diff --git "a/wandb/run-20220301_082052-1y1by2yf/files/output.log" "b/wandb/run-20220301_082052-1y1by2yf/files/output.log" new file mode 100644--- /dev/null +++ "b/wandb/run-20220301_082052-1y1by2yf/files/output.log" @@ -0,0 +1,1700 @@ + + + 0%| | 0/1189 [00:00> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:20:59,063 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 0%| | 1/1189 [00:05<1:55:48, 5.85s/it] + + 0%| | 1/1189 [00:05<1:55:48, 5.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:01,726 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.0423, 'learning_rate': 0.0, 'epoch': 0.0} +[WARNING|modeling_utils.py:388] 2022-03-01 08:21:04,248 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 0%|▏ | 2/1189 [00:11<1:47:57, 5.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:06,896 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:21:09,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 0%|▏ | 3/1189 [00:16<1:47:48, 5.45s/it] + + 0%|▏ | 3/1189 [00:16<1:47:48, 5.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:12,312 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:21:14,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 0%|▎ | 4/1189 [00:21<1:45:51, 5.36s/it] + + 0%|▎ | 4/1189 [00:21<1:45:51, 5.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:17,477 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:21:19,958 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 0%|▎ | 5/1189 [00:26<1:43:54, 5.27s/it] + + 0%|▎ | 5/1189 [00:26<1:43:54, 5.27s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:22,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9547, 'learning_rate': 2.4000000000000003e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-03-01 08:21:25,055 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▍ | 6/1189 [00:31<1:42:41, 5.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:27,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:21:30,175 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▍ | 7/1189 [00:37<1:42:01, 5.18s/it] + + 1%|▍ | 7/1189 [00:37<1:42:01, 5.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:32,776 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7239, 'learning_rate': 3.6e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-03-01 08:21:35,257 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▌ | 8/1189 [00:42<1:41:20, 5.15s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:37,843 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:21:40,316 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▌ | 9/1189 [00:47<1:40:22, 5.10s/it] + + 1%|▌ | 9/1189 [00:47<1:40:22, 5.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:42,854 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7796, 'learning_rate': 4.2e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-03-01 08:21:45,291 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▋ | 10/1189 [00:52<1:39:49, 5.08s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:47,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:21:50,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▋ | 11/1189 [00:57<1:38:38, 5.02s/it] + + 1%|▋ | 11/1189 [00:57<1:38:38, 5.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:52,679 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6947, 'learning_rate': 5.4e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-03-01 08:21:55,031 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▊ | 12/1189 [01:01<1:37:29, 4.97s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:57,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9776, 'learning_rate': 6.000000000000001e-07, 'epoch': 0.01} +[WARNING|modeling_utils.py:388] 2022-03-01 08:21:59,876 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 1%|▊ | 13/1189 [01:06<1:36:39, 4.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:02,362 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:22:04,721 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|▉ | 14/1189 [01:11<1:36:03, 4.90s/it] + + 1%|▉ | 14/1189 [01:11<1:36:03, 4.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:07,188 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:22:09,529 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6509, 'learning_rate': 7.2e-07, 'epoch': 0.01} + + 1%|▉ | 15/1189 [01:16<1:35:24, 4.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:11,968 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:22:14,278 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|█ | 16/1189 [01:21<1:34:35, 4.84s/it] + + 1%|█ | 16/1189 [01:21<1:34:35, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:16,727 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:22:19,079 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 1%|█▏ | 17/1189 [01:25<1:34:16, 4.83s/it] + + 1%|█▏ | 17/1189 [01:25<1:34:16, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:21,497 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:22:23,780 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9677, 'learning_rate': 9e-07, 'epoch': 0.02} + 2%|█▏ | 18/1189 [01:30<1:33:28, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:26,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:22:28,416 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7116, 'learning_rate': 9.600000000000001e-07, 'epoch': 0.02} + + 2%|█▎ | 19/1189 [01:35<1:32:28, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:30,776 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:22:32,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▎ | 20/1189 [01:39<1:31:25, 4.69s/it] + + 2%|█▎ | 20/1189 [01:39<1:31:25, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:35,328 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:22:37,575 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▍ | 21/1189 [01:44<1:30:42, 4.66s/it] + + 2%|█▍ | 21/1189 [01:44<1:30:42, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:39,896 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:22:42,129 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▍ | 22/1189 [01:48<1:30:01, 4.63s/it] + + 2%|█▍ | 22/1189 [01:48<1:30:01, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:44,456 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8528, 'learning_rate': 1.2000000000000002e-06, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-03-01 08:22:46,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 2%|█▌ | 23/1189 [01:53<1:29:41, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:49,066 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:22:51,291 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▌ | 24/1189 [01:58<1:29:23, 4.60s/it] + + 2%|█▌ | 24/1189 [01:58<1:29:23, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:53,614 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:22:55,780 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▋ | 25/1189 [02:02<1:28:39, 4.57s/it] + + 2%|█▋ | 25/1189 [02:02<1:28:39, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:58,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:00,237 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▋ | 26/1189 [02:07<1:27:54, 4.54s/it] + + 2%|█▋ | 26/1189 [02:07<1:27:54, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:02,506 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:04,669 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▊ | 27/1189 [02:11<1:27:14, 4.50s/it] + + 2%|█▊ | 27/1189 [02:11<1:27:14, 4.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:06,943 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:09,096 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▊ | 28/1189 [02:15<1:26:42, 4.48s/it] + + 2%|█▊ | 28/1189 [02:15<1:26:42, 4.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:11,290 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6476, 'learning_rate': 1.5599999999999999e-06, 'epoch': 0.02} +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:13,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 2%|█▉ | 29/1189 [02:20<1:25:44, 4.44s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:15,614 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:17,701 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|█▉ | 30/1189 [02:24<1:24:45, 4.39s/it] + + 3%|█▉ | 30/1189 [02:24<1:24:45, 4.39s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:19,874 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:21,950 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██ | 31/1189 [02:28<1:23:52, 4.35s/it] + + 3%|██ | 31/1189 [02:28<1:23:52, 4.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:24,094 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6104, 'learning_rate': 1.74e-06, 'epoch': 0.03} +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:26,164 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 3%|██▏ | 32/1189 [02:33<1:23:02, 4.31s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:28,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:30,358 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7272, 'learning_rate': 1.8e-06, 'epoch': 0.03} + 3%|██▏ | 33/1189 [02:37<1:22:19, 4.27s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:32,505 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:34,442 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▎ | 34/1189 [02:41<1:21:09, 4.22s/it] + + 3%|██▎ | 34/1189 [02:41<1:21:09, 4.22s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:36,480 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5867, 'learning_rate': 1.9200000000000003e-06, 'epoch': 0.03} +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:38,416 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 3%|██▎ | 35/1189 [02:45<1:19:41, 4.14s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:40,448 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9098, 'learning_rate': 1.98e-06, 'epoch': 0.03} +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:42,370 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 3%|██▍ | 36/1189 [02:49<1:18:31, 4.09s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:44,333 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7237, 'learning_rate': 2.0400000000000004e-06, 'epoch': 0.03} +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:46,179 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 3%|██▍ | 37/1189 [02:53<1:16:53, 4.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:48,087 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5612, 'learning_rate': 2.1000000000000002e-06, 'epoch': 0.03} +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:49,883 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 3%|██▌ | 38/1189 [02:56<1:15:04, 3.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:51,776 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.0326, 'learning_rate': 2.16e-06, 'epoch': 0.03} +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:53,512 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 3%|██▌ | 39/1189 [03:00<1:13:22, 3.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:55,336 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:23:57,064 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6771, 'learning_rate': 2.22e-06, 'epoch': 0.03} + 3%|██▋ | 40/1189 [03:03<1:11:43, 3.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:58,874 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5023, 'learning_rate': 2.28e-06, 'epoch': 0.03} +[WARNING|modeling_utils.py:388] 2022-03-01 08:24:00,492 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + + 3%|██▋ | 41/1189 [03:07<1:09:50, 3.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:02,158 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5602, 'learning_rate': 2.34e-06, 'epoch': 0.04} +[WARNING|modeling_utils.py:388] 2022-03-01 08:24:03,688 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▊ | 42/1189 [03:10<1:07:10, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:05,269 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5688, 'learning_rate': 2.4000000000000003e-06, 'epoch': 0.04} +[WARNING|modeling_utils.py:388] 2022-03-01 08:24:06,686 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▊ | 43/1189 [03:13<1:04:09, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:08,151 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:24:09,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|██▉ | 44/1189 [03:16<1:00:34, 3.17s/it] + + 4%|██▉ | 44/1189 [03:16<1:00:34, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:10,752 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.8205, 'learning_rate': 2.52e-06, 'epoch': 0.04} +[WARNING|modeling_utils.py:388] 2022-03-01 08:24:11,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███ | 45/1189 [03:18<56:27, 2.96s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:13,068 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7995, 'learning_rate': 2.58e-06, 'epoch': 0.04} +[WARNING|modeling_utils.py:388] 2022-03-01 08:24:14,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▏ | 46/1189 [03:20<51:54, 2.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:15,127 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.9812, 'learning_rate': 2.6399999999999997e-06, 'epoch': 0.04} +[WARNING|modeling_utils.py:388] 2022-03-01 08:24:16,032 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▏ | 47/1189 [03:22<47:32, 2.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:16,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 5.1944, 'learning_rate': 2.7e-06, 'epoch': 0.04} +[WARNING|modeling_utils.py:388] 2022-03-01 08:24:17,730 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▎ | 48/1189 [03:24<42:55, 2.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:18,522 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:24:19,173 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▎ | 49/1189 [03:26<38:14, 2.01s/it] +{'loss': 5.3073, 'learning_rate': 2.76e-06, 'epoch': 0.04} + 4%|███▎ | 49/1189 [03:26<38:14, 2.01s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:19,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:24:20,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 50/1189 [03:27<36:35, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:23,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 50/1189 [03:27<36:35, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:23,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 51/1189 [03:33<57:21, 3.02s/it]g-point operations will not be computed-01 08:24:23,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 51/1189 [03:33<57:21, 3.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:29,169 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 52/1189 [03:38<1:10:08, 3.70s/it]g-point operations will not be computed-01 08:24:29,169 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 52/1189 [03:38<1:10:08, 3.70s/it]g-point operations will not be computed-01 08:24:29,169 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 52/1189 [03:38<1:10:08, 3.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:34,402 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▍ | 52/1189 [03:38<1:10:08, 3.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:34,402 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▌ | 53/1189 [03:43<1:17:59, 4.12s/it]g-point operations will not be computed-01 08:24:34,402 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 4%|███▌ | 53/1189 [03:43<1:17:59, 4.12s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:39,338 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + g-point operations will not be computed-01 08:24:39,338 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + g-point operations will not be computed-01 08:24:39,338 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▌ | 54/1189 [03:48<1:22:32, 4.36s/it]g-point operations will not be computed-01 08:24:39,338 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▌ | 54/1189 [03:48<1:22:32, 4.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:44,379 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▌ | 54/1189 [03:48<1:22:32, 4.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:44,379 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 55/1189 [03:53<1:26:21, 4.57s/it]g-point operations will not be computed-01 08:24:44,379 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 55/1189 [03:53<1:26:21, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:49,401 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 56/1189 [03:58<1:28:33, 4.69s/it]g-point operations will not be computed-01 08:24:49,401 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 56/1189 [03:58<1:28:33, 4.69s/it]g-point operations will not be computed-01 08:24:49,401 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 56/1189 [03:58<1:28:33, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:54,373 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▋ | 56/1189 [03:58<1:28:33, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:54,373 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 57/1189 [04:03<1:30:07, 4.78s/it]g-point operations will not be computed-01 08:24:54,373 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 57/1189 [04:03<1:30:07, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:59,357 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 57/1189 [04:03<1:30:07, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:59,357 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 58/1189 [04:08<1:30:58, 4.83s/it]g-point operations will not be computed-01 08:24:59,357 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▊ | 58/1189 [04:08<1:30:58, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:04,178 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 59/1189 [04:13<1:31:01, 4.83s/it]g-point operations will not be computed-01 08:25:04,178 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 59/1189 [04:13<1:31:01, 4.83s/it]g-point operations will not be computed-01 08:25:04,178 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 59/1189 [04:13<1:31:01, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:09,073 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 60/1189 [04:18<1:31:09, 4.84s/it]g-point operations will not be computed-01 08:25:09,073 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 60/1189 [04:18<1:31:09, 4.84s/it]g-point operations will not be computed-01 08:25:09,073 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 60/1189 [04:18<1:31:09, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:13,897 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|███▉ | 60/1189 [04:18<1:31:09, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:13,897 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 61/1189 [04:23<1:30:50, 4.83s/it]g-point operations will not be computed-01 08:25:13,897 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 61/1189 [04:23<1:30:50, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:18,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 62/1189 [04:27<1:30:27, 4.82s/it]g-point operations will not be computed-01 08:25:18,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 62/1189 [04:27<1:30:27, 4.82s/it]g-point operations will not be computed-01 08:25:18,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████ | 62/1189 [04:27<1:30:27, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:23,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▏ | 63/1189 [04:32<1:30:07, 4.80s/it]g-point operations will not be computed-01 08:25:23,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▏ | 63/1189 [04:32<1:30:07, 4.80s/it]g-point operations will not be computed-01 08:25:23,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▏ | 63/1189 [04:32<1:30:07, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:28,293 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▏ | 63/1189 [04:32<1:30:07, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:28,293 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 64/1189 [04:37<1:30:09, 4.81s/it]g-point operations will not be computed-01 08:25:28,293 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 64/1189 [04:37<1:30:09, 4.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:33,029 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 65/1189 [04:42<1:29:17, 4.77s/it]g-point operations will not be computed-01 08:25:33,029 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 65/1189 [04:42<1:29:17, 4.77s/it]g-point operations will not be computed-01 08:25:33,029 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 5%|████▎ | 65/1189 [04:42<1:29:17, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:37,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 66/1189 [04:46<1:28:39, 4.74s/it]g-point operations will not be computed-01 08:25:37,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 66/1189 [04:46<1:28:39, 4.74s/it]g-point operations will not be computed-01 08:25:37,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 66/1189 [04:46<1:28:39, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:42,335 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 66/1189 [04:46<1:28:39, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:42,335 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 67/1189 [04:51<1:28:01, 4.71s/it]g-point operations will not be computed-01 08:25:42,335 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▍ | 67/1189 [04:51<1:28:01, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:46,907 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 68/1189 [04:55<1:27:00, 4.66s/it]g-point operations will not be computed-01 08:25:46,907 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 68/1189 [04:55<1:27:00, 4.66s/it]g-point operations will not be computed-01 08:25:46,907 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 68/1189 [04:55<1:27:00, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:51,526 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 69/1189 [05:00<1:26:39, 4.64s/it]g-point operations will not be computed-01 08:25:51,526 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 69/1189 [05:00<1:26:39, 4.64s/it]g-point operations will not be computed-01 08:25:51,526 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▌ | 69/1189 [05:00<1:26:39, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:56,073 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 70/1189 [05:05<1:25:56, 4.61s/it]g-point operations will not be computed-01 08:25:56,073 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 70/1189 [05:05<1:25:56, 4.61s/it]g-point operations will not be computed-01 08:25:56,073 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 70/1189 [05:05<1:25:56, 4.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:00,603 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 71/1189 [05:09<1:25:28, 4.59s/it]g-point operations will not be computed-01 08:26:00,603 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 71/1189 [05:09<1:25:28, 4.59s/it]g-point operations will not be computed-01 08:26:00,603 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 71/1189 [05:09<1:25:28, 4.59s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:05,149 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▋ | 71/1189 [05:09<1:25:28, 4.59s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:05,149 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 72/1189 [05:14<1:25:14, 4.58s/it]g-point operations will not be computed-01 08:26:05,149 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 72/1189 [05:14<1:25:14, 4.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:09,678 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 72/1189 [05:14<1:25:14, 4.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:09,678 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 73/1189 [05:18<1:25:00, 4.57s/it]g-point operations will not be computed-01 08:26:09,678 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 73/1189 [05:18<1:25:00, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:14,285 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▊ | 73/1189 [05:18<1:25:00, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:14,285 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 74/1189 [05:23<1:24:57, 4.57s/it]g-point operations will not be computed-01 08:26:14,285 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 74/1189 [05:23<1:24:57, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:18,803 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 75/1189 [05:27<1:24:19, 4.54s/it]g-point operations will not be computed-01 08:26:18,803 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 75/1189 [05:27<1:24:19, 4.54s/it]g-point operations will not be computed-01 08:26:18,803 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 75/1189 [05:27<1:24:19, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:23,237 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|████▉ | 75/1189 [05:27<1:24:19, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:23,237 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 76/1189 [05:32<1:23:22, 4.49s/it]g-point operations will not be computed-01 08:26:23,237 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 76/1189 [05:32<1:23:22, 4.49s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:27,623 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 76/1189 [05:32<1:23:22, 4.49s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:27,623 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 77/1189 [05:36<1:22:32, 4.45s/it]g-point operations will not be computed-01 08:26:27,623 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 6%|█████ | 77/1189 [05:36<1:22:32, 4.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:31,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 78/1189 [05:40<1:21:52, 4.42s/it]g-point operations will not be computed-01 08:26:31,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 78/1189 [05:40<1:21:52, 4.42s/it]g-point operations will not be computed-01 08:26:31,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 78/1189 [05:40<1:21:52, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:36,283 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 79/1189 [05:45<1:21:04, 4.38s/it]g-point operations will not be computed-01 08:26:36,283 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 79/1189 [05:45<1:21:04, 4.38s/it]g-point operations will not be computed-01 08:26:36,283 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▏ | 79/1189 [05:45<1:21:04, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:40,547 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:26:42,652 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:26:40,547 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:26:42,652 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:26:40,547 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▎ | 80/1189 [05:49<1:20:32, 4.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:44,842 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 81/1189 [05:53<1:19:33, 4.31s/it]g-point operations will not be computed-01 08:26:44,842 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 81/1189 [05:53<1:19:33, 4.31s/it]g-point operations will not be computed-01 08:26:44,842 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 81/1189 [05:53<1:19:33, 4.31s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:48,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 82/1189 [05:57<1:18:37, 4.26s/it]g-point operations will not be computed-01 08:26:48,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 82/1189 [05:57<1:18:37, 4.26s/it]g-point operations will not be computed-01 08:26:48,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▍ | 82/1189 [05:57<1:18:37, 4.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:53,092 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 83/1189 [06:01<1:17:30, 4.20s/it]g-point operations will not be computed-01 08:26:53,092 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 83/1189 [06:01<1:17:30, 4.20s/it]g-point operations will not be computed-01 08:26:53,092 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 83/1189 [06:01<1:17:30, 4.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:57,107 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 84/1189 [06:05<1:16:10, 4.14s/it]g-point operations will not be computed-01 08:26:57,107 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 84/1189 [06:05<1:16:10, 4.14s/it]g-point operations will not be computed-01 08:26:57,107 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▌ | 84/1189 [06:05<1:16:10, 4.14s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:01,053 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 85/1189 [06:09<1:14:41, 4.06s/it]g-point operations will not be computed-01 08:27:01,053 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 85/1189 [06:09<1:14:41, 4.06s/it]g-point operations will not be computed-01 08:27:01,053 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 85/1189 [06:09<1:14:41, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:04,931 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 86/1189 [06:13<1:13:34, 4.00s/it]g-point operations will not be computed-01 08:27:04,931 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 86/1189 [06:13<1:13:34, 4.00s/it]g-point operations will not be computed-01 08:27:04,931 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▋ | 86/1189 [06:13<1:13:34, 4.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:08,738 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 87/1189 [06:17<1:12:09, 3.93s/it]g-point operations will not be computed-01 08:27:08,738 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 87/1189 [06:17<1:12:09, 3.93s/it]g-point operations will not be computed-01 08:27:08,738 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 87/1189 [06:17<1:12:09, 3.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:12,443 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 88/1189 [06:21<1:10:32, 3.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:16,021 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▊ | 88/1189 [06:21<1:10:32, 3.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:16,021 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▉ | 89/1189 [06:24<1:08:44, 3.75s/it]g-point operations will not be computed-01 08:27:16,021 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▉ | 89/1189 [06:24<1:08:44, 3.75s/it]g-point operations will not be computed-01 08:27:16,021 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 7%|█████▉ | 89/1189 [06:24<1:08:44, 3.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:19,481 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▉ | 90/1189 [06:27<1:06:25, 3.63s/it]g-point operations will not be computed-01 08:27:19,481 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▉ | 90/1189 [06:27<1:06:25, 3.63s/it]g-point operations will not be computed-01 08:27:19,481 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|█████▉ | 90/1189 [06:27<1:06:25, 3.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:22,749 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 91/1189 [06:31<1:03:55, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:25,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 91/1189 [06:31<1:03:55, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:25,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4315, 'learning_rate': 5.22e-06, 'epoch': 0.08} +[WARNING|modeling_utils.py:388] 2022-03-01 08:27:27,324 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 92/1189 [06:34<1:01:32, 3.37s/it] + 8%|██████ | 92/1189 [06:34<1:01:32, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:28,794 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████ | 92/1189 [06:34<1:01:32, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:28,794 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▎ | 93/1189 [06:36<58:18, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:31,443 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▍ | 94/1189 [06:39<54:31, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:33,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▍ | 94/1189 [06:39<54:31, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:33,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▍ | 95/1189 [06:41<50:45, 2.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:36,040 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▍ | 95/1189 [06:41<50:45, 2.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:36,040 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 96/1189 [06:43<46:43, 2.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:37,958 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 96/1189 [06:43<46:43, 2.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:37,958 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 97/1189 [06:45<42:34, 2.34s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:39,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▌ | 97/1189 [06:45<42:34, 2.34s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:39,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 99/1189 [06:48<35:01, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:41,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:27:41,897 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 99/1189 [06:48<35:01, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:41,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6356, 'learning_rate': 5.64e-06, 'epoch': 0.08} + 8%|██████▋ | 100/1189 [06:50<34:12, 1.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:42,600 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:27:43,679 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 100/1189 [06:50<34:12, 1.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:42,600 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 100/1189 [06:50<34:12, 1.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:46,513 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▋ | 100/1189 [06:50<34:12, 1.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:46,513 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▊ | 101/1189 [06:55<52:54, 2.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:46,513 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▊ | 101/1189 [06:55<52:54, 2.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:51,602 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 8%|██████▊ | 101/1189 [06:55<52:54, 2.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:51,602 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 102/1189 [07:00<1:04:48, 3.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:51,602 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 102/1189 [07:00<1:04:48, 3.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:56,704 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▋ | 102/1189 [07:00<1:04:48, 3.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:56,704 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 103/1189 [07:06<1:12:50, 4.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:56,704 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 103/1189 [07:06<1:12:50, 4.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:01,690 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 104/1189 [07:10<1:17:48, 4.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:01,690 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 104/1189 [07:10<1:17:48, 4.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:01,690 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▊ | 104/1189 [07:10<1:17:48, 4.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:06,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 105/1189 [07:15<1:21:13, 4.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:06,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 105/1189 [07:15<1:21:13, 4.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:06,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 105/1189 [07:15<1:21:13, 4.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:11,606 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 105/1189 [07:15<1:21:13, 4.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:11,606 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 106/1189 [07:20<1:23:57, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:11,606 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 106/1189 [07:20<1:23:57, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:16,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 106/1189 [07:20<1:23:57, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:16,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|██████▉ | 106/1189 [07:20<1:23:57, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:16,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 107/1189 [07:25<1:25:48, 4.76s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:21,646 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 107/1189 [07:25<1:25:48, 4.76s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:21,646 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 108/1189 [07:30<1:26:36, 4.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:21,646 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 108/1189 [07:30<1:26:36, 4.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:26,503 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████ | 108/1189 [07:30<1:26:36, 4.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:26,503 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 109/1189 [07:35<1:27:02, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:26,503 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 109/1189 [07:35<1:27:02, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:31,451 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 109/1189 [07:35<1:27:02, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:31,451 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 110/1189 [07:40<1:27:35, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:31,451 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 110/1189 [07:40<1:27:35, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:36,319 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▏ | 110/1189 [07:40<1:27:35, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:36,319 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 111/1189 [07:45<1:27:07, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:36,319 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 111/1189 [07:45<1:27:07, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:41,115 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 112/1189 [07:50<1:26:58, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:41,115 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 112/1189 [07:50<1:26:58, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:41,115 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 112/1189 [07:50<1:26:58, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:45,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 9%|███████▎ | 112/1189 [07:50<1:26:58, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:45,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▍ | 113/1189 [07:55<1:26:29, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:45,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▍ | 113/1189 [07:55<1:26:29, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:50,791 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▍ | 113/1189 [07:55<1:26:29, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:50,791 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▍ | 114/1189 [07:59<1:26:28, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:50,791 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▍ | 114/1189 [07:59<1:26:28, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:55,647 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 115/1189 [08:04<1:26:49, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:55,647 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 115/1189 [08:04<1:26:49, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:55,647 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 116/1189 [08:09<1:26:21, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:00,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 116/1189 [08:09<1:26:21, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:00,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 116/1189 [08:09<1:26:21, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:05,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▌ | 116/1189 [08:09<1:26:21, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:05,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▋ | 117/1189 [08:14<1:25:45, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:05,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▋ | 117/1189 [08:14<1:25:45, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:09,946 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▋ | 118/1189 [08:19<1:25:05, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:09,946 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▋ | 118/1189 [08:19<1:25:05, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:09,946 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▋ | 118/1189 [08:19<1:25:05, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:14,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 119/1189 [08:23<1:24:55, 4.76s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:14,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 119/1189 [08:23<1:24:55, 4.76s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:14,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.189, 'learning_rate': 6.900000000000001e-06, 'epoch': 0.1} + 10%|███████▊ | 119/1189 [08:23<1:24:55, 4.76s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:19,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 120/1189 [08:28<1:24:23, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:19,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 120/1189 [08:28<1:24:23, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:19,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▊ | 120/1189 [08:28<1:24:23, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:24,100 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▉ | 121/1189 [08:33<1:24:09, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:24,100 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▉ | 121/1189 [08:33<1:24:09, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:24,100 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|███████▉ | 121/1189 [08:33<1:24:09, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:28,702 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 122/1189 [08:37<1:23:32, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:28,702 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 122/1189 [08:37<1:23:32, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:28,702 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 122/1189 [08:37<1:23:32, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:33,323 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 122/1189 [08:37<1:23:32, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:33,323 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 123/1189 [08:42<1:22:41, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:33,323 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 123/1189 [08:42<1:22:41, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:37,845 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████ | 123/1189 [08:42<1:22:41, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:37,845 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████▏ | 124/1189 [08:46<1:21:39, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:37,845 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 10%|████████▏ | 124/1189 [08:46<1:21:39, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:42,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▏ | 125/1189 [08:51<1:21:07, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:42,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▏ | 125/1189 [08:51<1:21:07, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:42,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▏ | 125/1189 [08:51<1:21:07, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:46,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 126/1189 [08:55<1:20:24, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:46,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 126/1189 [08:55<1:20:24, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:46,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 126/1189 [08:55<1:20:24, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:51,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 127/1189 [09:00<1:19:46, 4.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:51,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 127/1189 [09:00<1:19:46, 4.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:51,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 127/1189 [09:00<1:19:46, 4.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:55,613 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 127/1189 [09:00<1:19:46, 4.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:55,613 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▎ | 127/1189 [09:00<1:19:46, 4.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:55,613 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 128/1189 [09:04<1:18:44, 4.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:55,613 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 129/1189 [09:08<1:18:04, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:59,968 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 129/1189 [09:08<1:18:04, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:59,968 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▍ | 129/1189 [09:08<1:18:04, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:04,402 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + [WARNING|modeling_utils.py:388] 2022-03-01 08:30:04,402 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + [WARNING|modeling_utils.py:388] 2022-03-01 08:30:04,402 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▌ | 130/1189 [09:13<1:17:59, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:04,402 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▌ | 130/1189 [09:13<1:17:59, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:08,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▌ | 130/1189 [09:13<1:17:59, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:08,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▌ | 131/1189 [09:17<1:17:14, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:08,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▌ | 131/1189 [09:17<1:17:14, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:12,985 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▌ | 131/1189 [09:17<1:17:14, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:12,985 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 132/1189 [09:21<1:16:17, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:12,985 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 132/1189 [09:21<1:16:17, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:17,188 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 132/1189 [09:21<1:16:17, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:17,188 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 133/1189 [09:26<1:15:41, 4.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:21,297 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▋ | 133/1189 [09:26<1:15:41, 4.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:21,297 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 134/1189 [09:30<1:14:09, 4.22s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:25,333 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + [WARNING|modeling_utils.py:388] 2022-03-01 08:30:25,333 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + [WARNING|modeling_utils.py:388] 2022-03-01 08:30:25,333 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▊ | 135/1189 [09:34<1:12:40, 4.14s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:29,236 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 136/1189 [09:37<1:11:12, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:29,236 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 136/1189 [09:37<1:11:12, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:29,236 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 11%|████████▉ | 136/1189 [09:37<1:11:12, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:33,070 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|████████▉ | 137/1189 [09:41<1:09:49, 3.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:33,070 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|████████▉ | 137/1189 [09:41<1:09:49, 3.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:33,070 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|████████▉ | 137/1189 [09:41<1:09:49, 3.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:36,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████ | 138/1189 [09:45<1:08:30, 3.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:36,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████ | 138/1189 [09:45<1:08:30, 3.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:36,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████ | 138/1189 [09:45<1:08:30, 3.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:40,512 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████ | 139/1189 [09:49<1:06:42, 3.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:40,512 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████ | 139/1189 [09:49<1:06:42, 3.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:40,512 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▏ | 140/1189 [09:52<1:04:57, 3.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:44,041 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▏ | 140/1189 [09:52<1:04:57, 3.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:44,041 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▏ | 140/1189 [09:52<1:04:57, 3.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:47,390 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▏ | 140/1189 [09:52<1:04:57, 3.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:47,390 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▏ | 141/1189 [09:55<1:02:05, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:47,390 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▌ | 142/1189 [09:58<59:04, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:50,459 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▌ | 142/1189 [09:58<59:04, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:50,459 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▌ | 142/1189 [09:58<59:04, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:53,360 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▌ | 143/1189 [10:01<55:50, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:53,360 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▌ | 143/1189 [10:01<55:50, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:53,360 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1636, 'learning_rate': 8.340000000000001e-06, 'epoch': 0.12} + 12%|█████████▋ | 144/1189 [10:04<52:43, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:56,038 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▋ | 144/1189 [10:04<52:43, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:56,038 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▊ | 145/1189 [10:06<49:54, 2.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:58,567 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▊ | 145/1189 [10:06<49:54, 2.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:00,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▊ | 145/1189 [10:06<49:54, 2.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:00,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.6044, 'learning_rate': 8.52e-06, 'epoch': 0.12} + 12%|█████████▉ | 147/1189 [10:10<42:27, 2.44s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:03,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▉ | 147/1189 [10:10<42:27, 2.44s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:03,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▉ | 148/1189 [10:12<38:40, 2.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:04,845 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 12%|█████████▉ | 148/1189 [10:12<38:40, 2.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:04,845 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 149/1189 [10:13<34:44, 2.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:07,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 149/1189 [10:13<34:44, 2.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:07,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 150/1189 [10:15<33:41, 1.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:07,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 150/1189 [10:15<33:41, 1.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:11,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 150/1189 [10:15<33:41, 1.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:11,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 151/1189 [10:21<52:26, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:11,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 151/1189 [10:21<52:26, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:17,138 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 151/1189 [10:21<52:26, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:17,138 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|█████████▉ | 152/1189 [10:26<1:03:38, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:17,138 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|█████████▉ | 152/1189 [10:26<1:03:38, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:22,358 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|█████████▉ | 152/1189 [10:26<1:03:38, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:22,358 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 153/1189 [10:31<1:11:20, 4.13s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:22,358 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 153/1189 [10:31<1:11:20, 4.13s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:27,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 153/1189 [10:31<1:11:20, 4.13s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:27,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 154/1189 [10:36<1:16:51, 4.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:27,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████ | 154/1189 [10:36<1:16:51, 4.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:32,658 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 155/1189 [10:41<1:20:01, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:32,658 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 155/1189 [10:41<1:20:01, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:32,658 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 155/1189 [10:41<1:20:01, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:37,726 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 155/1189 [10:41<1:20:01, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:37,726 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 156/1189 [10:47<1:22:15, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:37,726 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▏ | 156/1189 [10:47<1:22:15, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:42,784 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 157/1189 [10:52<1:23:11, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:42,784 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 157/1189 [10:52<1:23:11, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:42,784 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 157/1189 [10:52<1:23:11, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:47,766 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 157/1189 [10:52<1:23:11, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:47,766 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 158/1189 [10:57<1:24:00, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:47,766 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▎ | 158/1189 [10:57<1:24:00, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:52,765 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 159/1189 [11:02<1:24:34, 4.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:52,765 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 159/1189 [11:02<1:24:34, 4.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:52,765 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 159/1189 [11:02<1:24:34, 4.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 159/1189 [11:02<1:24:34, 4.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 13%|██████████▍ | 159/1189 [11:02<1:24:34, 4.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.98, 'learning_rate': 9.36e-06, 'epoch': 0.13} + 13%|██████████▍ | 159/1189 [11:02<1:24:34, 4.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▌ | 161/1189 [11:11<1:24:40, 4.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▌ | 161/1189 [11:11<1:24:40, 4.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2868, 'learning_rate': 9.42e-06, 'epoch': 0.14} + 14%|██████████▋ | 162/1189 [11:16<1:24:07, 4.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▋ | 162/1189 [11:16<1:24:07, 4.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2953, 'learning_rate': 9.48e-06, 'epoch': 0.14} + 14%|██████████▋ | 162/1189 [11:16<1:24:07, 4.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▋ | 163/1189 [11:21<1:23:35, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▋ | 163/1189 [11:21<1:23:35, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▊ | 164/1189 [11:26<1:23:02, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▊ | 164/1189 [11:26<1:23:02, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0061, 'learning_rate': 9.600000000000001e-06, 'epoch': 0.14} + 14%|██████████▊ | 165/1189 [11:31<1:21:58, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▊ | 165/1189 [11:31<1:21:58, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2366, 'learning_rate': 9.66e-06, 'epoch': 0.14} + 14%|██████████▊ | 165/1189 [11:31<1:21:58, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▉ | 166/1189 [11:35<1:21:15, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▉ | 166/1189 [11:35<1:21:15, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▉ | 166/1189 [11:35<1:21:15, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▉ | 167/1189 [11:40<1:20:54, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|██████████▉ | 167/1189 [11:40<1:20:54, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 168/1189 [11:45<1:20:17, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 168/1189 [11:45<1:20:17, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1252, 'learning_rate': 9.84e-06, 'epoch': 0.14} + 14%|███████████ | 169/1189 [11:49<1:20:30, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████ | 169/1189 [11:49<1:20:30, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3622, 'learning_rate': 9.9e-06, 'epoch': 0.14} + 14%|███████████ | 169/1189 [11:49<1:20:30, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 170/1189 [11:54<1:19:49, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 170/1189 [11:54<1:19:49, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 171/1189 [11:59<1:18:58, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▏ | 171/1189 [11:59<1:18:58, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2973, 'learning_rate': 1.002e-05, 'epoch': 0.14} + 14%|███████████▎ | 172/1189 [12:03<1:18:24, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 14%|███████████▎ | 172/1189 [12:03<1:18:24, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.116, 'learning_rate': 1.008e-05, 'epoch': 0.14} + 15%|███████████▎ | 173/1189 [12:08<1:18:20, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▎ | 173/1189 [12:08<1:18:20, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0488, 'learning_rate': 1.0140000000000001e-05, 'epoch': 0.15} + 15%|███████████▎ | 173/1189 [12:08<1:18:20, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▍ | 174/1189 [12:12<1:18:05, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:33:10,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:33:10,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:33:10,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2722, 'learning_rate': 1.0260000000000002e-05, 'epoch': 0.15} + 15%|███████████▌ | 176/1189 [12:21<1:16:00, 4.50s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▌ | 176/1189 [12:21<1:16:00, 4.50s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2434, 'learning_rate': 1.032e-05, 'epoch': 0.15} + 15%|███████████▌ | 177/1189 [12:25<1:15:01, 4.45s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▌ | 177/1189 [12:25<1:15:01, 4.45s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3755, 'learning_rate': 1.0379999999999999e-05, 'epoch': 0.15} + 15%|███████████▋ | 178/1189 [12:30<1:14:27, 4.42s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▋ | 178/1189 [12:30<1:14:27, 4.42s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1772, 'learning_rate': 1.044e-05, 'epoch': 0.15} + 15%|███████████▋ | 179/1189 [12:34<1:13:46, 4.38s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▋ | 179/1189 [12:34<1:13:46, 4.38s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2407, 'learning_rate': 1.05e-05, 'epoch': 0.15} + 15%|███████████▊ | 180/1189 [12:38<1:13:11, 4.35s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▊ | 180/1189 [12:38<1:13:11, 4.35s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3553, 'learning_rate': 1.0559999999999999e-05, 'epoch': 0.15} + 15%|███████████▊ | 181/1189 [12:43<1:12:51, 4.34s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▊ | 181/1189 [12:43<1:12:51, 4.34s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.327, 'learning_rate': 1.062e-05, 'epoch': 0.15} + 15%|███████████▉ | 182/1189 [12:47<1:11:44, 4.27s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|███████████▉ | 182/1189 [12:47<1:11:44, 4.27s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3378, 'learning_rate': 1.068e-05, 'epoch': 0.15} + 15%|████████████ | 183/1189 [12:51<1:10:55, 4.23s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████ | 183/1189 [12:51<1:10:55, 4.23s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2012, 'learning_rate': 1.074e-05, 'epoch': 0.15} + 15%|████████████ | 183/1189 [12:51<1:10:55, 4.23s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████ | 184/1189 [12:55<1:09:49, 4.17s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████ | 184/1189 [12:55<1:09:49, 4.17s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 15%|████████████ | 184/1189 [12:55<1:09:49, 4.17s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▏ | 185/1189 [12:59<1:08:51, 4.11s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▏ | 185/1189 [12:59<1:08:51, 4.11s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▏ | 185/1189 [12:59<1:08:51, 4.11s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▏ | 186/1189 [13:03<1:07:43, 4.05s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▏ | 186/1189 [13:03<1:07:43, 4.05s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▏ | 186/1189 [13:03<1:07:43, 4.05s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▎ | 187/1189 [13:07<1:06:18, 3.97s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▎ | 187/1189 [13:07<1:06:18, 3.97s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▎ | 187/1189 [13:07<1:06:18, 3.97s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▎ | 188/1189 [13:10<1:04:49, 3.89s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:34:07,545 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:34:07,545 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.422, 'learning_rate': 1.11e-05, 'epoch': 0.16} +[WARNING|modeling_utils.py:388] 2022-03-01 08:34:07,545 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▍ | 190/1189 [13:17<1:00:13, 3.62s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▍ | 190/1189 [13:17<1:00:13, 3.62s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▍ | 190/1189 [13:17<1:00:13, 3.62s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▊ | 191/1189 [13:20<57:36, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:15,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▊ | 191/1189 [13:20<57:36, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:15,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▉ | 192/1189 [13:23<54:41, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:15,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|████████████▉ | 192/1189 [13:23<54:41, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:15,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:34:19,478 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:15,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:34:19,478 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:15,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:34:19,478 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:15,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|█████████████ | 194/1189 [13:28<48:40, 2.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:23,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|█████████████ | 194/1189 [13:28<48:40, 2.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:23,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|█████████████ | 195/1189 [13:31<45:37, 2.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:25,479 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|█████████████ | 195/1189 [13:31<45:37, 2.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:25,479 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|█████████████▏ | 196/1189 [13:33<42:26, 2.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:27,505 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 16%|█████████████▏ | 196/1189 [13:33<42:26, 2.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:27,505 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 197/1189 [13:35<39:19, 2.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:29,368 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 197/1189 [13:35<39:19, 2.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:29,368 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5566, 'learning_rate': 1.164e-05, 'epoch': 0.17} + 17%|█████████████▎ | 198/1189 [13:37<36:16, 2.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:31,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 200/1189 [13:40<31:52, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 200/1189 [13:40<31:52, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3267, 'learning_rate': 1.1760000000000001e-05, 'epoch': 0.17} + 17%|█████████████▍ | 200/1189 [13:40<31:52, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 200/1189 [13:40<31:52, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 201/1189 [13:45<49:14, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 201/1189 [13:45<49:14, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 202/1189 [13:50<59:57, 3.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 202/1189 [13:50<59:57, 3.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1833, 'learning_rate': 1.1880000000000001e-05, 'epoch': 0.17} + 17%|█████████████▌ | 202/1189 [13:50<59:57, 3.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 203/1189 [13:55<1:06:36, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 203/1189 [13:55<1:06:36, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 203/1189 [13:55<1:06:36, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 203/1189 [13:55<1:06:36, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1851, 'learning_rate': 1.2e-05, 'epoch': 0.17} + 17%|█████████████▎ | 203/1189 [13:55<1:06:36, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▎ | 203/1189 [13:55<1:06:36, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 205/1189 [14:05<1:14:22, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▍ | 205/1189 [14:05<1:14:22, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 206/1189 [14:10<1:16:12, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 206/1189 [14:10<1:16:12, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1966, 'learning_rate': 1.2120000000000001e-05, 'epoch': 0.17} + 17%|█████████████▌ | 206/1189 [14:10<1:16:12, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 207/1189 [14:15<1:17:44, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 207/1189 [14:15<1:17:44, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▌ | 207/1189 [14:15<1:17:44, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▋ | 208/1189 [14:20<1:18:28, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▋ | 208/1189 [14:20<1:18:28, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▋ | 208/1189 [14:20<1:18:28, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▋ | 208/1189 [14:20<1:18:28, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3371, 'learning_rate': 1.2299999999999999e-05, 'epoch': 0.18} + 17%|█████████████▋ | 208/1189 [14:20<1:18:28, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 17%|█████████████▋ | 208/1189 [14:20<1:18:28, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▊ | 210/1189 [14:30<1:19:07, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▊ | 210/1189 [14:30<1:19:07, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▊ | 211/1189 [14:35<1:19:26, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▊ | 211/1189 [14:35<1:19:26, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.217, 'learning_rate': 1.242e-05, 'epoch': 0.18} + 18%|█████████████▊ | 211/1189 [14:35<1:19:26, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▊ | 211/1189 [14:35<1:19:26, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2961, 'learning_rate': 1.2479999999999999e-05, 'epoch': 0.18} + 18%|█████████████▊ | 211/1189 [14:35<1:19:26, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▊ | 211/1189 [14:35<1:19:26, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▉ | 213/1189 [14:45<1:18:32, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|█████████████▉ | 213/1189 [14:45<1:18:32, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████ | 214/1189 [14:49<1:17:59, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████ | 214/1189 [14:49<1:17:59, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2395, 'learning_rate': 1.26e-05, 'epoch': 0.18} + 18%|██████████████ | 215/1189 [14:54<1:17:26, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████ | 215/1189 [14:54<1:17:26, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3181, 'learning_rate': 1.2659999999999999e-05, 'epoch': 0.18} + 18%|██████████████ | 215/1189 [14:54<1:17:26, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▏ | 216/1189 [14:59<1:17:04, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▏ | 216/1189 [14:59<1:17:04, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▏ | 217/1189 [15:03<1:16:33, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▏ | 217/1189 [15:03<1:16:33, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3477, 'learning_rate': 1.278e-05, 'epoch': 0.18} + 18%|██████████████▎ | 218/1189 [15:08<1:16:22, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▎ | 218/1189 [15:08<1:16:22, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2062, 'learning_rate': 1.284e-05, 'epoch': 0.18} + 18%|██████████████▎ | 219/1189 [15:13<1:16:10, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 18%|██████████████▎ | 219/1189 [15:13<1:16:10, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.9255, 'learning_rate': 1.29e-05, 'epoch': 0.18} + 18%|██████████████▎ | 219/1189 [15:13<1:16:10, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▍ | 220/1189 [15:17<1:15:37, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▍ | 220/1189 [15:17<1:15:37, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▍ | 221/1189 [15:22<1:14:50, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▍ | 221/1189 [15:22<1:14:50, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.212, 'learning_rate': 1.302e-05, 'epoch': 0.19} + 19%|██████████████▌ | 222/1189 [15:26<1:14:07, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▌ | 222/1189 [15:26<1:14:07, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5293, 'learning_rate': 1.308e-05, 'epoch': 0.19} + 19%|██████████████▋ | 223/1189 [15:31<1:13:42, 4.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▋ | 223/1189 [15:31<1:13:42, 4.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2978, 'learning_rate': 1.314e-05, 'epoch': 0.19} + 19%|██████████████▋ | 224/1189 [15:35<1:13:13, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▋ | 224/1189 [15:35<1:13:13, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3409, 'learning_rate': 1.32e-05, 'epoch': 0.19} + 19%|██████████████▋ | 224/1189 [15:35<1:13:13, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▋ | 224/1189 [15:35<1:13:13, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1193, 'learning_rate': 1.326e-05, 'epoch': 0.19} + 19%|██████████████▋ | 224/1189 [15:35<1:13:13, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:36:37,992 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:36:37,992 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:36:37,992 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:36:37,992 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2107, 'learning_rate': 1.338e-05, 'epoch': 0.19} +[WARNING|modeling_utils.py:388] 2022-03-01 08:36:37,992 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:36:37,992 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▉ | 228/1189 [15:53<1:11:02, 4.44s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▉ | 228/1189 [15:53<1:11:02, 4.44s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|██████████████▉ | 228/1189 [15:53<1:11:02, 4.44s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████ | 229/1189 [15:57<1:10:02, 4.38s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████ | 229/1189 [15:57<1:10:02, 4.38s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████ | 229/1189 [15:57<1:10:02, 4.38s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████ | 230/1189 [16:02<1:09:20, 4.34s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████ | 230/1189 [16:02<1:09:20, 4.34s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████ | 230/1189 [16:02<1:09:20, 4.34s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▏ | 231/1189 [16:06<1:08:41, 4.30s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▏ | 231/1189 [16:06<1:08:41, 4.30s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 19%|███████████████▏ | 231/1189 [16:06<1:08:41, 4.30s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▏ | 232/1189 [16:10<1:07:42, 4.24s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▏ | 232/1189 [16:10<1:07:42, 4.24s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▏ | 232/1189 [16:10<1:07:42, 4.24s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▎ | 233/1189 [16:14<1:07:07, 4.21s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▎ | 233/1189 [16:14<1:07:07, 4.21s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▎ | 233/1189 [16:14<1:07:07, 4.21s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▎ | 234/1189 [16:18<1:05:55, 4.14s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▎ | 234/1189 [16:18<1:05:55, 4.14s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▎ | 234/1189 [16:18<1:05:55, 4.14s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▍ | 235/1189 [16:22<1:04:47, 4.08s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▍ | 235/1189 [16:22<1:04:47, 4.08s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▍ | 235/1189 [16:22<1:04:47, 4.08s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▍ | 236/1189 [16:26<1:03:41, 4.01s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▍ | 236/1189 [16:26<1:03:41, 4.01s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▍ | 236/1189 [16:26<1:03:41, 4.01s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 237/1189 [16:30<1:02:43, 3.95s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 237/1189 [16:30<1:02:43, 3.95s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 237/1189 [16:30<1:02:43, 3.95s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 238/1189 [16:33<1:01:37, 3.89s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 238/1189 [16:33<1:01:37, 3.89s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▌ | 238/1189 [16:33<1:01:37, 3.89s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▋ | 239/1189 [16:37<1:00:28, 3.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|███████████████▋ | 239/1189 [16:37<1:00:28, 3.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▏ | 240/1189 [16:41<59:12, 3.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▏ | 240/1189 [16:41<59:12, 3.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▏ | 240/1189 [16:41<59:12, 3.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▏ | 241/1189 [16:44<57:53, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▏ | 241/1189 [16:44<57:53, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▏ | 241/1189 [16:44<57:53, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▎ | 242/1189 [16:47<55:58, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:42,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▎ | 242/1189 [16:47<55:58, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:42,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▎ | 243/1189 [16:50<53:46, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:42,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▎ | 243/1189 [16:50<53:46, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:42,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 20%|████████████████▎ | 243/1189 [16:50<53:46, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:42,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▍ | 244/1189 [16:53<51:04, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:48,359 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▍ | 244/1189 [16:53<51:04, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:48,359 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▍ | 245/1189 [16:56<48:04, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▍ | 245/1189 [16:56<48:04, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 246/1189 [16:58<44:46, 2.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 246/1189 [16:58<44:46, 2.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:37:54,047 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:37:54,047 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:37:55,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:37:55,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:37:57,405 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:37:57,405 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:37:59,213 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:37:59,213 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:37:59,213 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▉ | 251/1189 [17:11<47:22, 3.03s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▉ | 251/1189 [17:11<47:22, 3.03s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▉ | 251/1189 [17:11<47:22, 3.03s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▉ | 252/1189 [17:16<57:26, 3.68s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▉ | 252/1189 [17:16<57:26, 3.68s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▉ | 252/1189 [17:16<57:26, 3.68s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 253/1189 [17:21<1:04:03, 4.11s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 253/1189 [17:21<1:04:03, 4.11s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 253/1189 [17:21<1:04:03, 4.11s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 253/1189 [17:21<1:04:03, 4.11s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0302, 'learning_rate': 1.5e-05, 'epoch': 0.21} + 21%|████████████████▌ | 253/1189 [17:21<1:04:03, 4.11s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▌ | 253/1189 [17:21<1:04:03, 4.11s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▋ | 255/1189 [17:31<1:10:52, 4.55s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▋ | 255/1189 [17:31<1:10:52, 4.55s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 21%|████████████████▋ | 255/1189 [17:31<1:10:52, 4.55s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▊ | 256/1189 [17:36<1:13:09, 4.70s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▊ | 256/1189 [17:36<1:13:09, 4.70s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▊ | 256/1189 [17:36<1:13:09, 4.70s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▊ | 257/1189 [17:41<1:13:55, 4.76s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▊ | 257/1189 [17:41<1:13:55, 4.76s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▉ | 258/1189 [17:46<1:14:22, 4.79s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▉ | 258/1189 [17:46<1:14:22, 4.79s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4877, 'learning_rate': 1.524e-05, 'epoch': 0.22} + 22%|████████████████▉ | 259/1189 [17:51<1:14:44, 4.82s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|████████████████▉ | 259/1189 [17:51<1:14:44, 4.82s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.269, 'learning_rate': 1.53e-05, 'epoch': 0.22} + 22%|████████████████▉ | 259/1189 [17:51<1:14:44, 4.82s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████ | 260/1189 [17:56<1:15:09, 4.85s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████ | 260/1189 [17:56<1:15:09, 4.85s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████ | 261/1189 [18:01<1:15:10, 4.86s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████ | 261/1189 [18:01<1:15:10, 4.86s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2159, 'learning_rate': 1.542e-05, 'epoch': 0.22} + 22%|█████████████████ | 261/1189 [18:01<1:15:10, 4.86s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▏ | 262/1189 [18:05<1:14:40, 4.83s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▏ | 262/1189 [18:05<1:14:40, 4.83s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▏ | 262/1189 [18:05<1:14:40, 4.83s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▎ | 263/1189 [18:10<1:14:24, 4.82s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▎ | 263/1189 [18:10<1:14:24, 4.82s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▎ | 264/1189 [18:15<1:14:10, 4.81s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▎ | 264/1189 [18:15<1:14:10, 4.81s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3023, 'learning_rate': 1.56e-05, 'epoch': 0.22} + 22%|█████████████████▎ | 264/1189 [18:15<1:14:10, 4.81s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▍ | 265/1189 [18:20<1:13:43, 4.79s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▍ | 265/1189 [18:20<1:13:43, 4.79s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▍ | 265/1189 [18:20<1:13:43, 4.79s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▍ | 266/1189 [18:24<1:13:08, 4.75s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▍ | 266/1189 [18:24<1:13:08, 4.75s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▌ | 267/1189 [18:29<1:12:41, 4.73s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 22%|█████████████████▌ | 267/1189 [18:29<1:12:41, 4.73s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1519, 'learning_rate': 1.578e-05, 'epoch': 0.22} + 22%|█████████████████▌ | 267/1189 [18:29<1:12:41, 4.73s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▌ | 268/1189 [18:34<1:12:30, 4.72s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:39:32,100 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:39:32,100 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.188, 'learning_rate': 1.59e-05, 'epoch': 0.23} +[WARNING|modeling_utils.py:388] 2022-03-01 08:39:32,100 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▋ | 270/1189 [18:43<1:11:22, 4.66s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▋ | 270/1189 [18:43<1:11:22, 4.66s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1215, 'learning_rate': 1.596e-05, 'epoch': 0.23} + 23%|█████████████████▊ | 271/1189 [18:48<1:10:54, 4.63s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▊ | 271/1189 [18:48<1:10:54, 4.63s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4414, 'learning_rate': 1.6020000000000002e-05, 'epoch': 0.23} + 23%|█████████████████▊ | 272/1189 [18:52<1:10:10, 4.59s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▊ | 272/1189 [18:52<1:10:10, 4.59s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0973, 'learning_rate': 1.6080000000000002e-05, 'epoch': 0.23} + 23%|█████████████████▉ | 273/1189 [18:57<1:09:19, 4.54s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▉ | 273/1189 [18:57<1:09:19, 4.54s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1955, 'learning_rate': 1.614e-05, 'epoch': 0.23} + 23%|█████████████████▉ | 274/1189 [19:01<1:08:29, 4.49s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|█████████████████▉ | 274/1189 [19:01<1:08:29, 4.49s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.249, 'learning_rate': 1.62e-05, 'epoch': 0.23} + 23%|██████████████████ | 275/1189 [19:05<1:08:06, 4.47s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████ | 275/1189 [19:05<1:08:06, 4.47s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2878, 'learning_rate': 1.626e-05, 'epoch': 0.23} + 23%|██████████████████ | 275/1189 [19:05<1:08:06, 4.47s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████ | 276/1189 [19:10<1:07:29, 4.44s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████ | 276/1189 [19:10<1:07:29, 4.44s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▏ | 277/1189 [19:14<1:07:03, 4.41s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▏ | 277/1189 [19:14<1:07:03, 4.41s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0002, 'learning_rate': 1.6380000000000002e-05, 'epoch': 0.23} + 23%|██████████████████▏ | 278/1189 [19:18<1:06:09, 4.36s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▏ | 278/1189 [19:18<1:06:09, 4.36s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1866, 'learning_rate': 1.6440000000000002e-05, 'epoch': 0.23} + 23%|██████████████████▏ | 278/1189 [19:18<1:06:09, 4.36s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▎ | 279/1189 [19:23<1:05:33, 4.32s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 23%|██████████████████▎ | 279/1189 [19:23<1:05:33, 4.32s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▎ | 280/1189 [19:27<1:04:44, 4.27s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▎ | 280/1189 [19:27<1:04:44, 4.27s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1737, 'learning_rate': 1.656e-05, 'epoch': 0.24} + 24%|██████████████████▍ | 281/1189 [19:31<1:04:12, 4.24s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▍ | 281/1189 [19:31<1:04:12, 4.24s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1932, 'learning_rate': 1.6620000000000004e-05, 'epoch': 0.24} + 24%|██████████████████▍ | 282/1189 [19:35<1:03:08, 4.18s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▍ | 282/1189 [19:35<1:03:08, 4.18s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.307, 'learning_rate': 1.6680000000000003e-05, 'epoch': 0.24} + 24%|██████████████████▍ | 282/1189 [19:35<1:03:08, 4.18s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▌ | 283/1189 [19:39<1:02:12, 4.12s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▌ | 283/1189 [19:39<1:02:12, 4.12s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▌ | 283/1189 [19:39<1:02:12, 4.12s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▋ | 284/1189 [19:43<1:01:13, 4.06s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▋ | 284/1189 [19:43<1:01:13, 4.06s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██████████████████▋ | 284/1189 [19:43<1:01:13, 4.06s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▏ | 285/1189 [19:47<59:59, 3.98s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▏ | 285/1189 [19:47<59:59, 3.98s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▏ | 285/1189 [19:47<59:59, 3.98s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▏ | 286/1189 [19:50<59:02, 3.92s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▏ | 286/1189 [19:50<59:02, 3.92s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▏ | 286/1189 [19:50<59:02, 3.92s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▎ | 287/1189 [19:54<58:01, 3.86s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:40:51,269 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:40:51,269 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1832, 'learning_rate': 1.704e-05, 'epoch': 0.24} +[WARNING|modeling_utils.py:388] 2022-03-01 08:40:51,269 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▍ | 289/1189 [20:01<55:18, 3.69s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▍ | 289/1189 [20:01<55:18, 3.69s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▍ | 289/1189 [20:01<55:18, 3.69s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|██��████████████████▌ | 290/1189 [20:04<53:40, 3.58s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 24%|███████████████████▌ | 290/1189 [20:04<53:40, 3.58s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:01,197 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:01,197 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:01,197 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▋ | 292/1189 [20:10<48:42, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▋ | 292/1189 [20:10<48:42, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▋ | 293/1189 [20:13<45:35, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|███████████████████▋ | 293/1189 [20:13<45:35, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:09,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:09,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:11,198 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:11,198 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:13,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:13,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:14,896 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:14,896 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:16,435 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:16,435 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:19,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:19,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.7354, 'learning_rate': 1.776e-05, 'epoch': 0.25} +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:19,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:41:19,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▎ | 301/1189 [20:31<42:18, 2.86s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▎ | 301/1189 [20:31<42:18, 2.86s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▎ | 301/1189 [20:31<42:18, 2.86s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▎ | 302/1189 [20:36<52:02, 3.52s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▎ | 302/1189 [20:36<52:02, 3.52s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▎ | 302/1189 [20:36<52:02, 3.52s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▍ | 303/1189 [20:41<58:47, 3.98s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 25%|████████████████████▍ | 303/1189 [20:41<58:47, 3.98s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|███████████████████▉ | 304/1189 [20:46<1:03:29, 4.30s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|███████████████████▉ | 304/1189 [20:46<1:03:29, 4.30s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.8823, 'learning_rate': 1.8e-05, 'epoch': 0.26} + 26%|███████████████████▉ | 304/1189 [20:46<1:03:29, 4.30s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 305/1189 [20:51<1:06:42, 4.53s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 305/1189 [20:51<1:06:42, 4.53s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 306/1189 [20:56<1:08:49, 4.68s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 306/1189 [20:56<1:08:49, 4.68s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0446, 'learning_rate': 1.812e-05, 'epoch': 0.26} + 26%|████████████████████ | 306/1189 [20:56<1:08:49, 4.68s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████ | 306/1189 [20:56<1:08:49, 4.68s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2072, 'learning_rate': 1.818e-05, 'epoch': 0.26} + 26%|████████████████████ | 306/1189 [20:56<1:08:49, 4.68s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▏ | 308/1189 [21:06<1:10:10, 4.78s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▏ | 308/1189 [21:06<1:10:10, 4.78s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.9454, 'learning_rate': 1.824e-05, 'epoch': 0.26} + 26%|████████████████████▎ | 309/1189 [21:11<1:10:20, 4.80s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▎ | 309/1189 [21:11<1:10:20, 4.80s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.9268, 'learning_rate': 1.83e-05, 'epoch': 0.26} + 26%|████████████████████▎ | 309/1189 [21:11<1:10:20, 4.80s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▎ | 310/1189 [21:16<1:10:37, 4.82s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▎ | 310/1189 [21:16<1:10:37, 4.82s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▍ | 311/1189 [21:21<1:10:52, 4.84s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▍ | 311/1189 [21:21<1:10:52, 4.84s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.058, 'learning_rate': 1.842e-05, 'epoch': 0.26} + 26%|████████████████████▍ | 312/1189 [21:26<1:10:34, 4.83s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▍ | 312/1189 [21:26<1:10:34, 4.83s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0705, 'learning_rate': 1.848e-05, 'epoch': 0.26} + 26%|████████████████████▍ | 312/1189 [21:26<1:10:34, 4.83s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▌ | 313/1189 [21:30<1:10:01, 4.80s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▌ | 313/1189 [21:30<1:10:01, 4.80s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▌ | 314/1189 [21:35<1:09:40, 4.78s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▌ | 314/1189 [21:35<1:09:40, 4.78s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1257, 'learning_rate': 1.86e-05, 'epoch': 0.26} + 26%|████████████████████▋ | 315/1189 [21:40<1:09:18, 4.76s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 26%|████████████████████▋ | 315/1189 [21:40<1:09:18, 4.76s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0073, 'learning_rate': 1.866e-05, 'epoch': 0.26} + 27%|████████████████████▋ | 316/1189 [21:45<1:09:27, 4.77s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▋ | 316/1189 [21:45<1:09:27, 4.77s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3839, 'learning_rate': 1.872e-05, 'epoch': 0.27} + 27%|████████████████████▊ | 317/1189 [21:49<1:09:20, 4.77s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▊ | 317/1189 [21:49<1:09:20, 4.77s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3243, 'learning_rate': 1.878e-05, 'epoch': 0.27} + 27%|████████████████████▊ | 318/1189 [21:54<1:08:48, 4.74s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▊ | 318/1189 [21:54<1:08:48, 4.74s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2505, 'learning_rate': 1.884e-05, 'epoch': 0.27} + 27%|████████████████████▉ | 319/1189 [21:59<1:08:30, 4.72s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▉ | 319/1189 [21:59<1:08:30, 4.72s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0626, 'learning_rate': 1.8900000000000002e-05, 'epoch': 0.27} + 27%|████████████████████▉ | 320/1189 [22:03<1:08:15, 4.71s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|████████████████████▉ | 320/1189 [22:03<1:08:15, 4.71s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2428, 'learning_rate': 1.896e-05, 'epoch': 0.27} + 27%|█████████████████████ | 321/1189 [22:08<1:07:38, 4.68s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████ | 321/1189 [22:08<1:07:38, 4.68s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0947, 'learning_rate': 1.902e-05, 'epoch': 0.27} + 27%|█████████████████████ | 322/1189 [22:13<1:06:52, 4.63s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████ | 322/1189 [22:13<1:06:52, 4.63s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1172, 'learning_rate': 1.908e-05, 'epoch': 0.27} + 27%|█████████████████████▏ | 323/1189 [22:17<1:06:33, 4.61s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▏ | 323/1189 [22:17<1:06:33, 4.61s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.048, 'learning_rate': 1.914e-05, 'epoch': 0.27} + 27%|█████████████████████▏ | 323/1189 [22:17<1:06:33, 4.61s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▎ | 324/1189 [22:22<1:06:14, 4.59s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▎ | 324/1189 [22:22<1:06:14, 4.59s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▎ | 324/1189 [22:22<1:06:14, 4.59s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▎ | 325/1189 [22:26<1:05:51, 4.57s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▎ | 325/1189 [22:26<1:05:51, 4.57s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▎ | 325/1189 [22:26<1:05:51, 4.57s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▍ | 326/1189 [22:31<1:04:56, 4.52s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▍ | 326/1189 [22:31<1:04:56, 4.52s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 27%|█████████████████████▍ | 326/1189 [22:31<1:04:56, 4.52s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▍ | 327/1189 [22:35<1:04:18, 4.48s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▍ | 327/1189 [22:35<1:04:18, 4.48s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▌ | 328/1189 [22:39<1:03:50, 4.45s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▌ | 328/1189 [22:39<1:03:50, 4.45s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2394, 'learning_rate': 1.944e-05, 'epoch': 0.28} + 28%|█████████████████████▌ | 328/1189 [22:39<1:03:50, 4.45s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▌ | 329/1189 [22:44<1:03:06, 4.40s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▌ | 329/1189 [22:44<1:03:06, 4.40s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▌ | 329/1189 [22:44<1:03:06, 4.40s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▋ | 331/1189 [22:52<1:01:50, 4.32s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▋ | 331/1189 [22:52<1:01:50, 4.32s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▊ | 332/1189 [22:56<1:01:16, 4.29s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▊ | 332/1189 [22:56<1:01:16, 4.29s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2261, 'learning_rate': 1.968e-05, 'epoch': 0.28} + 28%|█████████████████████▊ | 332/1189 [22:56<1:01:16, 4.29s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▊ | 333/1189 [23:00<1:00:24, 4.23s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▊ | 333/1189 [23:00<1:00:24, 4.23s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|█████████████████████▊ | 333/1189 [23:00<1:00:24, 4.23s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▍ | 334/1189 [23:05<59:50, 4.20s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▍ | 334/1189 [23:05<59:50, 4.20s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▍ | 334/1189 [23:05<59:50, 4.20s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▌ | 335/1189 [23:09<58:51, 4.13s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▌ | 335/1189 [23:09<58:51, 4.13s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▌ | 335/1189 [23:09<58:51, 4.13s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▌ | 336/1189 [23:12<57:56, 4.08s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▌ | 336/1189 [23:12<57:56, 4.08s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▌ | 336/1189 [23:12<57:56, 4.08s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▋ | 337/1189 [23:16<56:53, 4.01s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▋ | 337/1189 [23:16<56:53, 4.01s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▋ | 337/1189 [23:16<56:53, 4.01s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▋ | 338/1189 [23:20<55:33, 3.92s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▋ | 338/1189 [23:20<55:33, 3.92s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 28%|██████████████████████▋ | 338/1189 [23:20<55:33, 3.92s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|██████████████████████▊ | 339/1189 [23:24<54:06, 3.82s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:44:20,747 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:44:20,747 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2188, 'learning_rate': 2.016e-05, 'epoch': 0.29} + 29%|██████████████████████▉ | 341/1189 [23:30<50:48, 3.60s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|██████████████████████▉ | 341/1189 [23:30<50:48, 3.60s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2795, 'learning_rate': 2.0220000000000003e-05, 'epoch': 0.29} + 29%|██████████████████████▉ | 341/1189 [23:30<50:48, 3.60s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|██████████████████���████ | 342/1189 [23:33<48:33, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:44:28,655 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████ | 343/1189 [23:36<46:07, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████ | 343/1189 [23:36<46:07, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████▏ | 344/1189 [23:39<43:30, 3.09s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 29%|███████████████████████▏ | 344/1189 [23:39<43:30, 3.09s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:44:35,142 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:44:35,142 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:44:37,387 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:44:37,387 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:44:39,373 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:44:41,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:44:41,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4257, 'learning_rate': 2.0580000000000003e-05, 'epoch': 0.29} +[WARNING|modeling_utils.py:388] 2022-03-01 08:44:42,622 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:44:42,622 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.857, 'learning_rate': 2.07e-05, 'epoch': 0.29} +[WARNING|modeling_utils.py:388] 2022-03-01 08:44:44,400 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:44:44,400 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▌ | 351/1189 [23:56<41:41, 2.99s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▌ | 351/1189 [23:56<41:41, 2.99s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4633, 'learning_rate': 2.082e-05, 'epoch': 0.3} + 30%|███████████████████████▌ | 351/1189 [23:56<41:41, 2.99s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▋ | 352/1189 [24:01<50:47, 3.64s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▋ | 352/1189 [24:01<50:47, 3.64s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▊ | 353/1189 [24:06<56:36, 4.06s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▊ | 353/1189 [24:06<56:36, 4.06s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.14, 'learning_rate': 2.094e-05, 'epoch': 0.3} + 30%|███████████████████████▊ | 353/1189 [24:06<56:36, 4.06s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▏ | 354/1189 [24:11<1:00:08, 4.32s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▏ | 354/1189 [24:11<1:00:08, 4.32s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▏ | 354/1189 [24:11<1:00:08, 4.32s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▎ | 355/1189 [24:16<1:02:34, 4.50s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▎ | 355/1189 [24:16<1:02:34, 4.50s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▎ | 355/1189 [24:16<1:02:34, 4.50s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▎ | 356/1189 [24:21<1:04:39, 4.66s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▎ | 356/1189 [24:21<1:04:39, 4.66s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|████████████████��██████▍ | 357/1189 [24:26<1:05:44, 4.74s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▍ | 357/1189 [24:26<1:05:44, 4.74s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2986, 'learning_rate': 2.118e-05, 'epoch': 0.3} + 30%|███████████████████████▍ | 358/1189 [24:31<1:06:28, 4.80s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▍ | 358/1189 [24:31<1:06:28, 4.80s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0543, 'learning_rate': 2.124e-05, 'epoch': 0.3} + 30%|███████████████████████▍ | 358/1189 [24:31<1:06:28, 4.80s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▌ | 359/1189 [24:36<1:06:50, 4.83s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▌ | 359/1189 [24:36<1:06:50, 4.83s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▌ | 360/1189 [24:41<1:06:59, 4.85s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▌ | 360/1189 [24:41<1:06:59, 4.85s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3371, 'learning_rate': 2.136e-05, 'epoch': 0.3} + 30%|███████████████████████▌ | 360/1189 [24:41<1:06:59, 4.85s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▋ | 361/1189 [24:46<1:06:38, 4.83s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▋ | 361/1189 [24:46<1:06:38, 4.83s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▋ | 361/1189 [24:46<1:06:38, 4.83s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▋ | 362/1189 [24:50<1:06:06, 4.80s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 30%|███████████████████████▋ | 362/1189 [24:50<1:06:06, 4.80s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|██████████████████���████▊ | 363/1189 [24:55<1:05:38, 4.77s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|███████████████████████▊ | 363/1189 [24:55<1:05:38, 4.77s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.126, 'learning_rate': 2.154e-05, 'epoch': 0.31} + 31%|███████████████████████▉ | 364/1189 [25:00<1:05:33, 4.77s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|███████████████████████▉ | 364/1189 [25:00<1:05:33, 4.77s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2623, 'learning_rate': 2.16e-05, 'epoch': 0.31} + 31%|███████████████████████▉ | 364/1189 [25:00<1:05:33, 4.77s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|███████████████████████▉ | 365/1189 [25:05<1:05:16, 4.75s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|███████████████████████▉ | 365/1189 [25:05<1:05:16, 4.75s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████ | 366/1189 [25:09<1:04:45, 4.72s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████ | 366/1189 [25:09<1:04:45, 4.72s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1573, 'learning_rate': 2.172e-05, 'epoch': 0.31} + 31%|████████████████████████ | 367/1189 [25:14<1:04:17, 4.69s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████ | 367/1189 [25:14<1:04:17, 4.69s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0573, 'learning_rate': 2.178e-05, 'epoch': 0.31} + 31%|████████████████████████ | 367/1189 [25:14<1:04:17, 4.69s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████ | 367/1189 [25:14<1:04:17, 4.69s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4715, 'learning_rate': 2.184e-05, 'epoch': 0.31} +[WARNING|modeling_utils.py:388] 2022-03-01 08:46:16,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:46:16,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:46:16,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3253, 'learning_rate': 2.19e-05, 'epoch': 0.31} + 31%|████████████████████████▎ | 370/1189 [25:28<1:03:00, 4.62s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▎ | 370/1189 [25:28<1:03:00, 4.62s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2055, 'learning_rate': 2.196e-05, 'epoch': 0.31} + 31%|████████████████████████▎ | 371/1189 [25:32<1:02:49, 4.61s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▎ | 371/1189 [25:32<1:02:49, 4.61s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1163, 'learning_rate': 2.202e-05, 'epoch': 0.31} + 31%|████████████████████████▍ | 372/1189 [25:37<1:02:10, 4.57s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▍ | 372/1189 [25:37<1:02:10, 4.57s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0746, 'learning_rate': 2.208e-05, 'epoch': 0.31} + 31%|████████████████████████▍ | 373/1189 [25:41<1:01:50, 4.55s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▍ | 373/1189 [25:41<1:01:50, 4.55s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0822, 'learning_rate': 2.214e-05, 'epoch': 0.31} + 31%|████████████████████████▍ | 373/1189 [25:41<1:01:50, 4.55s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▌ | 374/1189 [25:46<1:01:26, 4.52s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▌ | 374/1189 [25:46<1:01:26, 4.52s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 31%|████████████████████████▌ | 374/1189 [25:46<1:01:26, 4.52s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|████████████████████████▌ | 375/1189 [25:50<1:00:54, 4.49s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|████████████████████████▌ | 375/1189 [25:50<1:00:54, 4.49s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|████████████████████████▌ | 375/1189 [25:50<1:00:54, 4.49s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|████████████████████████▋ | 376/1189 [25:54<1:00:17, 4.45s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|████████████████████████▋ | 376/1189 [25:54<1:00:17, 4.45s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|████████████████████████▋ | 376/1189 [25:54<1:00:17, 4.45s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▎ | 377/1189 [25:59<59:39, 4.41s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▎ | 377/1189 [25:59<59:39, 4.41s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▎ | 377/1189 [25:59<59:39, 4.41s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▍ | 378/1189 [26:03<58:50, 4.35s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▍ | 378/1189 [26:03<58:50, 4.35s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▍ | 378/1189 [26:03<58:50, 4.35s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▌ | 379/1189 [26:07<58:29, 4.33s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▌ | 379/1189 [26:07<58:29, 4.33s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▌ | 380/1189 [26:11<58:04, 4.31s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▌ | 380/1189 [26:11<58:04, 4.31s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2768, 'learning_rate': 2.256e-05, 'epoch': 0.32} + 32%|█████████████████████████▌ | 380/1189 [26:11<58:04, 4.31s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▋ | 381/1189 [26:16<57:19, 4.26s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▋ | 381/1189 [26:16<57:19, 4.26s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▋ | 381/1189 [26:16<57:19, 4.26s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▋ | 382/1189 [26:20<56:40, 4.21s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▋ | 382/1189 [26:20<56:40, 4.21s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▋ | 382/1189 [26:20<56:40, 4.21s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▊ | 383/1189 [26:24<55:27, 4.13s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▊ | 383/1189 [26:24<55:27, 4.13s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▊ | 383/1189 [26:24<55:27, 4.13s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▊ | 384/1189 [26:28<54:42, 4.08s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▊ | 384/1189 [26:28<54:42, 4.08s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▊ | 384/1189 [26:28<54:42, 4.08s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▉ | 385/1189 [26:31<53:48, 4.02s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▉ | 385/1189 [26:31<53:48, 4.02s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▉ | 385/1189 [26:31<53:48, 4.02s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▉ | 386/1189 [26:35<53:13, 3.98s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▉ | 386/1189 [26:35<53:13, 3.98s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 32%|█████████████████████████▉ | 386/1189 [26:35<53:13, 3.98s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████ | 387/1189 [26:39<52:07, 3.90s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████ | 387/1189 [26:39<52:07, 3.90s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████ | 388/1189 [26:43<50:51, 3.81s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████ | 388/1189 [26:43<50:51, 3.81s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:47:39,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:47:39,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.365, 'learning_rate': 2.3100000000000002e-05, 'epoch': 0.33} +[WARNING|modeling_utils.py:388] 2022-03-01 08:47:39,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▏ | 390/1189 [26:50<48:03, 3.61s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▏ | 390/1189 [26:50<48:03, 3.61s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▏ | 390/1189 [26:50<48:03, 3.61s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▎ | 391/1189 [26:53<46:08, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:47,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▍ | 392/1189 [26:56<43:53, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:47,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▍ | 392/1189 [26:56<43:53, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:47,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:47:51,989 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:47:47,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:47:51,989 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:47:47,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2523, 'learning_rate': 2.334e-05, 'epoch': 0.33} +[WARNING|modeling_utils.py:388] 2022-03-01 08:47:51,989 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:47:47,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▌ | 394/1189 [27:01<39:09, 2.96s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:55,780 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▌ | 395/1189 [27:03<36:39, 2.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:57,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▌ | 395/1189 [27:03<36:39, 2.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:57,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▋ | 396/1189 [27:05<33:45, 2.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:59,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▋ | 396/1189 [27:05<33:45, 2.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:59,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▊ | 398/1189 [27:09<27:55, 2.12s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:01,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 33%|██████████████████████████▊ | 398/1189 [27:09<27:55, 2.12s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:01,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4165, 'learning_rate': 2.358e-05, 'epoch': 0.33} + 34%|██████████████████████████▊ | 399/1189 [27:10<25:02, 1.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:04,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▊ | 399/1189 [27:10<25:02, 1.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:04,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▉ | 400/1189 [27:12<24:25, 1.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:04,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▉ | 400/1189 [27:12<24:25, 1.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:04,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▉ | 400/1189 [27:12<24:25, 1.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▉ | 401/1189 [27:17<38:44, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▉ | 401/1189 [27:17<38:44, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0445, 'learning_rate': 2.3820000000000002e-05, 'epoch': 0.34} + 34%|███████████████████████████ | 402/1189 [27:22<47:17, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████ | 402/1189 [27:22<47:17, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1595, 'learning_rate': 2.3880000000000002e-05, 'epoch': 0.34} + 34%|███████████████████████████ | 403/1189 [27:28<52:58, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████ | 403/1189 [27:28<52:58, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1869, 'learning_rate': 2.394e-05, 'epoch': 0.34} + 34%|███████████████████████████ | 403/1189 [27:28<52:58, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▏ | 404/1189 [27:33<56:38, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▏ | 404/1189 [27:33<56:38, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▏ | 404/1189 [27:33<56:38, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▏ | 404/1189 [27:33<56:38, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1379, 'learning_rate': 2.4060000000000003e-05, 'epoch': 0.34} + 34%|███████████████████████████▏ | 404/1189 [27:33<56:38, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|███████████████████████████▏ | 404/1189 [27:33<56:38, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▋ | 406/1189 [27:42<1:00:46, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▋ | 406/1189 [27:42<1:00:46, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▋ | 407/1189 [27:47<1:01:58, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▋ | 407/1189 [27:47<1:01:58, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0632, 'learning_rate': 2.4180000000000002e-05, 'epoch': 0.34} + 34%|██████████████████████████▋ | 407/1189 [27:47<1:01:58, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▊ | 408/1189 [27:52<1:02:43, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▊ | 408/1189 [27:52<1:02:43, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▊ | 408/1189 [27:52<1:02:43, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▊ | 409/1189 [27:57<1:02:52, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▊ | 409/1189 [27:57<1:02:52, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▊ | 409/1189 [27:57<1:02:52, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▉ | 410/1189 [28:02<1:02:57, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▉ | 410/1189 [28:02<1:02:57, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 34%|██████████████████████████▉ | 410/1189 [28:02<1:02:57, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|██████████████████████████▉ | 411/1189 [28:07<1:02:55, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|██████████████████████████▉ | 411/1189 [28:07<1:02:55, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + [WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + [WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2136, 'learning_rate': 2.448e-05, 'epoch': 0.35} +[WARNING|modeling_utils.py:388] 2022-03-01 08:49:10,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:49:10,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2112, 'learning_rate': 2.454e-05, 'epoch': 0.35} +[WARNING|modeling_utils.py:388] 2022-03-01 08:49:10,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▏ | 414/1189 [28:21<1:01:43, 4.78s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▏ | 414/1189 [28:21<1:01:43, 4.78s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▏ | 414/1189 [28:21<1:01:43, 4.78s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▏ | 415/1189 [28:26<1:01:36, 4.78s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▏ | 415/1189 [28:26<1:01:36, 4.78s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▎ | 416/1189 [28:31<1:01:14, 4.75s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▎ | 416/1189 [28:31<1:01:14, 4.75s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2702, 'learning_rate': 2.472e-05, 'epoch': 0.35} + 35%|███████████████████████████▎ | 417/1189 [28:35<1:00:59, 4.74s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▎ | 417/1189 [28:35<1:00:59, 4.74s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.9489, 'learning_rate': 2.478e-05, 'epoch': 0.35} + 35%|███████████████████████████▎ | 417/1189 [28:35<1:00:59, 4.74s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|███████████████████████████▍ | 418/1189 [28:40<1:00:12, 4.69s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████���██████████▍ | 418/1189 [28:40<1:00:12, 4.69s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▏ | 419/1189 [28:45<59:50, 4.66s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▏ | 419/1189 [28:45<59:50, 4.66s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2809, 'learning_rate': 2.49e-05, 'epoch': 0.35} + 35%|████████████████████████████▎ | 420/1189 [28:49<59:12, 4.62s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▎ | 420/1189 [28:49<59:12, 4.62s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.176, 'learning_rate': 2.4959999999999998e-05, 'epoch': 0.35} + 35%|████████████████████████████▎ | 421/1189 [28:54<58:50, 4.60s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▎ | 421/1189 [28:54<58:50, 4.60s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1256, 'learning_rate': 2.502e-05, 'epoch': 0.35} + 35%|████████████████████████████▍ | 422/1189 [28:58<58:24, 4.57s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 35%|████████████████████████████▍ | 422/1189 [28:58<58:24, 4.57s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2436, 'learning_rate': 2.508e-05, 'epoch': 0.35} + 35%|████████████████████████████▍ | 422/1189 [28:58<58:24, 4.57s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▍ | 423/1189 [29:03<58:14, 4.56s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▍ | 423/1189 [29:03<58:14, 4.56s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▌ | 424/1189 [29:07<57:36, 4.52s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▌ | 424/1189 [29:07<57:36, 4.52s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1591, 'learning_rate': 2.52e-05, 'epoch': 0.36} + 36%|████████████████████████████▌ | 425/1189 [29:12<56:57, 4.47s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▌ | 425/1189 [29:12<56:57, 4.47s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.4836, 'learning_rate': 2.526e-05, 'epoch': 0.36} + 36%|████████████████████████████▋ | 426/1189 [29:16<56:14, 4.42s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▋ | 426/1189 [29:16<56:14, 4.42s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1937, 'learning_rate': 2.5319999999999998e-05, 'epoch': 0.36} + 36%|████████████████████████████▋ | 427/1189 [29:20<55:56, 4.40s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▋ | 427/1189 [29:20<55:56, 4.40s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1032, 'learning_rate': 2.538e-05, 'epoch': 0.36} + 36%|████████████████████████████▊ | 428/1189 [29:25<55:31, 4.38s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▊ | 428/1189 [29:25<55:31, 4.38s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1523, 'learning_rate': 2.544e-05, 'epoch': 0.36} + 36%|████████████████████████████▊ | 429/1189 [29:29<55:20, 4.37s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▊ | 429/1189 [29:29<55:20, 4.37s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.419, 'learning_rate': 2.55e-05, 'epoch': 0.36} + 36%|████████████████████████████▊ | 429/1189 [29:29<55:20, 4.37s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▊ | 429/1189 [29:29<55:20, 4.37s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3495, 'learning_rate': 2.556e-05, 'epoch': 0.36} + 36%|████████████████████████████▊ | 429/1189 [29:29<55:20, 4.37s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▉ | 431/1189 [29:37<54:34, 4.32s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▉ | 431/1189 [29:37<54:34, 4.32s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|████████████████████████████▉ | 431/1189 [29:37<54:34, 4.32s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|█████████████████████████████ | 432/1189 [29:42<53:53, 4.27s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|█████████████████████████████ | 432/1189 [29:42<53:53, 4.27s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|█████████████████████████████ | 432/1189 [29:42<53:53, 4.27s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|█████████████████████████████▏ | 433/1189 [29:46<53:14, 4.23s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|█████████████████████████████▏ | 433/1189 [29:46<53:14, 4.23s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 36%|█████████████████████████████▏ | 433/1189 [29:46<53:14, 4.23s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▏ | 434/1189 [29:50<52:26, 4.17s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▏ | 434/1189 [29:50<52:26, 4.17s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▏ | 434/1189 [29:50<52:26, 4.17s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▎ | 435/1189 [29:54<51:27, 4.09s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▎ | 435/1189 [29:54<51:27, 4.09s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▎ | 435/1189 [29:54<51:27, 4.09s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▎ | 436/1189 [29:58<50:30, 4.02s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▎ | 436/1189 [29:58<50:30, 4.02s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▎ | 436/1189 [29:58<50:30, 4.02s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▍ | 437/1189 [30:01<49:22, 3.94s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▍ | 437/1189 [30:01<49:22, 3.94s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▍ | 437/1189 [30:01<49:22, 3.94s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▍ | 438/1189 [30:05<48:06, 3.84s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:51:02,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:51:02,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3237, 'learning_rate': 2.61e-05, 'epoch': 0.37} +[WARNING|modeling_utils.py:388] 2022-03-01 08:51:02,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▌ | 440/1189 [30:12<45:19, 3.63s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▌ | 440/1189 [30:12<45:19, 3.63s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▌ | 440/1189 [30:12<45:19, 3.63s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▋ | 441/1189 [30:15<43:35, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:10,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▋ | 441/1189 [30:15<43:35, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:10,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▋ | 442/1189 [30:18<41:49, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:10,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:51:14,545 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:51:10,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:51:14,545 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:51:10,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1628, 'learning_rate': 2.6340000000000002e-05, 'epoch': 0.37} +[WARNING|modeling_utils.py:388] 2022-03-01 08:51:14,545 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:51:10,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▊ | 444/1189 [30:24<37:50, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:18,446 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▊ | 444/1189 [30:24<37:50, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:18,446 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▉ | 445/1189 [30:26<35:27, 2.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:20,759 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 37%|█████████████████████████████▉ | 445/1189 [30:26<35:27, 2.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:20,759 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████ | 446/1189 [30:28<32:40, 2.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:22,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████ | 446/1189 [30:28<32:40, 2.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:22,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████ | 447/1189 [30:30<30:01, 2.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:24,618 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████ | 447/1189 [30:30<30:01, 2.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:24,618 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▏ | 448/1189 [30:32<27:19, 2.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:26,205 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▏ | 448/1189 [30:32<27:19, 2.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:26,205 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▎ | 450/1189 [30:35<23:49, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:27,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▎ | 450/1189 [30:35<23:49, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:27,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▎ | 450/1189 [30:35<23:49, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██���███████████████████████████▎ | 450/1189 [30:35<23:49, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▎ | 451/1189 [30:40<36:40, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▎ | 451/1189 [30:40<36:40, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▎ | 451/1189 [30:40<36:40, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▎ | 451/1189 [30:40<36:40, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0877, 'learning_rate': 2.688e-05, 'epoch': 0.38} + 38%|██████████████████████████████▎ | 451/1189 [30:40<36:40, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▎ | 451/1189 [30:40<36:40, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▍ | 453/1189 [30:51<49:45, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▍ | 453/1189 [30:51<49:45, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▌ | 454/1189 [30:56<53:17, 4.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▌ | 454/1189 [30:56<53:17, 4.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2176, 'learning_rate': 2.7000000000000002e-05, 'epoch': 0.38} + 38%|██████████████████████████████▌ | 454/1189 [30:56<53:17, 4.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▌ | 455/1189 [31:01<55:17, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▌ | 455/1189 [31:01<55:17, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▌ | 455/1189 [31:01<55:17, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▋ | 456/1189 [31:06<56:47, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▋ | 456/1189 [31:06<56:47, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▋ | 456/1189 [31:06<56:47, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▋ | 457/1189 [31:10<57:25, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▋ | 457/1189 [31:10<57:25, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 38%|██████████████████████████████▋ | 457/1189 [31:10<57:25, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|██████████████████████████████▊ | 458/1189 [31:15<57:55, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|██████████████████████████████▊ | 458/1189 [31:15<57:55, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|██████████████████████████████▉ | 459/1189 [31:20<58:13, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|██████████████████████████████▉ | 459/1189 [31:20<58:13, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1156, 'learning_rate': 2.7300000000000003e-05, 'epoch': 0.39} + 39%|██████████████████████████████▉ | 460/1189 [31:25<58:04, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|██████████████████████████████▉ | 460/1189 [31:25<58:04, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2531, 'learning_rate': 2.7360000000000002e-05, 'epoch': 0.39} + 39%|██████████████████████████████▉ | 460/1189 [31:25<58:04, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████ | 461/1189 [31:30<57:53, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|█████��█████████████████████████ | 461/1189 [31:30<57:53, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████ | 462/1189 [31:34<57:45, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████ | 462/1189 [31:34<57:45, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2243, 'learning_rate': 2.748e-05, 'epoch': 0.39} + 39%|███████████████████████████████▏ | 463/1189 [31:39<57:52, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▏ | 463/1189 [31:39<57:52, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1874, 'learning_rate': 2.754e-05, 'epoch': 0.39} + 39%|███████████████████████████████▏ | 463/1189 [31:39<57:52, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▏ | 463/1189 [31:39<57:52, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▏ | 464/1189 [31:44<57:38, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▏ | 464/1189 [31:44<57:38, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▎ | 465/1189 [31:49<57:22, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▎ | 465/1189 [31:49<57:22, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3213, 'learning_rate': 2.7660000000000003e-05, 'epoch': 0.39} + 39%|███████████████████████████████▎ | 466/1189 [31:53<56:57, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▎ | 466/1189 [31:53<56:57, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0718, 'learning_rate': 2.7720000000000002e-05, 'epoch': 0.39} + 39%|███████████████████████████████▍ | 467/1189 [31:58<56:35, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|██████████████���████████████████▍ | 467/1189 [31:58<56:35, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2087, 'learning_rate': 2.778e-05, 'epoch': 0.39} + 39%|███████████████████████████████▍ | 468/1189 [32:03<56:12, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▍ | 468/1189 [32:03<56:12, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2517, 'learning_rate': 2.784e-05, 'epoch': 0.39} + 39%|███████████████████████████████▌ | 469/1189 [32:07<55:51, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 39%|███████████████████████████████▌ | 469/1189 [32:07<55:51, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0324, 'learning_rate': 2.79e-05, 'epoch': 0.39} + 40%|███████████████████████████████▌ | 470/1189 [32:12<55:22, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▌ | 470/1189 [32:12<55:22, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3931, 'learning_rate': 2.7960000000000003e-05, 'epoch': 0.4} + 40%|███████████████████████████████▌ | 470/1189 [32:12<55:22, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▌ | 470/1189 [32:12<55:22, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2216, 'learning_rate': 2.8020000000000003e-05, 'epoch': 0.4} + 40%|███████████████████████████████▌ | 470/1189 [32:12<55:22, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▌ | 470/1189 [32:12<55:22, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▊ | 472/1189 [32:21<54:43, 4.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▊ | 472/1189 [32:21<54:43, 4.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▊ | 473/1189 [32:25<54:16, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|█��█████████████████████████████▊ | 473/1189 [32:25<54:16, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 3.9645, 'learning_rate': 2.8139999999999998e-05, 'epoch': 0.4} + 40%|███████████████████████████████▉ | 474/1189 [32:30<53:57, 4.53s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▉ | 474/1189 [32:30<53:57, 4.53s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.306, 'learning_rate': 2.8199999999999998e-05, 'epoch': 0.4} + 40%|███████████████████████████████▉ | 475/1189 [32:34<53:19, 4.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|███████████████████████████████▉ | 475/1189 [32:34<53:19, 4.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3816, 'learning_rate': 2.826e-05, 'epoch': 0.4} + 40%|████████████████████████████████ | 476/1189 [32:39<52:54, 4.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████ | 476/1189 [32:39<52:54, 4.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3026, 'learning_rate': 2.832e-05, 'epoch': 0.4} + 40%|████████████████████████████████ | 477/1189 [32:43<52:24, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████ | 477/1189 [32:43<52:24, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.0065, 'learning_rate': 2.838e-05, 'epoch': 0.4} + 40%|████████████████████████████████▏ | 478/1189 [32:47<51:47, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▏ | 478/1189 [32:47<51:47, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.2526, 'learning_rate': 2.844e-05, 'epoch': 0.4} + 40%|████████████████████████████████▏ | 478/1189 [32:47<51:47, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▏ | 479/1189 [32:51<51:16, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▏ | 479/1189 [32:51<51:16, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▏ | 479/1189 [32:51<51:16, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▎ | 480/1189 [32:56<50:38, 4.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▎ | 480/1189 [32:56<50:38, 4.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▎ | 480/1189 [32:56<50:38, 4.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▎ | 481/1189 [33:00<50:13, 4.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▎ | 481/1189 [33:00<50:13, 4.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 40%|████████████████████████████████▎ | 481/1189 [33:00<50:13, 4.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▍ | 482/1189 [33:04<49:38, 4.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▍ | 482/1189 [33:04<49:38, 4.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▍ | 482/1189 [33:04<49:38, 4.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▍ | 483/1189 [33:08<49:07, 4.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▍ | 483/1189 [33:08<49:07, 4.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▍ | 483/1189 [33:08<49:07, 4.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▌ | 484/1189 [33:12<48:08, 4.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▌ | 484/1189 [33:12<48:08, 4.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▌ | 484/1189 [33:12<48:08, 4.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▋ | 485/1189 [33:16<47:36, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▋ | 485/1189 [33:16<47:36, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▋ | 485/1189 [33:16<47:36, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▋ | 486/1189 [33:20<46:51, 4.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▋ | 486/1189 [33:20<46:51, 4.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▋ | 486/1189 [33:20<46:51, 4.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▊ | 487/1189 [33:23<46:10, 3.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▊ | 487/1189 [33:23<46:10, 3.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▊ | 487/1189 [33:23<46:10, 3.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▊ | 488/1189 [33:27<45:21, 3.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▊ | 488/1189 [33:27<45:21, 3.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▊ | 488/1189 [33:27<45:21, 3.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|████████████████████████████████▉ | 489/1189 [33:31<44:24, 3.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|█████████████████████████��██████▉ | 489/1189 [33:31<44:24, 3.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:54:28,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:54:28,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:54:28,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|█████████████████████████████████ | 491/1189 [33:38<41:44, 3.59s/it]g-point operations will not be computed-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|█████████████████████████████████ | 491/1189 [33:38<41:44, 3.59s/it]g-point operations will not be computed-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.1793, 'learning_rate': 2.928e-05, 'epoch': 0.41} + 41%|█████████████████████████████████ | 492/1189 [33:41<40:11, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:36,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|█████████████████████████████████ | 492/1189 [33:41<40:11, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:36,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 41%|█████████████████████████████████▏ | 493/1189 [33:44<38:27, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:36,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:54:40,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:54:36,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[WARNING|modeling_utils.py:388] 2022-03-01 08:54:40,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:54:36,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.3125, 'learning_rate': 2.94e-05, 'epoch': 0.42} +[WARNING|modeling_utils.py:388] 2022-03-01 08:54:40,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:54:36,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|█████████████████████████████████▎ | 495/1189 [33:49<34:00, 2.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:43,886 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|█████████████████████████████████▎ | 495/1189 [33:49<34:00, 2.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:43,886 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|█████████████████████████████████▎ | 496/1189 [33:51<31:40, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:45,976 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|█████████████████████████████████▎ | 496/1189 [33:51<31:40, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:45,976 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|█████████████████████████████████▌ | 498/1189 [33:55<25:53, 2.25s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:47,775 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|█████████████████████████████████▌ | 498/1189 [33:55<25:53, 2.25s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:47,775 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +{'loss': 4.5546, 'learning_rate': 2.964e-05, 'epoch': 0.42} + 42%|█████████████████████████████████▌ | 499/1189 [33:56<23:13, 2.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:50,710 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed + 42%|█████████████████████████████████▌ | 499/1189 [33:56<23:13, 2.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:50,710 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed +[INFO|trainer.py:2366] 2022-03-01 08:54:51,982 >> Num examples = 2642 | 500/1189 [33:58<22:27, 1.96s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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] 2022-03-01 08:54:51,982 >> Num examples = 2642 | 500/1189 [33:58<22:27, 1.96s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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] 2022-03-01 08:54:51,982 >> Num examples = 2642 | 500/1189 [33:58<22:27, 1.96s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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] 2022-03-01 08:54:51,982 >> Num examples = 2642 | 500/1189 [33:58<22:27, 1.96s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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<08:52, 2.45s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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<09:32, 2.65s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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<10:18, 2.87s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [00:18<11:16, 3.16s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [00:21<11:01, 3.11s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [00:24<10:49, 3.07s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [00:28<11:44, 3.34s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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<12:39, 3.62s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [00:35<11:50, 3.40s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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<11:31, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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<11:37, 3.37s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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<13:04, 3.81s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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<13:59, 4.09s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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<13:16, 3.91s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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<13:02, 3.86s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:02<12:24, 3.69s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:05<11:45, 3.51s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:08<11:00, 3.30s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:11<10:47, 3.25s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:14<10:31, 3.19s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:18<11:03, 3.37s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:22<11:38, 3.56s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:26<11:52, 3.65s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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<10:48, 3.34s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:32<11:19, 3.52s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:37<12:02, 3.76s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:40<11:16, 3.54s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:42<10:19, 3.26s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:46<10:16, 3.26s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:49<10:41, 3.41s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:53<10:47, 3.46s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:56<10:22, 3.35s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [01:59<10:11, 3.31s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:04<11:00, 3.59s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:07<10:20, 3.39s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:10<10:37, 3.50s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:13<10:01, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:17<10:12, 3.40s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:21<11:08, 3.74s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:25<10:38, 3.59s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:29<11:39, 3.95s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:34<12:10, 4.15s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:38<12:06, 4.15s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:42<11:55, 4.11s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:46<11:50, 4.11s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:50<11:24, 3.98s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:54<11:24, 4.01s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [02:57<10:44, 3.79s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:00<09:59, 3.55s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:03<09:23, 3.35s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:07<09:36, 3.45s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:10<09:41, 3.50s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:15<10:29, 3.81s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:19<10:30, 3.85s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:22<10:09, 3.74s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:26<09:37, 3.56s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:28<08:49, 3.29s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:32<09:02, 3.39s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:35<08:47, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:35<08:47, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:35<08:47, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:42<08:46, 3.35s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:45<08:38, 3.33s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:49<08:48, 3.41s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:51<08:15, 3.22s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:55<08:52, 3.48s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [03:59<08:33, 3.38s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:02<08:27, 3.36s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:05<08:16, 3.31s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:08<07:48, 3.14s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:12<08:06, 3.29s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:15<07:59, 3.26s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:18<07:55, 3.25s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:21<07:49, 3.24s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:24<07:46, 3.24s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:28<07:53, 3.31s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:28<07:53, 3.31s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:28<07:53, 3.31s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:34<07:34, 3.22s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:38<07:56, 3.40s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:42<08:27, 3.65s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:46<08:50, 3.85s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:50<08:53, 3.89s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:55<09:14, 4.07s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [04:59<08:53, 3.95s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:03<09:09, 4.10s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:06<08:33, 3.86s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:10<08:03, 3.66s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:13<08:00, 3.67s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:17<08:15, 3.81s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:22<08:32, 3.98s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:26<08:40, 4.06s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:30<08:24, 3.97s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:34<08:23, 3.99s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:38<08:09, 3.91s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:42<08:20, 4.04s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:46<08:07, 3.97s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:48<07:21, 3.62s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:52<07:20, 3.64s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:55<06:59, 3.49s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [05:58<06:36, 3.33s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:02<06:54, 3.51s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:06<07:03, 3.62s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:10<07:25, 3.84s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:14<07:25, 3.88s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:18<06:56, 3.66s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:22<07:13, 3.84s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:26<07:16, 3.90s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:29<06:54, 3.74s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:32<06:35, 3.59s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:36<06:40, 3.67s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:40<06:35, 3.66s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:43<06:19, 3.55s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:47<06:14, 3.54s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:50<06:01, 3.44s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:53<05:55, 3.42s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [06:57<06:03, 3.53s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:01<06:24, 3.77s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:06<06:38, 3.94s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:09<06:24, 3.85s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:12<05:39, 3.43s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:14<05:06, 3.12s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:17<05:01, 3.11s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:21<05:18, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:24<05:00, 3.16s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:27<04:46, 3.05s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:29<04:28, 2.89s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:33<04:49, 3.14s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:36<04:34, 3.02s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:39<04:48, 3.21s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:42<04:28, 3.01s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:45<04:27, 3.04s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:48<04:16, 2.94s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:51<04:21, 3.05s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:55<04:36, 3.26s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [07:58<04:38, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:02<04:47, 3.47s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:06<04:49, 3.54s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:08<04:20, 3.22s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:11<04:17, 3.21s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:15<04:10, 3.17s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:17<03:50, 2.96s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:21<04:08, 3.23s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:24<04:03, 3.20s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:28<04:11, 3.35s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:30<03:54, 3.16s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:34<03:52, 3.18s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:37<03:51, 3.21s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:40<03:47, 3.20s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:44<03:56, 3.37s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:47<03:49, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:50<03:43, 3.28s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:54<03:44, 3.35s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [08:57<03:42, 3.37s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:01<03:42, 3.42s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:03<03:25, 3.21s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:08<03:48, 3.63s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:12<03:47, 3.66s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:16<03:50, 3.79s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:20<03:54, 3.91s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:24<03:51, 3.92s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:28<03:55, 4.05s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:33<03:59, 4.20s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:36<03:44, 4.01s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:40<03:25, 3.73s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:43<03:18, 3.67s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:46<03:04, 3.48s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:50<03:06, 3.58s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:54<03:05, 3.63s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [09:57<03:02, 3.64s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:01<02:52, 3.52s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:04<02:48, 3.50s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:07<02:39, 3.40s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:10<02:32, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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%|████████████████████████████████████████████████████████████████▌ | 176/221 [10:14<02:36, 3.48s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:17<02:25, 3.31s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:21<02:29, 3.48s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:24<02:23, 3.42s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:28<02:29, 3.65s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:32<02:29, 3.74s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:36<02:25, 3.72s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:40<02:28, 3.90s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:44<02:22, 3.86s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:47<02:12, 3.69s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:52<02:16, 3.91s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:55<02:07, 3.76s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [10:59<02:07, 3.87s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:03<02:05, 3.93s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:08<02:06, 4.07s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:12<02:06, 4.22s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:17<02:02, 4.24s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:20<01:50, 3.93s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:23<01:39, 3.70s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:26<01:30, 3.49s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:29<01:25, 3.43s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:32<01:17, 3.24s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:36<01:20, 3.52s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:41<01:23, 3.80s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:44<01:17, 3.70s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:48<01:11, 3.59s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:50<01:04, 3.37s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:54<01:02, 3.45s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [11:59<01:03, 3.75s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:03<01:05, 4.08s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:08<01:03, 4.24s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:11<00:55, 4.00s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:15<00:50, 3.91s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:18<00:44, 3.70s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:22<00:41, 3.77s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:27<00:39, 3.96s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:30<00:34, 3.88s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:33<00:28, 3.61s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:37<00:25, 3.61s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:41<00:22, 3.79s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:45<00:19, 3.89s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:49<00:15, 3.90s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:53<00:11, 3.90s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [12:57<00:07, 3.87s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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 [13:01<00:04, 4.06s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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%|█████████████████████████████████████████████████████████████████████████████████| 221/221 [13:03<00:00, 3.39s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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%|█████████████████████████████████████████████████████████████████████████████████| 221/221 [13:03<00:00, 3.39s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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. +03/01/2022 09:07:59 - INFO - datasets.metric - Removing /home/sanchit_huggingface_co/.cache/huggingface/metrics/wer/default/default_experiment-1-0.arrow +[INFO|configuration_utils.py:438] 2022-03-01 09:07:59,039 >> Configuration saved in ./checkpoint-500/config.json [INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> 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] 2022-03-01 09:08:15,475 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-03-01 08:54:51,979 >> 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] 2022-03-01 09:08:15,475 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-03-01 08:54:51,979 >> 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] 2022-03-01 09:08:15,475 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-03-01 08:54:51,979 >> 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] 2022-03-01 09:08:15,475 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-03-01 08:54:51,979 >> 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.