.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 238/1189 [16:49<1:01:36, 3.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3195, 'learning_rate': 4.680000000000001e-06, 'epoch': 0.2} + 20%|███████████████▌ | 238/1189 [16:49<1:01:36, 3.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▋ | 239/1189 [16:52<1:00:20, 3.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> 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 16:50:46,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:47:48,977 >> 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 16:50:46,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.341, 'learning_rate': 4.7200000000000005e-06, 'epoch': 0.2} + 20%|████████████████▏ | 241/1189 [16:59<57:37, 3.65s/it]g-point operations will not be computed-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▏ | 241/1189 [16:59<57:37, 3.65s/it]g-point operations will not be computed-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4422, 'learning_rate': 4.74e-06, 'epoch': 0.2} + 20%|████████████████▏ | 241/1189 [16:59<57:37, 3.65s/it]g-point operations will not be computed-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▎ | 242/1189 [17:02<55:30, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:50:54,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▎ | 243/1189 [17:06<53:26, 3.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:50:54,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▎ | 243/1189 [17:06<53:26, 3.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:50:54,641 >> 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 16:50:58,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:50:54,641 >> 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 16:50:58,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:50:54,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3036, 'learning_rate': 4.800000000000001e-06, 'epoch': 0.21} +[WARNING|modeling_utils.py:388] 2022-02-28 16:50:58,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:50:54,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▍ | 245/1189 [17:11<47:40, 3.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:02,782 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 246/1189 [17:13<44:14, 2.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:04,974 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 246/1189 [17:13<44:14, 2.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:04,974 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 247/1189 [17:15<40:41, 2.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:06,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 247/1189 [17:15<40:41, 2.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:06,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.818, 'learning_rate': 4.86e-06, 'epoch': 0.21} + 21%|████████████████▋ | 248/1189 [17:17<36:55, 2.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:08,572 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▋ | 248/1189 [17:17<36:55, 2.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:08,572 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▊ | 249/1189 [17:19<33:07, 2.11s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▊ | 249/1189 [17:19<33:07, 2.11s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▊ | 250/1189 [17:21<31:45, 2.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▊ | 250/1189 [17:21<31:45, 2.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▉ | 251/1189 [17:26<47:06, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▉ | 251/1189 [17:26<47:06, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3932, 'learning_rate': 4.94e-06, 'epoch': 0.21} + 21%|████████████████▉ | 251/1189 [17:26<47:06, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▉ | 252/1189 [17:31<57:00, 3.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▉ | 252/1189 [17:31<57:00, 3.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 253/1189 [17:36<1:03:15, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 253/1189 [17:36<1:03:15, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3453, 'learning_rate': 4.980000000000001e-06, 'epoch': 0.21} + 21%|████████████████▌ | 253/1189 [17:36<1:03:15, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 253/1189 [17:36<1:03:15, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.077, 'learning_rate': 5e-06, 'epoch': 0.21} + 21%|████████████████▌ | 253/1189 [17:36<1:03:15, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▋ | 255/1189 [17:46<1:10:28, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▋ | 255/1189 [17:46<1:10:28, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0752, 'learning_rate': 5.02e-06, 'epoch': 0.21} + 21%|████████████████▋ | 255/1189 [17:46<1:10:28, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▋ | 255/1189 [17:46<1:10:28, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2665, 'learning_rate': 5.04e-06, 'epoch': 0.22} + 21%|████████████████▋ | 255/1189 [17:46<1:10:28, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▊ | 257/1189 [17:56<1:13:33, 4.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▊ | 257/1189 [17:56<1:13:33, 4.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0714, 'learning_rate': 5.060000000000001e-06, 'epoch': 0.22} + 22%|████████████████▉ | 258/1189 [18:01<1:13:52, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▉ | 258/1189 [18:01<1:13:52, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5038, 'learning_rate': 5.0800000000000005e-06, 'epoch': 0.22} + 22%|████████████████▉ | 258/1189 [18:01<1:13:52, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▉ | 259/1189 [18:06<1:14:20, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▉ | 259/1189 [18:06<1:14:20, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████ | 260/1189 [18:10<1:14:48, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████ | 260/1189 [18:10<1:14:48, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2644, 'learning_rate': 5.12e-06, 'epoch': 0.22} + 22%|█████████████████ | 261/1189 [18:15<1:14:40, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████ | 261/1189 [18:15<1:14:40, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2386, 'learning_rate': 5.140000000000001e-06, 'epoch': 0.22} + 22%|█████████████████▏ | 262/1189 [18:20<1:14:26, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▏ | 262/1189 [18:20<1:14:26, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2262, 'learning_rate': 5.1600000000000006e-06, 'epoch': 0.22} + 22%|█████████████████▎ | 263/1189 [18:25<1:14:27, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▎ | 263/1189 [18:25<1:14:27, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3571, 'learning_rate': 5.18e-06, 'epoch': 0.22} + 22%|█████████████████▎ | 264/1189 [18:30<1:14:09, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▎ | 264/1189 [18:30<1:14:09, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3429, 'learning_rate': 5.2e-06, 'epoch': 0.22} + 22%|█████████████████▍ | 265/1189 [18:34<1:13:31, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▍ | 265/1189 [18:34<1:13:31, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2446, 'learning_rate': 5.220000000000001e-06, 'epoch': 0.22} + 22%|█████████████████▍ | 266/1189 [18:39<1:12:44, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▍ | 266/1189 [18:39<1:12:44, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3092, 'learning_rate': 5.240000000000001e-06, 'epoch': 0.22} + 22%|█████████████████▌ | 267/1189 [18:44<1:12:18, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▌ | 267/1189 [18:44<1:12:18, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1785, 'learning_rate': 5.2600000000000005e-06, 'epoch': 0.22} + 23%|█████████████████▌ | 268/1189 [18:48<1:12:07, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▌ | 268/1189 [18:48<1:12:07, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2174, 'learning_rate': 5.28e-06, 'epoch': 0.23} + 23%|█████████████████▋ | 269/1189 [18:53<1:11:39, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|███████████���█████▋ | 269/1189 [18:53<1:11:39, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2146, 'learning_rate': 5.300000000000001e-06, 'epoch': 0.23} + 23%|█████████████████▋ | 270/1189 [18:57<1:11:05, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▋ | 270/1189 [18:57<1:11:05, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1565, 'learning_rate': 5.320000000000001e-06, 'epoch': 0.23} + 23%|█████████████████▊ | 271/1189 [19:02<1:10:39, 4.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▊ | 271/1189 [19:02<1:10:39, 4.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4837, 'learning_rate': 5.3400000000000005e-06, 'epoch': 0.23} + 23%|█████████████████▊ | 272/1189 [19:07<1:09:53, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▊ | 272/1189 [19:07<1:09:53, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1145, 'learning_rate': 5.36e-06, 'epoch': 0.23} + 23%|█████████████████▊ | 272/1189 [19:07<1:09:53, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▊ | 272/1189 [19:07<1:09:53, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2404, 'learning_rate': 5.380000000000001e-06, 'epoch': 0.23} + 23%|█████████████████▊ | 272/1189 [19:07<1:09:53, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▉ | 274/1189 [19:15<1:08:25, 4.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▉ | 274/1189 [19:15<1:08:25, 4.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▉ | 274/1189 [19:15<1:08:25, 4.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████ | 275/1189 [19:20<1:08:01, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████ | 275/1189 [19:20<1:08:01, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|███████████████���██ | 275/1189 [19:20<1:08:01, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████ | 276/1189 [19:24<1:07:15, 4.42s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████ | 276/1189 [19:24<1:07:15, 4.42s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████ | 276/1189 [19:24<1:07:15, 4.42s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▏ | 277/1189 [19:28<1:06:44, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▏ | 277/1189 [19:28<1:06:44, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▏ | 277/1189 [19:28<1:06:44, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▏ | 278/1189 [19:33<1:05:43, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▏ | 278/1189 [19:33<1:05:43, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▏ | 278/1189 [19:33<1:05:43, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▎ | 279/1189 [19:37<1:04:56, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▎ | 279/1189 [19:37<1:04:56, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▎ | 279/1189 [19:37<1:04:56, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▎ | 280/1189 [19:41<1:04:17, 4.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▎ | 280/1189 [19:41<1:04:17, 4.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▎ | 280/1189 [19:41<1:04:17, 4.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▍ | 281/1189 [19:45<1:03:42, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▍ | 281/1189 [19:45<1:03:42, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▍ | 281/1189 [19:45<1:03:42, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▍ | 282/1189 [19:49<1:02:40, 4.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▍ | 282/1189 [19:49<1:02:40, 4.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▍ | 282/1189 [19:49<1:02:40, 4.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▌ | 283/1189 [19:53<1:01:47, 4.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▌ | 283/1189 [19:53<1:01:47, 4.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▌ | 283/1189 [19:53<1:01:47, 4.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▋ | 284/1189 [19:57<1:01:06, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▋ | 284/1189 [19:57<1:01:06, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▋ | 284/1189 [19:57<1:01:06, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▏ | 285/1189 [20:01<59:58, 3.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▏ | 285/1189 [20:01<59:58, 3.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▏ | 285/1189 [20:01<59:58, 3.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▏ | 286/1189 [20:05<58:57, 3.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▏ | 286/1189 [20:05<58:57, 3.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▏ | 286/1189 [20:05<58:57, 3.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▎ | 287/1189 [20:08<57:39, 3.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> 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 16:54:02,321 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:51:10,003 >> 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 16:54:02,321 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2194, 'learning_rate': 5.68e-06, 'epoch': 0.24} +[WARNING|modeling_utils.py:388] 2022-02-28 16:54:02,321 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▍ | 289/1189 [20:15<55:08, 3.68s/it]g-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▍ | 289/1189 [20:15<55:08, 3.68s/it]g-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▍ | 289/1189 [20:15<55:08, 3.68s/it]g-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▌ | 290/1189 [20:19<53:43, 3.59s/it]g-point operations will not be computed-28 16:51:10,003 >> 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 16:54:12,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:51:10,003 >> 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 16:54:12,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3521, 'learning_rate': 5.74e-06, 'epoch': 0.24} +[WARNING|modeling_utils.py:388] 2022-02-28 16:54:12,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▋ | 292/1189 [20:25<49:02, 3.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▋ | 292/1189 [20:25<49:02, 3.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▋ | 293/1189 [20:27<45:53, 3.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▋ | 293/1189 [20:27<45:53, 3.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:54:16,583 >> 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 16:54:20,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:54:20,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:54:22,459 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:54:22,459 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:54:24,399 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:54:24,399 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:54:26,152 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:54:26,152 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:54:27,684 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:54:27,684 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:54:30,927 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:54:30,927 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7455, 'learning_rate': 5.92e-06, 'epoch': 0.25} +[WARNING|modeling_utils.py:388] 2022-02-28 16:54:30,927 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:54:30,927 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▎ | 301/1189 [20:46<42:56, 2.90s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▎ | 301/1189 [20:46<42:56, 2.90s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▎ | 301/1189 [20:46<42:56, 2.90s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▎ | 302/1189 [20:51<52:41, 3.56s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▎ | 302/1189 [20:51<52:41, 3.56s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▎ | 302/1189 [20:51<52:41, 3.56s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▍ | 303/1189 [20:56<59:12, 4.01s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▍ | 303/1189 [20:56<59:12, 4.01s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|███████████████████▉ | 304/1189 [21:01<1:03:55, 4.33s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|███████████████████▉ | 304/1189 [21:01<1:03:55, 4.33s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.8708, 'learning_rate': 6e-06, 'epoch': 0.26} + 26%|███████████████████▉ | 304/1189 [21:01<1:03:55, 4.33s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 305/1189 [21:06<1:06:56, 4.54s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 305/1189 [21:06<1:06:56, 4.54s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 305/1189 [21:06<1:06:56, 4.54s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 305/1189 [21:06<1:06:56, 4.54s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0563, 'learning_rate': 6.040000000000001e-06, 'epoch': 0.26} + 26%|████████████████████ | 305/1189 [21:06<1:06:56, 4.54s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▏ | 307/1189 [21:16<1:09:45, 4.75s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▏ | 307/1189 [21:16<1:09:45, 4.75s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▏ | 307/1189 [21:16<1:09:45, 4.75s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▏ | 308/1189 [21:21<1:10:10, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▏ | 308/1189 [21:21<1:10:10, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▎ | 309/1189 [21:26<1:10:20, 4.80s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▎ | 309/1189 [21:26<1:10:20, 4.80s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.9649, 'learning_rate': 6.1e-06, 'epoch': 0.26} + 26%|████████████████████▎ | 309/1189 [21:26<1:10:20, 4.80s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▎ | 310/1189 [21:30<1:10:37, 4.82s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▎ | 310/1189 [21:30<1:10:37, 4.82s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▍ | 311/1189 [21:35<1:10:48, 4.84s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▍ | 311/1189 [21:35<1:10:48, 4.84s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1021, 'learning_rate': 6.1400000000000005e-06, 'epoch': 0.26} + 26%|████████████████████▍ | 312/1189 [21:40<1:10:39, 4.83s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▍ | 312/1189 [21:40<1:10:39, 4.83s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1044, 'learning_rate': 6.16e-06, 'epoch': 0.26} + 26%|████████████████████▍ | 312/1189 [21:40<1:10:39, 4.83s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▌ | 313/1189 [21:45<1:10:12, 4.81s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▌ | 313/1189 [21:45<1:10:12, 4.81s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▌ | 314/1189 [21:50<1:09:49, 4.79s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▌ | 314/1189 [21:50<1:09:49, 4.79s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1376, 'learning_rate': 6.200000000000001e-06, 'epoch': 0.26} + 26%|████████████████████▋ | 315/1189 [21:54<1:09:39, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▋ | 315/1189 [21:54<1:09:39, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0619, 'learning_rate': 6.220000000000001e-06, 'epoch': 0.26} + 26%|████████████████████▋ | 315/1189 [21:54<1:09:39, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▋ | 315/1189 [21:54<1:09:39, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▋ | 316/1189 [21:59<1:09:33, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▋ | 316/1189 [21:59<1:09:33, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▊ | 317/1189 [22:04<1:09:35, 4.79s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▊ | 317/1189 [22:04<1:09:35, 4.79s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3625, 'learning_rate': 6.26e-06, 'epoch': 0.27} + 27%|████████████████████▊ | 318/1189 [22:09<1:09:18, 4.77s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▊ | 318/1189 [22:09<1:09:18, 4.77s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2863, 'learning_rate': 6.280000000000001e-06, 'epoch': 0.27} + 27%|████████████████████▊ | 318/1189 [22:09<1:09:18, 4.77s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▉ | 319/1189 [22:14<1:09:10, 4.77s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▉ | 319/1189 [22:14<1:09:10, 4.77s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▉ | 320/1189 [22:18<1:08:35, 4.74s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▉ | 320/1189 [22:18<1:08:35, 4.74s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2889, 'learning_rate': 6.3200000000000005e-06, 'epoch': 0.27} + 27%|█████████████████████ | 321/1189 [22:23<1:08:09, 4.71s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████ | 321/1189 [22:23<1:08:09, 4.71s/it]g-point operations will not be computed-28 16:54:16,583 >> 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 16:56:18,040 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:56:18,040 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1358, 'learning_rate': 6.360000000000001e-06, 'epoch': 0.27} +[WARNING|modeling_utils.py:388] 2022-02-28 16:56:18,040 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:56:18,040 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▏ | 323/1189 [22:32<1:07:06, 4.65s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▏ | 323/1189 [22:32<1:07:06, 4.65s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▎ | 324/1189 [22:37<1:06:37, 4.62s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▎ | 324/1189 [22:37<1:06:37, 4.62s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2859, 'learning_rate': 6.4000000000000006e-06, 'epoch': 0.27} + 27%|█████████████████████▎ | 325/1189 [22:41<1:05:52, 4.57s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▎ | 325/1189 [22:41<1:05:52, 4.57s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2048, 'learning_rate': 6.42e-06, 'epoch': 0.27} + 27%|█████████████████████▍ | 326/1189 [22:45<1:05:14, 4.54s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▍ | 326/1189 [22:45<1:05:14, 4.54s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3831, 'learning_rate': 6.440000000000001e-06, 'epoch': 0.27} + 28%|██���██████████████████▍ | 327/1189 [22:50<1:04:49, 4.51s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▍ | 327/1189 [22:50<1:04:49, 4.51s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3815, 'learning_rate': 6.460000000000001e-06, 'epoch': 0.27} + 28%|█████████████████████▍ | 327/1189 [22:50<1:04:49, 4.51s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▌ | 328/1189 [22:54<1:04:22, 4.49s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▌ | 328/1189 [22:54<1:04:22, 4.49s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▌ | 329/1189 [22:59<1:03:43, 4.45s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▌ | 329/1189 [22:59<1:03:43, 4.45s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1473, 'learning_rate': 6.5000000000000004e-06, 'epoch': 0.28} + 28%|█████████████████████▋ | 330/1189 [23:03<1:03:00, 4.40s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▋ | 330/1189 [23:03<1:03:00, 4.40s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3793, 'learning_rate': 6.520000000000001e-06, 'epoch': 0.28} + 28%|█████████████████████▋ | 331/1189 [23:07<1:02:21, 4.36s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▋ | 331/1189 [23:07<1:02:21, 4.36s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0783, 'learning_rate': 6.540000000000001e-06, 'epoch': 0.28} + 28%|█████████████████████▊ | 332/1189 [23:11<1:01:41, 4.32s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▊ | 332/1189 [23:11<1:01:41, 4.32s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2146, 'learning_rate': 6.560000000000001e-06, 'epoch': 0.28} + 28%|█████████████████████▊ | 333/1189 [23:16<1:00:53, 4.27s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▊ | 333/1189 [23:16<1:00:53, 4.27s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2755, 'learning_rate': 6.5800000000000005e-06, 'epoch': 0.28} + 28%|█████████████████████▉ | 334/1189 [23:20<1:00:20, 4.23s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▉ | 334/1189 [23:20<1:00:20, 4.23s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0445, 'learning_rate': 6.600000000000001e-06, 'epoch': 0.28} + 28%|██████████████████████▌ | 335/1189 [23:24<59:22, 4.17s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▌ | 335/1189 [23:24<59:22, 4.17s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2928, 'learning_rate': 6.620000000000001e-06, 'epoch': 0.28} + 28%|██████████████████████▌ | 336/1189 [23:28<58:21, 4.11s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▌ | 336/1189 [23:28<58:21, 4.11s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3136, 'learning_rate': 6.640000000000001e-06, 'epoch': 0.28} + 28%|██████████████████████▌ | 336/1189 [23:28<58:21, 4.11s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▋ | 337/1189 [23:32<57:04, 4.02s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▋ | 337/1189 [23:32<57:04, 4.02s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▋ | 337/1189 [23:32<57:04, 4.02s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▋ | 338/1189 [23:35<56:01, 3.95s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▋ | 338/1189 [23:35<56:01, 3.95s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▋ | 338/1189 [23:35<56:01, 3.95s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|██████████████████████▊ | 339/1189 [23:39<54:48, 3.87s/it]g-point operations will not be computed-28 16:54:16,583 >> 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 16:57:33,185 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> 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 16:57:33,185 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2516, 'learning_rate': 6.720000000000001e-06, 'epoch': 0.29} +[WARNING|modeling_utils.py:388] 2022-02-28 16:57:33,185 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|██████████████████████▉ | 341/1189 [23:46<51:27, 3.64s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|██████████████████████▉ | 341/1189 [23:46<51:27, 3.64s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|██████████████████████▉ | 341/1189 [23:46<51:27, 3.64s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████ | 342/1189 [23:49<49:15, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:41,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████ | 342/1189 [23:49<49:15, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:41,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████ | 343/1189 [23:52<46:45, 3.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:41,217 >> 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 16:57:45,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:57:41,217 >> 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 16:57:45,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:57:41,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4456, 'learning_rate': 6.800000000000001e-06, 'epoch': 0.29} +[WARNING|modeling_utils.py:388] 2022-02-28 16:57:45,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:57:41,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████▏ | 345/1189 [23:57<41:20, 2.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:49,000 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████▏ | 345/1189 [23:57<41:20, 2.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:49,000 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████▎ | 346/1189 [23:59<38:31, 2.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:51,103 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████▎ | 346/1189 [23:59<38:31, 2.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:51,103 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████▎ | 347/1189 [24:01<35:12, 2.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:52,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████▎ | 347/1189 [24:01<35:12, 2.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:52,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6718, 'learning_rate': 6.88e-06, 'epoch': 0.29} + 29%|███████████████████████▍ | 349/1189 [24:05<28:30, 2.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:54,584 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████▍ | 349/1189 [24:05<28:30, 2.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:54,584 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████▌ | 350/1189 [24:07<27:31, 1.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:55,940 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████▌ | 350/1189 [24:07<27:31, 1.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████▌ | 350/1189 [24:07<27:31, 1.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▌ | 351/1189 [24:12<41:34, 2.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▌ | 351/1189 [24:12<41:34, 2.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▋ | 352/1189 [24:17<50:34, 3.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▋ | 352/1189 [24:17<50:34, 3.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.157, 'learning_rate': 6.96e-06, 'epoch': 0.3} + 30%|███████████████████████▋ | 352/1189 [24:17<50:34, 3.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▊ | 353/1189 [24:22<56:28, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▊ | 353/1189 [24:22<56:28, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▊ | 353/1189 [24:22<56:28, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▏ | 354/1189 [24:27<1:00:18, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▏ | 354/1189 [24:27<1:00:18, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▎ | 355/1189 [24:32<1:02:48, 4.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▎ | 355/1189 [24:32<1:02:48, 4.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1486, 'learning_rate': 7.0200000000000006e-06, 'epoch': 0.3} + 30%|███████████████████████▎ | 355/1189 [24:32<1:02:48, 4.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▎ | 356/1189 [24:37<1:04:29, 4.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▎ | 356/1189 [24:37<1:04:29, 4.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▍ | 357/1189 [24:42<1:05:24, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▍ | 357/1189 [24:42<1:05:24, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3384, 'learning_rate': 7.06e-06, 'epoch': 0.3} + 30%|███████████████████████▍ | 358/1189 [24:47<1:06:01, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▍ | 358/1189 [24:47<1:06:01, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0699, 'learning_rate': 7.08e-06, 'epoch': 0.3} + 30%|███████████████████████▌ | 359/1189 [24:52<1:06:32, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▌ | 359/1189 [24:52<1:06:32, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.238, 'learning_rate': 7.100000000000001e-06, 'epoch': 0.3} + 30%|███████████████████████▌ | 360/1189 [24:56<1:06:52, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▌ | 360/1189 [24:56<1:06:52, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3706, 'learning_rate': 7.1200000000000004e-06, 'epoch': 0.3} + 30%|███████████████████████▌ | 360/1189 [24:56<1:06:52, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▋ | 361/1189 [25:01<1:06:40, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▋ | 361/1189 [25:01<1:06:40, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▋ | 362/1189 [25:06<1:06:26, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▋ | 362/1189 [25:06<1:06:26, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0899, 'learning_rate': 7.16e-06, 'epoch': 0.3} + 31%|███████████████████████▊ | 363/1189 [25:11<1:06:12, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|███████████████████████▊ | 363/1189 [25:11<1:06:12, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1032, 'learning_rate': 7.180000000000001e-06, 'epoch': 0.31} + 31%|███████████████████████▉ | 364/1189 [25:16<1:06:22, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|███████████████████████▉ | 364/1189 [25:16<1:06:22, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2998, 'learning_rate': 7.2000000000000005e-06, 'epoch': 0.31} + 31%|███████████████████████▉ | 365/1189 [25:20<1:05:49, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|███████████████████████▉ | 365/1189 [25:20<1:05:49, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2338, 'learning_rate': 7.22e-06, 'epoch': 0.31} + 31%|████████████████████████ | 366/1189 [25:25<1:05:35, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████ | 366/1189 [25:25<1:05:35, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1811, 'learning_rate': 7.24e-06, 'epoch': 0.31} + 31%|████████████████████████ | 367/1189 [25:30<1:04:49, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████ | 367/1189 [25:30<1:04:49, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0937, 'learning_rate': 7.260000000000001e-06, 'epoch': 0.31} + 31%|████████████████████████▏ | 368/1189 [25:34<1:04:30, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▏ | 368/1189 [25:34<1:04:30, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5385, 'learning_rate': 7.280000000000001e-06, 'epoch': 0.31} + 31%|████████████████████████▏ | 369/1189 [25:39<1:04:07, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▏ | 369/1189 [25:39<1:04:07, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3573, 'learning_rate': 7.3e-06, 'epoch': 0.31} + 31%|████████████████████████▏ | 369/1189 [25:39<1:04:07, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▎ | 370/1189 [25:44<1:03:43, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▎ | 370/1189 [25:44<1:03:43, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▎ | 370/1189 [25:44<1:03:43, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▎ | 371/1189 [25:48<1:03:13, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▎ | 371/1189 [25:48<1:03:13, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▎ | 371/1189 [25:48<1:03:13, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0908, 'learning_rate': 7.360000000000001e-06, 'epoch': 0.31} + 31%|████████████████████████▎ | 371/1189 [25:48<1:03:13, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▎ | 371/1189 [25:48<1:03:13, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▍ | 373/1189 [25:57<1:02:09, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▍ | 373/1189 [25:57<1:02:09, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▍ | 373/1189 [25:57<1:02:09, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▌ | 374/1189 [26:02<1:01:30, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▌ | 374/1189 [26:02<1:01:30, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▌ | 374/1189 [26:02<1:01:30, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|████████████████████████▌ | 375/1189 [26:06<1:01:00, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|████████████████████████▌ | 375/1189 [26:06<1:01:00, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|████████████████████████▋ | 376/1189 [26:11<1:00:30, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|████████████████████████▋ | 376/1189 [26:11<1:00:30, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2195, 'learning_rate': 7.440000000000001e-06, 'epoch': 0.32} + 32%|█████████████████████████▎ | 377/1189 [26:15<59:59, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▎ | 377/1189 [26:15<59:59, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1713, 'learning_rate': 7.4600000000000006e-06, 'epoch': 0.32} + 32%|█████████████████████████▍ | 378/1189 [26:19<59:30, 4.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▍ | 378/1189 [26:19<59:30, 4.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1561, 'learning_rate': 7.48e-06, 'epoch': 0.32} + 32%|█████████████████████████▌ | 379/1189 [26:24<59:01, 4.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▌ | 379/1189 [26:24<59:01, 4.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1195, 'learning_rate': 7.500000000000001e-06, 'epoch': 0.32} + 32%|█████████████████████████▌ | 380/1189 [26:28<58:32, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▌ | 380/1189 [26:28<58:32, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> 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 17:00:22,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> 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 17:00:22,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0967, 'learning_rate': 7.540000000000001e-06, 'epoch': 0.32} + 32%|█████████████████████████▋ | 382/1189 [26:36<57:39, 4.29s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▋ | 382/1189 [26:36<57:39, 4.29s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2816, 'learning_rate': 7.5600000000000005e-06, 'epoch': 0.32} + 32%|█████████████████████████▊ | 383/1189 [26:40<56:12, 4.18s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▊ | 383/1189 [26:40<56:12, 4.18s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0563, 'learning_rate': 7.58e-06, 'epoch': 0.32} + 32%|█████████████████████████▊ | 384/1189 [26:44<54:56, 4.10s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▊ | 384/1189 [26:44<54:56, 4.10s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3362, 'learning_rate': 7.600000000000001e-06, 'epoch': 0.32} + 32%|█████████████████████████▉ | 385/1189 [26:48<53:51, 4.02s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▉ | 385/1189 [26:48<53:51, 4.02s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3688, 'learning_rate': 7.620000000000001e-06, 'epoch': 0.32} + 32%|█████████████████████████▉ | 386/1189 [26:52<53:06, 3.97s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▉ | 386/1189 [26:52<53:06, 3.97s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1055, 'learning_rate': 7.640000000000001e-06, 'epoch': 0.32} + 33%|██████████████████████████ | 387/1189 [26:56<52:08, 3.90s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████ | 387/1189 [26:56<52:08, 3.90s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3171, 'learning_rate': 7.660000000000001e-06, 'epoch': 0.33} + 33%|██████████████████████████ | 388/1189 [26:59<51:05, 3.83s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████ | 388/1189 [26:59<51:05, 3.83s/it]g-point operations will not be computed-28 16:59:41,150 >> 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 17:00:53,336 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> 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 17:00:53,336 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4034, 'learning_rate': 7.7e-06, 'epoch': 0.33} + 33%|██████████████████████████▏ | 390/1189 [27:06<48:24, 3.63s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▏ | 390/1189 [27:06<48:24, 3.63s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3698, 'learning_rate': 7.72e-06, 'epoch': 0.33} + 33%|██████████████████████████▏ | 390/1189 [27:06<48:24, 3.63s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▎ | 391/1189 [27:09<46:20, 3.48s/it]g-point operations will not be computed-28 16:59:41,150 >> 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 17:01:02,818 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> 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 17:01:02,818 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> 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 17:01:05,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> 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 17:01:05,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1896, 'learning_rate': 7.78e-06, 'epoch': 0.33} + 33%|██████████████████████████▌ | 394/1189 [27:18<39:45, 3.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▌ | 394/1189 [27:18<39:45, 3.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▌ | 395/1189 [27:20<37:18, 2.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▌ | 395/1189 [27:20<37:18, 2.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:01:09,504 >> 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 17:01:12,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> 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 17:01:12,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> 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 17:01:14,501 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> 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 17:01:14,501 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3534, 'learning_rate': 7.860000000000001e-06, 'epoch': 0.33} +[WARNING|modeling_utils.py:388] 2022-02-28 17:01:17,513 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> 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 17:01:17,513 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> 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 17:01:19,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> 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 17:01:19,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6628, 'learning_rate': 7.92e-06, 'epoch': 0.34} +[WARNING|modeling_utils.py:388] 2022-02-28 17:01:24,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> 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 17:01:24,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0486, 'learning_rate': 7.94e-06, 'epoch': 0.34} + 34%|███████████████████████████ | 402/1189 [27:39<47:09, 3.60s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████ | 402/1189 [27:39<47:09, 3.60s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1799, 'learning_rate': 7.960000000000002e-06, 'epoch': 0.34} + 34%|███████████████████████████ | 403/1189 [27:44<53:08, 4.06s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████ | 403/1189 [27:44<53:08, 4.06s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1841, 'learning_rate': 7.980000000000002e-06, 'epoch': 0.34} + 34%|███████████████████████████▏ | 404/1189 [27:49<56:51, 4.35s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▏ | 404/1189 [27:49<56:51, 4.35s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2834, 'learning_rate': 8.000000000000001e-06, 'epoch': 0.34} + 34%|███████████████████████████▏ | 405/1189 [27:54<59:41, 4.57s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▏ | 405/1189 [27:54<59:41, 4.57s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1536, 'learning_rate': 8.020000000000001e-06, 'epoch': 0.34} + 34%|███████████████████████████▏ | 405/1189 [27:54<59:41, 4.57s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▋ | 406/1189 [28:00<1:01:33, 4.72s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▋ | 406/1189 [28:00<1:01:33, 4.72s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▋ | 406/1189 [28:00<1:01:33, 4.72s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▋ | 407/1189 [28:05<1:02:43, 4.81s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▋ | 407/1189 [28:05<1:02:43, 4.81s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▋ | 407/1189 [28:05<1:02:43, 4.81s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▊ | 408/1189 [28:10<1:03:21, 4.87s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▊ | 408/1189 [28:10<1:03:21, 4.87s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▊ | 408/1189 [28:10<1:03:21, 4.87s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▊ | 408/1189 [28:10<1:03:21, 4.87s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1054, 'learning_rate': 8.1e-06, 'epoch': 0.34} + 34%|██████████████████████████▊ | 408/1189 [28:10<1:03:21, 4.87s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▊ | 408/1189 [28:10<1:03:21, 4.87s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▉ | 410/1189 [28:19<1:03:22, 4.88s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▉ | 410/1189 [28:19<1:03:22, 4.88s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▉ | 410/1189 [28:19<1:03:22, 4.88s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|██████████████████████████▉ | 411/1189 [28:24<1:03:20, 4.88s/it]g-point operations will not be computed-28 17:01:09,504 >> 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 17:02:19,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> 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 17:02:19,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2693, 'learning_rate': 8.16e-06, 'epoch': 0.35} +[WARNING|modeling_utils.py:388] 2022-02-28 17:02:19,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> 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 17:02:19,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████ | 413/1189 [28:34<1:02:12, 4.81s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████ | 413/1189 [28:34<1:02:12, 4.81s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████ | 413/1189 [28:34<1:02:12, 4.81s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▏ | 414/1189 [28:38<1:01:33, 4.77s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▏ | 414/1189 [28:38<1:01:33, 4.77s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▏ | 415/1189 [28:43<1:01:30, 4.77s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▏ | 415/1189 [28:43<1:01:30, 4.77s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1823, 'learning_rate': 8.220000000000001e-06, 'epoch': 0.35} + 35%|███████████████████████████▏ | 415/1189 [28:43<1:01:30, 4.77s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▎ | 416/1189 [28:48<1:01:12, 4.75s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▎ | 416/1189 [28:48<1:01:12, 4.75s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▎ | 416/1189 [28:48<1:01:12, 4.75s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▎ | 417/1189 [28:53<1:00:47, 4.73s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▎ | 417/1189 [28:53<1:00:47, 4.73s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▍ | 418/1189 [28:57<1:00:15, 4.69s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▍ | 418/1189 [28:57<1:00:15, 4.69s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0802, 'learning_rate': 8.28e-06, 'epoch': 0.35} + 35%|████████████████████████████▏ | 419/1189 [29:02<59:53, 4.67s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▏ | 419/1189 [29:02<59:53, 4.67s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2756, 'learning_rate': 8.3e-06, 'epoch': 0.35} + 35%|████████████████████████████▏ | 419/1189 [29:02<59:53, 4.67s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▎ | 420/1189 [29:06<59:13, 4.62s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▎ | 420/1189 [29:06<59:13, 4.62s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▎ | 420/1189 [29:06<59:13, 4.62s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▎ | 421/1189 [29:11<58:52, 4.60s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▎ | 421/1189 [29:11<58:52, 4.60s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▍ | 422/1189 [29:15<58:48, 4.60s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▍ | 422/1189 [29:15<58:48, 4.60s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2496, 'learning_rate': 8.36e-06, 'epoch': 0.35} + 36%|████████████████████████████▍ | 423/1189 [29:20<58:20, 4.57s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▍ | 423/1189 [29:20<58:20, 4.57s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2382, 'learning_rate': 8.380000000000001e-06, 'epoch': 0.36} + 36%|████████████████████████████▍ | 423/1189 [29:20<58:20, 4.57s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▌ | 424/1189 [29:24<57:36, 4.52s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▌ | 424/1189 [29:24<57:36, 4.52s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▌ | 424/1189 [29:24<57:36, 4.52s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▌ | 425/1189 [29:29<56:49, 4.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:21,475 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▌ | 425/1189 [29:29<56:49, 4.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:21,475 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▌ | 425/1189 [29:29<56:49, 4.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:21,475 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2347, 'learning_rate': 8.44e-06, 'epoch': 0.36} + 36%|████████████████████████████▌ | 425/1189 [29:29<56:49, 4.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:21,475 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▌ | 425/1189 [29:29<56:49, 4.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:21,475 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▋ | 427/1189 [29:37<56:01, 4.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:30,202 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▋ | 427/1189 [29:37<56:01, 4.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:30,202 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▋ | 427/1189 [29:37<56:01, 4.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:30,202 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1574, 'learning_rate': 8.48e-06, 'epoch': 0.36} + 36%|████████████████████████████▋ | 427/1189 [29:37<56:01, 4.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:30,202 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▋ | 427/1189 [29:37<56:01, 4.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:30,202 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▊ | 429/1189 [29:46<55:09, 4.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> 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 17:03:38,815 >> 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 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3594, 'learning_rate': 8.52e-06, 'epoch': 0.36} + 36%|████████████████████████████▉ | 431/1189 [29:55<54:23, 4.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▉ | 431/1189 [29:55<54:23, 4.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2223, 'learning_rate': 8.540000000000001e-06, 'epoch': 0.36} + 36%|█████████████████████████████ | 432/1189 [29:59<53:44, 4.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|█████████████████████████████ | 432/1189 [29:59<53:44, 4.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1815, 'learning_rate': 8.560000000000001e-06, 'epoch': 0.36} + 36%|█████████████████████████████▏ | 433/1189 [30:03<53:06, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|█████████████████████████████▏ | 433/1189 [30:03<53:06, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2792, 'learning_rate': 8.580000000000001e-06, 'epoch': 0.36} + 37%|█████████████████████████████▏ | 434/1189 [30:07<52:10, 4.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▏ | 434/1189 [30:07<52:10, 4.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1954, 'learning_rate': 8.6e-06, 'epoch': 0.36} + 37%|█████████████████████████████▎ | 435/1189 [30:11<51:14, 4.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▎ | 435/1189 [30:11<51:14, 4.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4341, 'learning_rate': 8.62e-06, 'epoch': 0.37} + 37%|█████████████████████████████▎ | 436/1189 [30:14<50:13, 4.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▎ | 436/1189 [30:14<50:13, 4.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1195, 'learning_rate': 8.64e-06, 'epoch': 0.37} + 37%|█████████████████████████████▍ | 437/1189 [30:18<49:16, 3.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▍ | 437/1189 [30:18<49:16, 3.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1726, 'learning_rate': 8.66e-06, 'epoch': 0.37} + 37%|█████████████████████████████▍ | 438/1189 [30:22<48:02, 3.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▍ | 438/1189 [30:22<48:02, 3.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> 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 17:04:15,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:03:38,815 >> 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 17:04:15,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3113, 'learning_rate': 8.700000000000001e-06, 'epoch': 0.37} + 37%|█████████████████████████████▌ | 440/1189 [30:29<45:10, 3.62s/it]g-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|██████████████████████��██████▌ | 440/1189 [30:29<45:10, 3.62s/it]g-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2111, 'learning_rate': 8.720000000000001e-06, 'epoch': 0.37} + 37%|█████████████████████████████▋ | 441/1189 [30:32<43:26, 3.48s/it]g-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▋ | 441/1189 [30:32<43:26, 3.48s/it]g-point operations will not be computed-28 17:03:38,815 >> 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 17:04:25,510 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:03:38,815 >> 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 17:04:25,510 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2824, 'learning_rate': 8.76e-06, 'epoch': 0.37} +[WARNING|modeling_utils.py:388] 2022-02-28 17:04:25,510 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▊ | 443/1189 [30:38<39:49, 3.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▊ | 444/1189 [30:40<37:37, 3.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▊ | 444/1189 [30:40<37:37, 3.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:04:29,793 >> 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 17:04:33,364 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> 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 17:04:33,364 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> 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 17:04:35,488 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> 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 17:04:35,488 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> 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 17:04:37,400 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> 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 17:04:37,400 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> 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 17:04:39,088 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> 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 17:04:39,088 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4837, 'learning_rate': 8.880000000000001e-06, 'epoch': 0.38} +[WARNING|modeling_utils.py:388] 2022-02-28 17:04:42,362 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> 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 17:04:42,362 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.591, 'learning_rate': 8.920000000000001e-06, 'epoch': 0.38} +[WARNING|modeling_utils.py:388] 2022-02-28 17:04:42,362 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▎ | 451/1189 [30:57<36:32, 2.97s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▎ | 451/1189 [30:57<36:32, 2.97s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1316, 'learning_rate': 8.94e-06, 'epoch': 0.38} + 38%|██████████████████████████████▎ | 451/1189 [30:57<36:32, 2.97s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▍ | 452/1189 [31:02<44:18, 3.61s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▍ | 452/1189 [31:02<44:18, 3.61s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▍ | 453/1189 [31:07<49:27, 4.03s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▍ | 453/1189 [31:07<49:27, 4.03s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1289, 'learning_rate': 8.98e-06, 'epoch': 0.38} + 38%|██████████████████████████████▍ | 453/1189 [31:07<49:27, 4.03s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▌ | 454/1189 [31:12<52:52, 4.32s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▌ | 454/1189 [31:12<52:52, 4.32s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▌ | 455/1189 [31:17<54:57, 4.49s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▌ | 455/1189 [31:17<54:57, 4.49s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0944, 'learning_rate': 9.020000000000002e-06, 'epoch': 0.38} + 38%|██████████████████████████████▋ | 456/1189 [31:22<56:34, 4.63s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▋ | 456/1189 [31:22<56:34, 4.63s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1625, 'learning_rate': 9.040000000000002e-06, 'epoch': 0.38} + 38%|██████████████████████████████▋ | 456/1189 [31:22<56:34, 4.63s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▋ | 457/1189 [31:27<57:17, 4.70s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▋ | 457/1189 [31:27<57:17, 4.70s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▋ | 457/1189 [31:27<57:17, 4.70s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|██████████████████████████████▊ | 458/1189 [31:32<57:46, 4.74s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|██████████████████████████████▊ | 458/1189 [31:32<57:46, 4.74s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|██████████████████████████████▉ | 459/1189 [31:37<58:09, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|██████████████████████████████▉ | 459/1189 [31:37<58:09, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0962, 'learning_rate': 9.100000000000001e-06, 'epoch': 0.39} + 39%|██████████████████████████████▉ | 459/1189 [31:37<58:09, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|██████████████████████████████▉ | 460/1189 [31:41<58:08, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|██████████████████████████████▉ | 460/1189 [31:41<58:08, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|██████████████████████████████▉ | 460/1189 [31:41<58:08, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████ | 461/1189 [31:46<57:57, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████ | 461/1189 [31:46<57:57, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████ | 462/1189 [31:51<57:54, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████ | 462/1189 [31:51<57:54, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2095, 'learning_rate': 9.16e-06, 'epoch': 0.39} + 39%|███████████████████████████████ | 462/1189 [31:51<57:54, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▏ | 463/1189 [31:56<58:05, 4.80s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▏ | 463/1189 [31:56<58:05, 4.80s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▏ | 463/1189 [31:56<58:05, 4.80s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▏ | 464/1189 [32:01<57:50, 4.79s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▏ | 464/1189 [32:01<57:50, 4.79s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▎ | 465/1189 [32:05<57:39, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▎ | 465/1189 [32:05<57:39, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2855, 'learning_rate': 9.220000000000002e-06, 'epoch': 0.39} + 39%|███████████████████████████████▎ | 465/1189 [32:05<57:39, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▎ | 465/1189 [32:05<57:39, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|██████████████████████████��████▎ | 466/1189 [32:10<57:20, 4.76s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▎ | 466/1189 [32:10<57:20, 4.76s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▎ | 466/1189 [32:10<57:20, 4.76s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▍ | 467/1189 [32:15<56:49, 4.72s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▍ | 467/1189 [32:15<56:49, 4.72s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▍ | 468/1189 [32:19<56:22, 4.69s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▍ | 468/1189 [32:19<56:22, 4.69s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2952, 'learning_rate': 9.280000000000001e-06, 'epoch': 0.39} + 39%|███████████████████████████████▌ | 469/1189 [32:24<56:09, 4.68s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▌ | 469/1189 [32:24<56:09, 4.68s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0674, 'learning_rate': 9.3e-06, 'epoch': 0.39} + 39%|███████████████████████████████▌ | 469/1189 [32:24<56:09, 4.68s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▌ | 470/1189 [32:29<55:43, 4.65s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▌ | 470/1189 [32:29<55:43, 4.65s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▌ | 470/1189 [32:29<55:43, 4.65s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▋ | 471/1189 [32:33<55:21, 4.63s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▋ | 471/1189 [32:33<55:21, 4.63s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▋ | 471/1189 [32:33<55:21, 4.63s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▊ | 472/1189 [32:38<54:52, 4.59s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▊ | 472/1189 [32:38<54:52, 4.59s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▊ | 472/1189 [32:38<54:52, 4.59s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▊ | 473/1189 [32:42<54:29, 4.57s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▊ | 473/1189 [32:42<54:29, 4.57s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▉ | 474/1189 [32:47<54:08, 4.54s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▉ | 474/1189 [32:47<54:08, 4.54s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3065, 'learning_rate': 9.4e-06, 'epoch': 0.4} + 40%|███████████████████████████████▉ | 475/1189 [32:51<53:29, 4.49s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▉ | 475/1189 [32:51<53:29, 4.49s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3725, 'learning_rate': 9.42e-06, 'epoch': 0.4} + 40%|████████████████████████████████ | 476/1189 [32:55<52:59, 4.46s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████ | 476/1189 [32:55<52:59, 4.46s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2321, 'learning_rate': 9.440000000000001e-06, 'epoch': 0.4} + 40%|████████████████████████████████ | 477/1189 [33:00<52:23, 4.42s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████ | 477/1189 [33:00<52:23, 4.42s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0517, 'learning_rate': 9.460000000000001e-06, 'epoch': 0.4} + 40%|████████████████████████████████▏ | 478/1189 [33:04<51:45, 4.37s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▏ | 478/1189 [33:04<51:45, 4.37s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1719, 'learning_rate': 9.48e-06, 'epoch': 0.4} + 40%|████████████████████████████████▏ | 479/1189 [33:08<51:21, 4.34s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▏ | 479/1189 [33:08<51:21, 4.34s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2294, 'learning_rate': 9.5e-06, 'epoch': 0.4} + g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2519, 'learning_rate': 9.52e-06, 'epoch': 0.4} + 40%|████████████████████████████████▎ | 481/1189 [33:17<50:14, 4.26s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▎ | 481/1189 [33:17<50:14, 4.26s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1538, 'learning_rate': 9.54e-06, 'epoch': 0.4} + 41%|████████████████████████████████▍ | 482/1189 [33:21<49:57, 4.24s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▍ | 482/1189 [33:21<49:57, 4.24s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2508, 'learning_rate': 9.56e-06, 'epoch': 0.41} + 41%|████████████████████████████████▍ | 483/1189 [33:25<49:27, 4.20s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▍ | 483/1189 [33:25<49:27, 4.20s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2302, 'learning_rate': 9.58e-06, 'epoch': 0.41} + 41%|████████████████████████████████▌ | 484/1189 [33:29<48:29, 4.13s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▌ | 484/1189 [33:29<48:29, 4.13s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2961, 'learning_rate': 9.600000000000001e-06, 'epoch': 0.41} + 41%|████████████████████████████████▋ | 485/1189 [33:33<47:41, 4.06s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▋ | 485/1189 [33:33<47:41, 4.06s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2522, 'learning_rate': 9.620000000000001e-06, 'epoch': 0.41} + 41%|████████████████████████████████▋ | 485/1189 [33:33<47:41, 4.06s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▋ | 486/1189 [33:37<47:07, 4.02s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▋ | 486/1189 [33:37<47:07, 4.02s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▊ | 487/1189 [33:41<46:20, 3.96s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▊ | 487/1189 [33:41<46:20, 3.96s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0833, 'learning_rate': 9.66e-06, 'epoch': 0.41} + 41%|████████████████████████████████▊ | 487/1189 [33:41<46:20, 3.96s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▊ | 488/1189 [33:44<45:27, 3.89s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▊ | 488/1189 [33:44<45:27, 3.89s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▉ | 489/1189 [33:48<44:20, 3.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▉ | 489/1189 [33:48<44:20, 3.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▉ | 490/1189 [33:51<43:12, 3.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▉ | 490/1189 [33:51<43:12, 3.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2419, 'learning_rate': 9.72e-06, 'epoch': 0.41} + 41%|█████████████████████████████████ | 491/1189 [33:55<41:51, 3.60s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|█████████████████████████████████ | 491/1189 [33:55<41:51, 3.60s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:40,310 >> 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 17:07:48,484 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:07:40,310 >> 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 17:07:48,484 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1422, 'learning_rate': 9.760000000000001e-06, 'epoch': 0.41} +[WARNING|modeling_utils.py:388] 2022-02-28 17:07:48,484 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|█████████████████████████████████▏ | 493/1189 [34:01<38:31, 3.32s/it]g-point operations will not be computed-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|█████████████████████████████████▏ | 493/1189 [34:01<38:31, 3.32s/it]g-point operations will not be computed-28 17:07:40,310 >> 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 17:07:54,193 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:07:40,310 >> 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 17:07:56,639 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:07:40,310 >> 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 17:07:56,639 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5124, 'learning_rate': 9.820000000000001e-06, 'epoch': 0.42} +[WARNING|modeling_utils.py:388] 2022-02-28 17:07:56,639 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|█████████████████████████████████▎ | 496/1189 [34:08<31:26, 2.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:59,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|█████████████████████████████████▎ | 496/1189 [34:08<31:26, 2.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:59,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3506, 'learning_rate': 9.86e-06, 'epoch': 0.42} + 42%|█████████████████████████████████▌ | 498/1189 [34:12<25:44, 2.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:08:01,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|█████████████████████████████████▌ | 498/1189 [34:12<25:44, 2.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:08:01,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|█████████████████████████████████▌ | 499/1189 [34:13<23:07, 2.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:08:04,636 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|█████████████████████████████████▌ | 499/1189 [34:13<23:07, 2.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:08:04,636 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2366] 2022-02-28 17:08:05,927 >> Num examples = 2642 | 500/1189 [34:15<22:25, 1.95s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[INFO|trainer.py:2366] 2022-02-28 17:08:05,927 >> Num examples = 2642 | 500/1189 [34:15<22:25, 1.95s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[INFO|trainer.py:2366] 2022-02-28 17:08:05,927 >> Num examples = 2642 | 500/1189 [34:15<22:25, 1.95s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[INFO|trainer.py:2366] 2022-02-28 17:08:05,927 >> Num examples = 2642 | 500/1189 [34:15<22:25, 1.95s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 2%|█▌ | 4/221 [00:08<08:58, 2.48s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 2%|█▉ | 5/221 [00:11<09:42, 2.70s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 3%|██▎ | 6/221 [00:15<10:21, 2.89s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 3%|██▋ | 7/221 [00:19<11:19, 3.17s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 4%|███ | 8/221 [00:22<11:06, 3.13s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 4%|███▍ | 9/221 [00:25<10:58, 3.11s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 5%|███▋ | 10/221 [00:29<11:50, 3.37s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 5%|████ | 11/221 [00:33<12:46, 3.65s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 5%|████▍ | 12/221 [00:36<12:00, 3.45s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 6%|████▊ | 13/221 [00:39<11:36, 3.35s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 6%|█████▏ | 14/221 [00:42<11:38, 3.37s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 7%|█████▌ | 15/221 [00:47<13:03, 3.81s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 7%|█████▉ | 16/221 [00:52<13:57, 4.09s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 8%|██████▎ | 17/221 [00:55<13:18, 3.92s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 8%|██████▋ | 18/221 [00:59<13:07, 3.88s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 9%|███████ | 19/221 [01:03<12:25, 3.69s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 9%|███████▍ | 20/221 [01:06<11:50, 3.53s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 10%|███████▊ | 21/221 [01:09<11:08, 3.34s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 10%|████████▏ | 22/221 [01:12<10:55, 3.29s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 10%|████████▌ | 23/221 [01:15<10:43, 3.25s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 11%|████████▉ | 24/221 [01:19<11:15, 3.43s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 11%|█████████▎ | 25/221 [01:23<11:46, 3.61s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 12%|█████████▋ | 26/221 [01:27<11:59, 3.69s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 12%|██████████ | 27/221 [01:29<10:59, 3.40s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 13%|██████████▍ | 28/221 [01:33<11:30, 3.58s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 13%|██████████▊ | 29/221 [01:38<12:12, 3.81s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 14%|███████████▏ | 30/221 [01:41<11:21, 3.57s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 14%|███████████▌ | 31/221 [01:43<10:20, 3.27s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 14%|███████████▊ | 32/221 [01:47<10:16, 3.26s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 15%|████████████▏ | 33/221 [01:50<10:40, 3.41s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 15%|████████████▌ | 34/221 [01:54<10:46, 3.46s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 16%|████████████▉ | 35/221 [01:57<10:21, 3.34s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 16%|█████████████▎ | 36/221 [02:00<10:15, 3.33s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 17%|█████████████▋ | 37/221 [02:05<11:08, 3.63s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 17%|██████████████ | 38/221 [02:08<10:32, 3.45s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 18%|██████████████▍ | 39/221 [02:11<10:46, 3.55s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 18%|██████████████▊ | 40/221 [02:14<10:13, 3.39s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 19%|███████████████▏ | 41/221 [02:18<10:24, 3.47s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 19%|███████████████▌ | 42/221 [02:23<11:17, 3.79s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 19%|███████████████▉ | 43/221 [02:26<10:49, 3.65s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 20%|████████████████▎ | 44/221 [02:31<11:50, 4.01s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 20%|████████████████▋ | 45/221 [02:35<12:21, 4.21s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 21%|█████████████████ | 46/221 [02:40<12:12, 4.19s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 21%|█████████████████▍ | 47/221 [02:44<11:56, 4.12s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 22%|█████████████████▊ | 48/221 [02:48<11:51, 4.11s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 22%|██████████████████▏ | 49/221 [02:51<11:23, 3.97s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 23%|██████████████████▌ | 50/221 [02:55<11:21, 3.99s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 23%|██████████████████▉ | 51/221 [02:59<10:39, 3.76s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 24%|███████████████████▎ | 52/221 [03:02<09:57, 3.54s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 24%|███████████████████▋ | 53/221 [03:05<09:24, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 24%|████████████████████ | 54/221 [03:08<09:40, 3.47s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 25%|████████████████████▍ | 55/221 [03:12<09:42, 3.51s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 25%|████████████████████▊ | 56/221 [03:16<10:28, 3.81s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 26%|█████████████████████▏ | 57/221 [03:20<10:31, 3.85s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 26%|█████████████████████▌ | 58/221 [03:24<10:06, 3.72s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 27%|█████████████████████▉ | 59/221 [03:27<09:32, 3.54s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 27%|██████████████████████▎ | 60/221 [03:29<08:47, 3.27s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 28%|██████████████████████▋ | 61/221 [03:33<09:00, 3.38s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 28%|███████████████████████ | 62/221 [03:36<08:50, 3.34s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 29%|███████████████████████▍ | 63/221 [03:40<08:56, 3.40s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 29%|███████████████████████▋ | 64/221 [03:43<08:50, 3.38s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 29%|████████████████████████ | 65/221 [03:47<08:44, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 30%|████████████████████████▍ | 66/221 [03:50<08:49, 3.42s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 30%|████████████████████████▊ | 67/221 [03:53<08:16, 3.22s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 31%|█████████████████████████▏ | 68/221 [03:57<08:56, 3.50s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 31%|█████████████████████████▌ | 69/221 [04:00<08:32, 3.37s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 32%|█████████████████████████▉ | 70/221 [04:03<08:24, 3.34s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 32%|██████████████████████████▎ | 71/221 [04:07<08:13, 3.29s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 33%|██████████████████████████▋ | 72/221 [04:09<07:48, 3.15s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 33%|███████████████████████████ | 73/221 [04:13<08:05, 3.28s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 33%|███████████████████████████▍ | 74/221 [04:16<08:02, 3.29s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 34%|███████████████████████████▊ | 75/221 [04:19<07:58, 3.27s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 34%|████████████████████████████▏ | 76/221 [04:23<07:52, 3.26s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 35%|████████████████████████████▌ | 77/221 [04:26<07:48, 3.25s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 35%|████████████████████████████▉ | 78/221 [04:29<07:56, 3.33s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 36%|█████████████████████████████▎ | 79/221 [04:32<07:38, 3.23s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 36%|█████████████████████████████▋ | 80/221 [04:36<07:33, 3.22s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 37%|██████████████████████████████ | 81/221 [04:39<07:56, 3.41s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 37%|██████████████████████████████▍ | 82/221 [04:44<08:28, 3.66s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 38%|██████████████████████████████▊ | 83/221 [04:48<08:53, 3.87s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 38%|███████████████████████████████▏ | 84/221 [04:52<08:54, 3.91s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 38%|███████████████████████████████▌ | 85/221 [04:57<09:14, 4.08s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 39%|████████��██████████████████████▉ | 86/221 [05:00<09:01, 4.01s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 39%|████████████████████████████████▎ | 87/221 [05:05<09:17, 4.16s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 40%|████████████████████████████████▋ | 88/221 [05:08<08:42, 3.93s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 40%|█████████████████████████████████ | 89/221 [05:12<08:11, 3.73s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 41%|█████████████████████████████████▍ | 90/221 [05:15<08:07, 3.73s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 41%|█████████████████████████████████▊ | 91/221 [05:19<08:20, 3.85s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 42%|██████████████████████████████████▏ | 92/221 [05:24<08:32, 3.97s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 42%|██████████████████████████████████▌ | 93/221 [05:28<08:37, 4.04s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 43%|██████████████████████████████████▉ | 94/221 [05:32<08:24, 3.98s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 43%|███████████████████████████████████▏ | 95/221 [05:36<08:23, 3.99s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 43%|███████████████████████████████████▌ | 96/221 [05:40<08:12, 3.94s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 44%|███████████████████████████████████▉ | 97/221 [05:44<08:22, 4.06s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 44%|████████████████████████████████████▎ | 98/221 [05:48<08:09, 3.98s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 45%|████████████████████████████████████▋ | 99/221 [05:51<07:25, 3.66s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 45%|████████████████████████████████████▋ | 100/221 [05:54<07:23, 3.67s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 46%|█████████████████████████████████████ | 101/221 [05:57<07:02, 3.52s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 46%|█████████████████████████████████████▍ | 102/221 [06:00<06:38, 3.35s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 47%|█████████████████████████████████████▊ | 103/221 [06:04<06:54, 3.51s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 47%|██████████████████████████████████████ | 104/221 [06:08<07:06, 3.65s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 48%|██████████████████████████████████████▍ | 105/221 [06:13<07:27, 3.86s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 48%|█████████████████████████████████���████▊ | 106/221 [06:17<07:26, 3.88s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 48%|███████████████████████████████████████▏ | 107/221 [06:20<06:54, 3.64s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 49%|███████████████████████████████████████▌ | 108/221 [06:24<07:13, 3.84s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 49%|███████████████████████████████████████▉ | 109/221 [06:28<07:16, 3.90s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 50%|████████████████████████████████████████▎ | 110/221 [06:31<06:56, 3.75s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 50%|████████████████████████████████████████▋ | 111/221 [06:35<06:39, 3.63s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 51%|█████████████████████████████████████████ | 112/221 [06:39<06:42, 3.69s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 51%|█████████████████████████████████████████▍ | 113/221 [06:42<06:37, 3.68s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 52%|█████████████████████████████████████████▊ | 114/221 [06:46<06:23, 3.59s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 52%|██████████████████████████████████████████▏ | 115/221 [06:49<06:16, 3.56s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 52%|██████████��███████████████████████████████▌ | 116/221 [06:52<06:02, 3.45s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 53%|██████████████████████████████████████████▉ | 117/221 [06:56<05:55, 3.42s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 53%|███████████████████████████████████████████▏ | 118/221 [06:59<06:05, 3.54s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 54%|███████████████████████████████████████████▌ | 119/221 [07:04<06:28, 3.81s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 54%|███████████████████████████████████████████▉ | 120/221 [07:08<06:42, 3.98s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 55%|████████████████████████████████████████████▎ | 121/221 [07:12<06:27, 3.88s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 55%|████████████████████████████████████████████▋ | 122/221 [07:14<05:43, 3.47s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 56%|█████████████████████████████████████████████ | 123/221 [07:17<05:09, 3.16s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 56%|█████████████████████████████████████████████▍ | 124/221 [07:20<05:04, 3.14s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 57%|█████████████████████████████████████████████▊ | 125/221 [07:24<05:22, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 57%|██████████████████████████████████████████████▏ | 126/221 [07:27<05:03, 3.19s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 57%|██████████████████████████████████████████████▌ | 127/221 [07:29<04:50, 3.09s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 58%|██████████████████████████████████████████████▉ | 128/221 [07:32<04:33, 2.94s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 58%|███████████████████████████████████████████████▎ | 129/221 [07:36<04:51, 3.17s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 59%|███████████████████████████████████████████████▋ | 130/221 [07:38<04:35, 3.03s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 59%|████████████████████████████████████████████████ | 131/221 [07:42<04:48, 3.21s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 60%|████████████████████████████████████████████████▍ | 132/221 [07:45<04:29, 3.03s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 60%|████████████████████████████████████████████████▋ | 133/221 [07:48<04:30, 3.07s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 61%|█████████████████████████████████████████████████ | 134/221 [07:51<04:18, 2.97s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 61%|█████████████████████████████████████████████████▍ | 135/221 [07:54<04:22, 3.05s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 62%|█████████████████████████████████████████████████▊ | 136/221 [07:58<04:38, 3.27s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 62%|██████████████████████████████████████████████████▏ | 137/221 [08:01<04:42, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 62%|██████████████████████████████████████████████████▌ | 138/221 [08:05<04:50, 3.50s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 63%|██████████████████████████████████████████████████▉ | 139/221 [08:09<04:52, 3.56s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 63%|███████████████████████████████████████████████████▎ | 140/221 [08:11<04:21, 3.22s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 64%|███████████████████████████████████████████████████▋ | 141/221 [08:14<04:18, 3.23s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 64%|████████████████████████████████████████████████████ | 142/221 [08:17<04:10, 3.17s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 65%|████████████████████████████████████████████████████▍ | 143/221 [08:20<03:51, 2.97s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 65%|████████████████████████████████████████████████████▊ | 144/221 [08:24<04:08, 3.23s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 66%|█████████████████████████████████████████████████████▏ | 145/221 [08:27<04:02, 3.19s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 66%|█████████████████████████████████████████████████████▌ | 146/221 [08:31<04:12, 3.37s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 67%|█████████████████████████████████████████████████████▉ | 147/221 [08:33<03:57, 3.21s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 67%|██████████████████████████████████████████████████████▏ | 148/221 [08:37<03:57, 3.25s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 67%|██████████████████████████████████████████████████████▌ | 149/221 [08:40<03:56, 3.28s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 68%|██████████████████████████████████████████████████████▉ | 150/221 [08:43<03:51, 3.26s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 68%|███████████████████████████████████████████████████████▎ | 151/221 [08:47<03:58, 3.41s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 69%|███████████████████████████████████████████████████████▋ | 152/221 [08:50<03:50, 3.34s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 69%|████████████████████████████████████████████████████████ | 153/221 [08:53<03:43, 3.28s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 70%|████████████████████████████████████████████████████████▍ | 154/221 [08:57<03:43, 3.33s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 70%|████████████████████████████████████████████████████████▊ | 155/221 [09:00<03:40, 3.35s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 71%|█████████████████████████████████████████████████████████▏ | 156/221 [09:04<03:40, 3.39s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 71%|█████████████████████████████████████████████████████████▌ | 157/221 [09:07<03:24, 3.19s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 71%|█████████████████████████████████████████████████████████▉ | 158/221 [09:11<03:48, 3.63s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 72%|██████████████████████████████████████████████████████████▎ | 159/221 [09:15<03:47, 3.67s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 72%|██████████████████████████████████████████████████████████▋ | 160/221 [09:19<03:52, 3.81s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 73%|███████████████████████████████████████████████████████████ | 161/221 [09:23<03:55, 3.93s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 73%|███████████████████████████████████████████████████████████▍ | 162/221 [09:27<03:52, 3.94s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 74%|███████████████████████████████████████████████████████████▋ | 163/221 [09:32<03:55, 4.07s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 74%|████████████████████████████████████████████████████████████ | 164/221 [09:36<03:59, 4.21s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 75%|████████████████████████████████████████████████████████████▍ | 165/221 [09:40<03:45, 4.03s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 75%|████████████████████████████████████████████████████████████▊ | 166/221 [09:43<03:26, 3.75s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 76%|█████████████████████████████████████████████████████████████▏ | 167/221 [09:46<03:19, 3.69s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 76%|█████████████████████████████████████████████████████████████▌ | 168/221 [09:50<03:06, 3.51s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 76%|█████████████████████████████████████████████████████████████▉ | 169/221 [09:53<03:07, 3.61s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 77%|██████████████████████████████████████████████████████████████▎ | 170/221 [09:57<03:07, 3.68s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 77%|██████████████████████████████████████████████████████████████▋ | 171/221 [10:01<03:04, 3.68s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 78%|███████████████████████████████████████████████████████████████ | 172/221 [10:04<02:54, 3.57s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 78%|███████████████████████████████████████████████████████████████▍ | 173/221 [10:08<02:50, 3.55s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 79%|███████████████████████████████████████████████████████████████▊ | 174/221 [10:11<02:40, 3.41s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 79%|████████████████████████████████████████████████████████████████▏ | 175/221 [10:14<02:32, 3.32s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 79%|████████████████████████████████████████████████████████████████▏ | 175/221 [10:14<02:32, 3.32s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 79%|████████████████████████████████████████████████████████████████▏ | 175/221 [10:14<02:32, 3.32s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 80%|████████████████████████████████████████████████████████████████▊ | 177/221 [10:21<02:25, 3.31s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 81%|█████████████████████████████████████████████████████████████████▏ | 178/221 [10:24<02:28, 3.45s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 81%|█████████████████████████████████████████████████████████████████▌ | 179/221 [10:28<02:22, 3.40s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 81%|█████████████████████████████████████████████████████████████████▉ | 180/221 [10:32<02:29, 3.64s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 82%|██████████████████████████████████████████████████████████████████▎ | 181/221 [10:36<02:29, 3.73s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 82%|██████████████████████████████████████████████████████████████████▋ | 182/221 [10:39<02:24, 3.70s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 83%|███████████████████████████████████████████████████████████████████ | 183/221 [10:44<02:27, 3.87s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 83%|███████████████████████████████████████████████████████████████████▍ | 184/221 [10:48<02:22, 3.84s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 84%|███████████████████████████████████████████████████████████████████▊ | 185/221 [10:51<02:12, 3.69s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 84%|████████████████████████████████████████████████████████████████████▏ | 186/221 [10:55<02:16, 3.91s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 85%|████████████████████████████████████████████████████████████████████▌ | 187/221 [10:59<02:08, 3.78s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 85%|████████████████████████████████████████████████████████████████████▉ | 188/221 [11:03<02:08, 3.90s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 86%|█████████████████████████████████████████████████████████████████████▎ | 189/221 [11:07<02:06, 3.96s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 86%|█████████████████████████████████████████████████████████████████████▋ | 190/221 [11:11<02:06, 4.10s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 86%|██████████████████████████████████████████████████████████████████████ | 191/221 [11:16<02:07, 4.24s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 87%|██████████████████████████████████████████████████████████████████████▎ | 192/221 [11:20<02:02, 4.23s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 87%|██████████████████████████████████████████████████████████████████████▋ | 193/221 [11:24<01:50, 3.95s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 88%|███████████████████████████████████████████████████████████████████████ | 194/221 [11:27<01:40, 3.71s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 88%|███████████████████████████████████████████████████████████████████████▍ | 195/221 [11:30<01:31, 3.50s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 89%|███████████████████████████████████████████████████████████████████████▊ | 196/221 [11:33<01:25, 3.43s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 89%|████████████████████████████████████████████████████████████████████████▏ | 197/221 [11:36<01:18, 3.26s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 90%|████████████████████████████████████████████████████████████████████████▌ | 198/221 [11:40<01:21, 3.54s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 90%|████████████████████████████████████████████████████████████████████████▉ | 199/221 [11:44<01:23, 3.81s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 90%|█████████████████████████████████████████████████████████████████████████▎ | 200/221 [11:48<01:18, 3.72s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 91%|█████████████████████████████████████████████████████████████████████████▋ | 201/221 [11:51<01:11, 3.60s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 91%|██████████████████████████████████████████████████████████████████████████ | 202/221 [11:54<01:04, 3.38s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 92%|██████████████████████████████████████████████████████████████████████████▍ | 203/221 [11:58<01:02, 3.45s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 92%|██████████████████████████████████████████████████████████████████████████▊ | 204/221 [12:02<01:03, 3.75s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 93%|███████████████████████████████████████████████████████████████████████████▏ | 205/221 [12:07<01:05, 4.07s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 93%|███████████████████████████████████████████████████████████████████████████▌ | 206/221 [12:12<01:03, 4.24s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 94%|███████████████████████████████████████████████████████████████████████████▊ | 207/221 [12:15<00:56, 4.02s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 94%|████████████████████████████████████████████████████████████████████████████▏ | 208/221 [12:19<00:51, 3.96s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 95%|████████████████████████████████████████████████████████████████████████████▌ | 209/221 [12:22<00:45, 3.75s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 95%|████████████████████████████████████████████████████████████████████████████▉ | 210/221 [12:26<00:42, 3.84s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 95%|█████████████████████████████████████████████████████████████████████████████▎ | 211/221 [12:31<00:40, 4.01s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 96%|█████████████████████████████████████████████████████████████████████████████▋ | 212/221 [12:34<00:35, 3.93s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 96%|██████████████████████████████████████████████████████████████████████████████ | 213/221 [12:38<00:29, 3.67s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 97%|██████████████████████████████████████████████████████████████████████████████▍ | 214/221 [12:41<00:25, 3.64s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 97%|██████████████████████████████████████████████████████████████████████████████▊ | 215/221 [12:45<00:22, 3.80s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 98%|███████████████████████████████████████████████████████████████████████████████▏ | 216/221 [12:49<00:19, 3.89s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 98%|███████████████████████████████████████████████████████████████████████████████▌ | 217/221 [12:53<00:15, 3.90s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 99%|███████████████████████████████████████████████████████████████████████████████▉ | 218/221 [12:57<00:11, 3.86s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + 99%|████████████████████████████████████████████████████████████████████████████████▎| 219/221 [13:01<00:07, 3.86s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +100%|████████████████████████████████████████████████████████████████████████████████▋| 220/221 [13:05<00:04, 4.06s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[INFO|configuration_utils.py:438] 2022-02-28 17:21:17,260 >> Configuration saved in ./checkpoint-500/config.json [INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[INFO|configuration_utils.py:438] 2022-02-28 17:21:17,260 >> Configuration saved in ./checkpoint-500/config.json [INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +02/28/2022 17:21:17 - INFO - datasets.metric - Removing /home/sanchit_huggingface_co/.cache/huggingface/metrics/wer/default/default_experiment-1-0.arrow +[INFO|feature_extraction_utils.py:324] 2022-02-28 17:21:33,438 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[INFO|feature_extraction_utils.py:324] 2022-02-28 17:21:33,438 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[INFO|feature_extraction_utils.py:324] 2022-02-28 17:21:33,438 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[INFO|feature_extraction_utils.py:324] 2022-02-28 17:21:33,438 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message.